diff --git "a/checkpoint-2365920/trainer_state.json" "b/checkpoint-2365920/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2365920/trainer_state.json" @@ -0,0 +1,27993 @@ +{ + "best_metric": 3.972705602645874, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/det-noun/lstm/3/checkpoints/checkpoint-2365920", + "epoch": 1.0250006060157382, + "eval_steps": 10, + "global_step": 2365920, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 4.999998362119627e-05, + "loss": 10.8197, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 7.5539, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 7.0582, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 6.9918, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 6.9478, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 6.9292, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 6.7834, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 6.6757, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 6.5691, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 6.4876, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 6.4094, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 6.3303, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 6.2514, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989098268236324e-05, + "loss": 6.1836, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988259673485272e-05, + "loss": 6.1346, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.98742107873422e-05, + "loss": 6.0712, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986582483983168e-05, + "loss": 6.0433, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985743889232116e-05, + "loss": 5.9875, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984905294481064e-05, + "loss": 5.9448, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984066699730012e-05, + "loss": 5.9113, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.8768, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.982391148108281e-05, + "loss": 5.8365, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.981552553357229e-05, + "loss": 5.8086, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.980713958606178e-05, + "loss": 5.7736, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 5.753, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790384069844466e-05, + "loss": 5.7157, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9781998122333946e-05, + "loss": 5.6963, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773612174823426e-05, + "loss": 5.6633, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765258984920364e-05, + "loss": 5.6397, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756873037409844e-05, + "loss": 5.6228, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 5.6018, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 5.5862, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 5.5672, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.9723329247367764e-05, + "loss": 5.5486, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.9714943299857244e-05, + "loss": 5.5339, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970659010995419e-05, + "loss": 5.5162, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969820416244367e-05, + "loss": 5.5024, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968981821493315e-05, + "loss": 5.4744, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.968143226742263e-05, + "loss": 5.4698, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 5.4298, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 5.432, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.96562908036948e-05, + "loss": 5.4221, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964790485618428e-05, + "loss": 5.4198, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963951890867376e-05, + "loss": 5.3826, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.963113296116324e-05, + "loss": 5.3835, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 5.3733, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 5.3656, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 5.3626, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 5.328, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.958920322361064e-05, + "loss": 5.3232, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958085003370758e-05, + "loss": 5.3277, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957246408619706e-05, + "loss": 5.3157, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956407813868654e-05, + "loss": 5.297, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 5.2764, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 5.2807, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 5.2619, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 5.2831, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522148401133936e-05, + "loss": 5.2321, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951376245362342e-05, + "loss": 5.2424, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 5.2307, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 5.2272, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 5.2255, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.948023504238507e-05, + "loss": 5.2025, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947184909487455e-05, + "loss": 5.1847, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946349590497149e-05, + "loss": 5.1901, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945510995746097e-05, + "loss": 5.2013, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944672400995045e-05, + "loss": 5.1712, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 5.1703, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 5.1461, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942156616741889e-05, + "loss": 5.1456, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.9413196598712105e-05, + "loss": 5.1592, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404810651201585e-05, + "loss": 5.1559, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396424703691065e-05, + "loss": 5.1294, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388038756180545e-05, + "loss": 5.1408, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379652808670025e-05, + "loss": 5.1392, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371266861159505e-05, + "loss": 5.1267, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362880913648985e-05, + "loss": 5.0978, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354494966138465e-05, + "loss": 5.1046, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346109018627945e-05, + "loss": 5.0928, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337739449921154e-05, + "loss": 5.0868, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.9329353502410634e-05, + "loss": 5.0845, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932098393370384e-05, + "loss": 5.0824, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931259798619332e-05, + "loss": 5.081, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930421203868281e-05, + "loss": 5.0691, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929582609117229e-05, + "loss": 5.0513, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.928744014366177e-05, + "loss": 5.0523, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927905419615125e-05, + "loss": 5.0518, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927066824864073e-05, + "loss": 5.0437, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.92622823011302e-05, + "loss": 5.0394, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925389635361968e-05, + "loss": 5.0228, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924554316371663e-05, + "loss": 5.0231, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923717359500984e-05, + "loss": 5.0128, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922878764749932e-05, + "loss": 5.0206, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.92204016999888e-05, + "loss": 5.0087, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921201575247828e-05, + "loss": 5.0065, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920362980496776e-05, + "loss": 5.0032, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919524385745724e-05, + "loss": 4.9901, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918685790994672e-05, + "loss": 4.9866, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.91784719624362e-05, + "loss": 4.9784, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917010239372941e-05, + "loss": 4.9735, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.916171644621889e-05, + "loss": 4.9759, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915333049870837e-05, + "loss": 4.9591, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914494455119785e-05, + "loss": 4.9629, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136558603687325e-05, + "loss": 4.9589, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.9128172656176805e-05, + "loss": 4.9462, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.9119786708666285e-05, + "loss": 4.9427, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.9111400761155765e-05, + "loss": 4.9358, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.9103014813645245e-05, + "loss": 4.9357, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909462886613473e-05, + "loss": 4.9267, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908624291862421e-05, + "loss": 4.9306, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907785697111369e-05, + "loss": 4.9208, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.90694874024069e-05, + "loss": 4.9086, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906110145489638e-05, + "loss": 4.9223, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905271550738586e-05, + "loss": 4.9037, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904432955987534e-05, + "loss": 4.9093, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903595999116855e-05, + "loss": 4.904, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902757404365803e-05, + "loss": 4.8987, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901918809614751e-05, + "loss": 4.8941, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901080214863699e-05, + "loss": 4.8883, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.900241620112647e-05, + "loss": 4.9029, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.899403025361595e-05, + "loss": 4.8901, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.898564430610543e-05, + "loss": 4.8729, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.897725835859491e-05, + "loss": 4.8702, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968905168691855e-05, + "loss": 4.8686, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960519221181335e-05, + "loss": 4.862, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952133273670815e-05, + "loss": 4.8551, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943747326160294e-05, + "loss": 4.8582, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935361378649774e-05, + "loss": 4.8441, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.8926975431139254e-05, + "loss": 4.8457, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918589483628734e-05, + "loss": 4.8404, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.8910219914921943e-05, + "loss": 4.8582, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890185034621515e-05, + "loss": 4.8513, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889346439870464e-05, + "loss": 4.833, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888507845119412e-05, + "loss": 4.8326, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.88766925036836e-05, + "loss": 4.8258, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886830655617308e-05, + "loss": 4.8367, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885992060866256e-05, + "loss": 4.8286, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.885155103995577e-05, + "loss": 4.8248, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884316509244525e-05, + "loss": 4.821, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883477914493473e-05, + "loss": 4.8162, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882639319742421e-05, + "loss": 4.8122, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881800724991369e-05, + "loss": 4.8017, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.880962130240316e-05, + "loss": 4.8099, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880123535489264e-05, + "loss": 4.7998, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879284940738212e-05, + "loss": 4.7882, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878447983867534e-05, + "loss": 4.7995, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877609389116482e-05, + "loss": 4.7955, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.87677079436543e-05, + "loss": 4.7967, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875932199614378e-05, + "loss": 4.7854, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875093604863326e-05, + "loss": 4.7819, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.744897842407227, + "eval_runtime": 295.7439, + "eval_samples_per_second": 1290.275, + "eval_steps_per_second": 40.322, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.8742566479926466e-05, + "loss": 4.775, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.8734180532415946e-05, + "loss": 4.7702, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.8725794584905426e-05, + "loss": 4.7849, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.8717408637394906e-05, + "loss": 4.7694, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709022689884386e-05, + "loss": 4.7753, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.8700653121177595e-05, + "loss": 4.7575, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.8692267173667075e-05, + "loss": 4.7725, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.868389760496029e-05, + "loss": 4.7531, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.867551165744977e-05, + "loss": 4.7561, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.866712570993925e-05, + "loss": 4.7534, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.865873976242873e-05, + "loss": 4.7605, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865035381491821e-05, + "loss": 4.7538, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.864198424621142e-05, + "loss": 4.7356, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.86335982987009e-05, + "loss": 4.7392, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862521235119038e-05, + "loss": 4.7325, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.861682640367986e-05, + "loss": 4.7327, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.860845683497307e-05, + "loss": 4.735, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860007088746255e-05, + "loss": 4.7246, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.859168493995203e-05, + "loss": 4.729, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858329899244151e-05, + "loss": 4.7401, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.8574913044930995e-05, + "loss": 4.7267, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.8566527097420475e-05, + "loss": 4.7245, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558141149909955e-05, + "loss": 4.7166, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.8549755202399435e-05, + "loss": 4.7319, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.8541385633692644e-05, + "loss": 4.7007, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.8532999686182124e-05, + "loss": 4.7142, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.8524613738671604e-05, + "loss": 4.7018, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.8516227791161084e-05, + "loss": 4.7046, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.8507841843650564e-05, + "loss": 4.6991, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.8499455896140044e-05, + "loss": 4.6933, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.8491069948629524e-05, + "loss": 4.6997, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848270037992273e-05, + "loss": 4.7063, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847433081121595e-05, + "loss": 4.6926, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846594486370543e-05, + "loss": 4.6983, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845755891619491e-05, + "loss": 4.6845, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844917296868439e-05, + "loss": 4.6897, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.84408033999776e-05, + "loss": 4.677, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843241745246708e-05, + "loss": 4.6853, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842403150495656e-05, + "loss": 4.6615, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.841564555744604e-05, + "loss": 4.6742, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840725960993552e-05, + "loss": 4.669, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.8398873662425e-05, + "loss": 4.6815, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839048771491447e-05, + "loss": 4.6542, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.8382118146207687e-05, + "loss": 4.6706, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.8373732198697167e-05, + "loss": 4.6665, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.8365346251186646e-05, + "loss": 4.6598, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.8356960303676126e-05, + "loss": 4.6699, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.8348574356165606e-05, + "loss": 4.645, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.8340188408655086e-05, + "loss": 4.6464, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.8331802461144566e-05, + "loss": 4.6634, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.8323416513634046e-05, + "loss": 4.6515, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.8315030566123526e-05, + "loss": 4.6456, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.8306644618613006e-05, + "loss": 4.6407, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.8298258671102486e-05, + "loss": 4.6454, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.8289889102395695e-05, + "loss": 4.6347, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.8281519533688904e-05, + "loss": 4.6543, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273133586178384e-05, + "loss": 4.6214, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.826474763866787e-05, + "loss": 4.6326, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.825636169115735e-05, + "loss": 4.6317, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.824797574364683e-05, + "loss": 4.6302, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823958979613631e-05, + "loss": 4.637, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823120384862579e-05, + "loss": 4.6255, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.822281790111527e-05, + "loss": 4.6064, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.821444833240848e-05, + "loss": 4.6129, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820607876370169e-05, + "loss": 4.6376, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.819769281619117e-05, + "loss": 4.6114, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.818930686868065e-05, + "loss": 4.6114, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.818092092117013e-05, + "loss": 4.6049, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.817253497365961e-05, + "loss": 4.6062, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.816414902614909e-05, + "loss": 4.6226, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.815576307863857e-05, + "loss": 4.6209, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.8147393509931785e-05, + "loss": 4.6061, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.8139007562421265e-05, + "loss": 4.6163, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.8130637993714474e-05, + "loss": 4.6221, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.8122252046203954e-05, + "loss": 4.6159, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.8113866098693434e-05, + "loss": 4.5911, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.8105480151182914e-05, + "loss": 4.6058, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.8097094203672393e-05, + "loss": 4.596, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.8088708256161873e-05, + "loss": 4.5968, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808032230865135e-05, + "loss": 4.5936, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.8071936361140827e-05, + "loss": 4.596, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806356679243404e-05, + "loss": 4.6032, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805519722372726e-05, + "loss": 4.5945, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804681127621674e-05, + "loss": 4.5791, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803842532870622e-05, + "loss": 4.583, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.80300393811957e-05, + "loss": 4.585, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.802166981248891e-05, + "loss": 4.5889, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801328386497839e-05, + "loss": 4.5875, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.800489791746787e-05, + "loss": 4.5731, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.799651196995735e-05, + "loss": 4.5812, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.798812602244683e-05, + "loss": 4.5679, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.7979756453740036e-05, + "loss": 4.5801, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.7971370506229516e-05, + "loss": 4.5769, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.7962984558718996e-05, + "loss": 4.5718, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.7954598611208476e-05, + "loss": 4.579, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.7946212663697956e-05, + "loss": 4.5681, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.7937826716187436e-05, + "loss": 4.5664, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.7929440768676916e-05, + "loss": 4.566, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.7921054821166396e-05, + "loss": 4.5683, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.791270163126334e-05, + "loss": 4.5626, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.790431568375282e-05, + "loss": 4.5555, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.78959297362423e-05, + "loss": 4.5604, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.7887543788731774e-05, + "loss": 4.5614, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.7879157841221254e-05, + "loss": 4.5569, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.787078827251447e-05, + "loss": 4.5424, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.786241870380768e-05, + "loss": 4.5536, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.7854032756297166e-05, + "loss": 4.5536, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.7845646808786646e-05, + "loss": 4.5471, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.7837260861276126e-05, + "loss": 4.5477, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.7828874913765606e-05, + "loss": 4.5462, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782048896625508e-05, + "loss": 4.5331, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.781210301874456e-05, + "loss": 4.5527, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.7803733450037775e-05, + "loss": 4.5394, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779534750252725e-05, + "loss": 4.5415, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.778696155501673e-05, + "loss": 4.5389, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777857560750621e-05, + "loss": 4.547, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.777018965999569e-05, + "loss": 4.5373, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.776180371248517e-05, + "loss": 4.5373, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775341776497465e-05, + "loss": 4.5478, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.7745031817464134e-05, + "loss": 4.539, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.7736645869953614e-05, + "loss": 4.5277, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.7728259922443094e-05, + "loss": 4.5292, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.77198903537363e-05, + "loss": 4.5247, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771150440622578e-05, + "loss": 4.523, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770311845871526e-05, + "loss": 4.5257, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769473251120474e-05, + "loss": 4.5223, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768634656369422e-05, + "loss": 4.5148, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.76779606161837e-05, + "loss": 4.5179, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766957466867318e-05, + "loss": 4.5142, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766120509996639e-05, + "loss": 4.5326, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765281915245587e-05, + "loss": 4.5304, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764443320494535e-05, + "loss": 4.5179, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.763604725743483e-05, + "loss": 4.5094, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762767768872805e-05, + "loss": 4.5148, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761929174121753e-05, + "loss": 4.5221, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761090579370701e-05, + "loss": 4.5212, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.760251984619649e-05, + "loss": 4.5123, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.759413389868596e-05, + "loss": 4.5182, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758574795117544e-05, + "loss": 4.5087, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.757737838246866e-05, + "loss": 4.5103, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.7568992434958137e-05, + "loss": 4.5054, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.756060648744761e-05, + "loss": 4.5093, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.755222053993709e-05, + "loss": 4.5029, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.754383459242657e-05, + "loss": 4.4982, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.753544864491605e-05, + "loss": 4.504, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.7527062697405536e-05, + "loss": 4.506, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.7518693128698745e-05, + "loss": 4.5058, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.7510307181188225e-05, + "loss": 4.4957, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.7501921233677705e-05, + "loss": 4.4958, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.465510368347168, + "eval_runtime": 296.4209, + "eval_samples_per_second": 1287.328, + "eval_steps_per_second": 40.23, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.7493535286167185e-05, + "loss": 4.4919, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.7485149338656665e-05, + "loss": 4.4885, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.7476763391146145e-05, + "loss": 4.5034, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.7468377443635625e-05, + "loss": 4.4919, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.7459991496125105e-05, + "loss": 4.5005, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.7451605548614585e-05, + "loss": 4.4836, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.7443219601104065e-05, + "loss": 4.4963, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434833653593545e-05, + "loss": 4.4821, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.7426447706083025e-05, + "loss": 4.4903, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.7418061758572505e-05, + "loss": 4.4854, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.7409675811061985e-05, + "loss": 4.4945, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.7401289863551465e-05, + "loss": 4.4898, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739292029484468e-05, + "loss": 4.4732, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.7384534347334154e-05, + "loss": 4.4797, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.7376148399823634e-05, + "loss": 4.4728, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.7367762452313114e-05, + "loss": 4.4773, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.7359376504802594e-05, + "loss": 4.4768, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.73510069360958e-05, + "loss": 4.4692, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734262098858528e-05, + "loss": 4.4741, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733423504107476e-05, + "loss": 4.4913, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732584909356424e-05, + "loss": 4.4772, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731746314605372e-05, + "loss": 4.474, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.73090771985432e-05, + "loss": 4.4743, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730069125103269e-05, + "loss": 4.4808, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729230530352217e-05, + "loss": 4.456, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728391935601165e-05, + "loss": 4.4675, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727554978730486e-05, + "loss": 4.465, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726716383979434e-05, + "loss": 4.4608, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725877789228382e-05, + "loss": 4.4566, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.72503919447733e-05, + "loss": 4.454, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.724202237606651e-05, + "loss": 4.4633, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723363642855599e-05, + "loss": 4.4717, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.722525048104547e-05, + "loss": 4.4587, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721686453353495e-05, + "loss": 4.4617, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720847858602443e-05, + "loss": 4.4542, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720009263851391e-05, + "loss": 4.4578, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719172306980712e-05, + "loss": 4.4469, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.71833371222966e-05, + "loss": 4.4629, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.717495117478608e-05, + "loss": 4.4348, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.716656522727556e-05, + "loss": 4.4492, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.715817927976504e-05, + "loss": 4.4438, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.7149793332254516e-05, + "loss": 4.4582, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.7141407384743996e-05, + "loss": 4.4357, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.7133021437233476e-05, + "loss": 4.448, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.7124651868526685e-05, + "loss": 4.4483, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.7116265921016165e-05, + "loss": 4.4401, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.7107879973505645e-05, + "loss": 4.4508, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.7099494025995125e-05, + "loss": 4.4317, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.709112445728834e-05, + "loss": 4.4301, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.708273850977782e-05, + "loss": 4.45, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.70743525622673e-05, + "loss": 4.4356, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706596661475678e-05, + "loss": 4.4346, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705759704604999e-05, + "loss": 4.4293, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704921109853947e-05, + "loss": 4.4379, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704082515102895e-05, + "loss": 4.422, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703245558232216e-05, + "loss": 4.4428, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.702406963481164e-05, + "loss": 4.416, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.701568368730112e-05, + "loss": 4.4285, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.70072977397906e-05, + "loss": 4.4317, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.699891179228008e-05, + "loss": 4.4245, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699052584476956e-05, + "loss": 4.4308, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.6982139897259045e-05, + "loss": 4.4277, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.6973770328552254e-05, + "loss": 4.4051, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.6965384381041734e-05, + "loss": 4.4161, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.6956998433531214e-05, + "loss": 4.4286, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.6948612486020694e-05, + "loss": 4.419, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.69402429173139e-05, + "loss": 4.4179, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693185696980338e-05, + "loss": 4.4048, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692347102229286e-05, + "loss": 4.4108, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691508507478234e-05, + "loss": 4.4298, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690671550607555e-05, + "loss": 4.4259, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689832955856503e-05, + "loss": 4.4106, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.688994361105451e-05, + "loss": 4.4259, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.6881557663544e-05, + "loss": 4.4306, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.687317171603348e-05, + "loss": 4.4292, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.686478576852296e-05, + "loss": 4.3976, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.685639982101244e-05, + "loss": 4.4197, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.684803025230565e-05, + "loss": 4.4098, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683964430479513e-05, + "loss": 4.4071, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.683127473608834e-05, + "loss": 4.4117, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.682288878857782e-05, + "loss": 4.4105, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.68145028410673e-05, + "loss": 4.415, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.680611689355678e-05, + "loss": 4.4143, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679773094604626e-05, + "loss": 4.3937, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.6789361377339466e-05, + "loss": 4.4029, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678097542982895e-05, + "loss": 4.4029, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.677258948231843e-05, + "loss": 4.4074, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676420353480791e-05, + "loss": 4.4088, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675583396610112e-05, + "loss": 4.3935, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.67474480185906e-05, + "loss": 4.4035, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.673906207108008e-05, + "loss": 4.3908, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.673067612356956e-05, + "loss": 4.4026, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.672229017605904e-05, + "loss": 4.3998, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671390422854852e-05, + "loss": 4.398, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670553465984173e-05, + "loss": 4.4029, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.669714871233121e-05, + "loss": 4.3989, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.668876276482069e-05, + "loss": 4.3911, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668037681731017e-05, + "loss": 4.3964, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667199086979965e-05, + "loss": 4.3977, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666360492228913e-05, + "loss": 4.3951, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665521897477861e-05, + "loss": 4.3818, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664683302726809e-05, + "loss": 4.3906, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.66384634585613e-05, + "loss": 4.3941, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663007751105078e-05, + "loss": 4.3902, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662169156354026e-05, + "loss": 4.3702, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661332199483347e-05, + "loss": 4.3852, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660493604732295e-05, + "loss": 4.3919, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659655009981243e-05, + "loss": 4.3812, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.658816415230191e-05, + "loss": 4.3821, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.6579794583595124e-05, + "loss": 4.3844, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.6571408636084604e-05, + "loss": 4.3726, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.6563022688574084e-05, + "loss": 4.3897, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655465311986729e-05, + "loss": 4.3734, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654626717235677e-05, + "loss": 4.3824, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.653788122484625e-05, + "loss": 4.3812, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652949527733573e-05, + "loss": 4.3848, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.652110932982521e-05, + "loss": 4.3766, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651272338231469e-05, + "loss": 4.3814, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650433743480417e-05, + "loss": 4.3872, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649595148729365e-05, + "loss": 4.382, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648756553978313e-05, + "loss": 4.3686, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.647919597107634e-05, + "loss": 4.3718, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.647081002356582e-05, + "loss": 4.3679, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.646242407605531e-05, + "loss": 4.3723, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645403812854479e-05, + "loss": 4.3677, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644565218103427e-05, + "loss": 4.3717, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.643726623352375e-05, + "loss": 4.3579, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.642888028601323e-05, + "loss": 4.3657, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642051071730644e-05, + "loss": 4.3611, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.641212476979592e-05, + "loss": 4.3815, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.64037388222854e-05, + "loss": 4.3788, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.639535287477488e-05, + "loss": 4.3716, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.638696692726436e-05, + "loss": 4.3575, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637858097975383e-05, + "loss": 4.3653, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.637019503224331e-05, + "loss": 4.3737, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636180908473279e-05, + "loss": 4.3708, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.6353439516026006e-05, + "loss": 4.3656, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.634508632612295e-05, + "loss": 4.3702, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633670037861243e-05, + "loss": 4.3619, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.632831443110191e-05, + "loss": 4.3698, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.631992848359139e-05, + "loss": 4.3528, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.631154253608087e-05, + "loss": 4.3669, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.630315658857035e-05, + "loss": 4.3571, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629477064105983e-05, + "loss": 4.3514, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.6286384693549304e-05, + "loss": 4.3604, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.6277998746038784e-05, + "loss": 4.3645, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.6269612798528264e-05, + "loss": 4.36, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.6261226851017744e-05, + "loss": 4.3546, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625284090350723e-05, + "loss": 4.3518, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 4.331331253051758, + "eval_runtime": 292.666, + "eval_samples_per_second": 1303.845, + "eval_steps_per_second": 40.746, + "step": 228960 + }, + { + "epoch": 0.0, + "learning_rate": 4.624445495599671e-05, + "loss": 4.3551, + "step": 229376 + }, + { + "epoch": 0.0, + "learning_rate": 4.623606900848619e-05, + "loss": 4.3451, + "step": 229888 + }, + { + "epoch": 0.0, + "learning_rate": 4.622768306097567e-05, + "loss": 4.3621, + "step": 230400 + }, + { + "epoch": 0.0, + "learning_rate": 4.621929711346515e-05, + "loss": 4.3482, + "step": 230912 + }, + { + "epoch": 0.0, + "learning_rate": 4.621091116595463e-05, + "loss": 4.366, + "step": 231424 + }, + { + "epoch": 0.0, + "learning_rate": 4.620252521844411e-05, + "loss": 4.3413, + "step": 231936 + }, + { + "epoch": 0.0, + "learning_rate": 4.619413927093359e-05, + "loss": 4.3591, + "step": 232448 + }, + { + "epoch": 0.0, + "learning_rate": 4.618575332342307e-05, + "loss": 4.3423, + "step": 232960 + }, + { + "epoch": 0.0, + "learning_rate": 4.6177367375912543e-05, + "loss": 4.3547, + "step": 233472 + }, + { + "epoch": 0.0, + "learning_rate": 4.6168981428402023e-05, + "loss": 4.3508, + "step": 233984 + }, + { + "epoch": 0.0, + "learning_rate": 4.61605954808915e-05, + "loss": 4.3511, + "step": 234496 + }, + { + "epoch": 0.0, + "learning_rate": 4.615220953338098e-05, + "loss": 4.3575, + "step": 235008 + }, + { + "epoch": 0.0, + "learning_rate": 4.61438399646742e-05, + "loss": 4.337, + "step": 235520 + }, + { + "epoch": 0.0, + "learning_rate": 4.613545401716368e-05, + "loss": 4.3444, + "step": 236032 + }, + { + "epoch": 0.0, + "learning_rate": 4.612706806965316e-05, + "loss": 4.3392, + "step": 236544 + }, + { + "epoch": 0.0, + "learning_rate": 4.611868212214264e-05, + "loss": 4.3427, + "step": 237056 + }, + { + "epoch": 0.0, + "learning_rate": 4.611029617463212e-05, + "loss": 4.34, + "step": 237568 + }, + { + "epoch": 0.0, + "learning_rate": 4.61019102271216e-05, + "loss": 4.3395, + "step": 238080 + }, + { + "epoch": 0.0, + "learning_rate": 4.609352427961108e-05, + "loss": 4.3409, + "step": 238592 + }, + { + "epoch": 0.0, + "learning_rate": 4.608513833210056e-05, + "loss": 4.3578, + "step": 239104 + }, + { + "epoch": 0.0, + "learning_rate": 4.607676876339377e-05, + "loss": 4.3432, + "step": 239616 + }, + { + "epoch": 0.0, + "learning_rate": 4.606838281588325e-05, + "loss": 4.3429, + "step": 240128 + }, + { + "epoch": 0.0, + "learning_rate": 4.605999686837273e-05, + "loss": 4.3457, + "step": 240640 + }, + { + "epoch": 0.0, + "learning_rate": 4.605161092086221e-05, + "loss": 4.3473, + "step": 241152 + }, + { + "epoch": 0.0, + "learning_rate": 4.604324135215542e-05, + "loss": 4.3271, + "step": 241664 + }, + { + "epoch": 0.0, + "learning_rate": 4.60348554046449e-05, + "loss": 4.3454, + "step": 242176 + }, + { + "epoch": 0.0, + "learning_rate": 4.602646945713438e-05, + "loss": 4.3298, + "step": 242688 + }, + { + "epoch": 0.0, + "learning_rate": 4.6018083509623864e-05, + "loss": 4.3323, + "step": 243200 + }, + { + "epoch": 0.0, + "learning_rate": 4.6009697562113344e-05, + "loss": 4.3258, + "step": 243712 + }, + { + "epoch": 0.01, + "learning_rate": 4.6001311614602824e-05, + "loss": 4.3327, + "step": 244224 + }, + { + "epoch": 0.01, + "learning_rate": 4.5992925667092303e-05, + "loss": 4.3314, + "step": 244736 + }, + { + "epoch": 0.01, + "learning_rate": 4.598455609838551e-05, + "loss": 4.346, + "step": 245248 + }, + { + "epoch": 0.01, + "learning_rate": 4.597617015087499e-05, + "loss": 4.3346, + "step": 245760 + }, + { + "epoch": 0.01, + "learning_rate": 4.596778420336447e-05, + "loss": 4.3361, + "step": 246272 + }, + { + "epoch": 0.01, + "learning_rate": 4.595941463465768e-05, + "loss": 4.3256, + "step": 246784 + }, + { + "epoch": 0.01, + "learning_rate": 4.595102868714716e-05, + "loss": 4.3362, + "step": 247296 + }, + { + "epoch": 0.01, + "learning_rate": 4.594264273963664e-05, + "loss": 4.3199, + "step": 247808 + }, + { + "epoch": 0.01, + "learning_rate": 4.593425679212612e-05, + "loss": 4.3402, + "step": 248320 + }, + { + "epoch": 0.01, + "learning_rate": 4.59258708446156e-05, + "loss": 4.3121, + "step": 248832 + }, + { + "epoch": 0.01, + "learning_rate": 4.591748489710508e-05, + "loss": 4.3235, + "step": 249344 + }, + { + "epoch": 0.01, + "learning_rate": 4.590909894959456e-05, + "loss": 4.324, + "step": 249856 + }, + { + "epoch": 0.01, + "learning_rate": 4.590071300208404e-05, + "loss": 4.3371, + "step": 250368 + }, + { + "epoch": 0.01, + "learning_rate": 4.589232705457352e-05, + "loss": 4.317, + "step": 250880 + }, + { + "epoch": 0.01, + "learning_rate": 4.5883941107063e-05, + "loss": 4.324, + "step": 251392 + }, + { + "epoch": 0.01, + "learning_rate": 4.587555515955248e-05, + "loss": 4.3262, + "step": 251904 + }, + { + "epoch": 0.01, + "learning_rate": 4.586716921204196e-05, + "loss": 4.3223, + "step": 252416 + }, + { + "epoch": 0.01, + "learning_rate": 4.585879964333517e-05, + "loss": 4.3293, + "step": 252928 + }, + { + "epoch": 0.01, + "learning_rate": 4.585043007462838e-05, + "loss": 4.3147, + "step": 253440 + }, + { + "epoch": 0.01, + "learning_rate": 4.584204412711786e-05, + "loss": 4.3066, + "step": 253952 + }, + { + "epoch": 0.01, + "learning_rate": 4.583365817960734e-05, + "loss": 4.3274, + "step": 254464 + }, + { + "epoch": 0.01, + "learning_rate": 4.5825288610900555e-05, + "loss": 4.3179, + "step": 254976 + }, + { + "epoch": 0.01, + "learning_rate": 4.5816902663390035e-05, + "loss": 4.3142, + "step": 255488 + }, + { + "epoch": 0.01, + "learning_rate": 4.5808516715879515e-05, + "loss": 4.3152, + "step": 256000 + }, + { + "epoch": 0.01, + "learning_rate": 4.5800130768368995e-05, + "loss": 4.3189, + "step": 256512 + }, + { + "epoch": 0.01, + "learning_rate": 4.5791744820858475e-05, + "loss": 4.3028, + "step": 257024 + }, + { + "epoch": 0.01, + "learning_rate": 4.5783358873347955e-05, + "loss": 4.3259, + "step": 257536 + }, + { + "epoch": 0.01, + "learning_rate": 4.5774972925837435e-05, + "loss": 4.2986, + "step": 258048 + }, + { + "epoch": 0.01, + "learning_rate": 4.5766586978326915e-05, + "loss": 4.3122, + "step": 258560 + }, + { + "epoch": 0.01, + "learning_rate": 4.5758201030816395e-05, + "loss": 4.3129, + "step": 259072 + }, + { + "epoch": 0.01, + "learning_rate": 4.5749831462109604e-05, + "loss": 4.3149, + "step": 259584 + }, + { + "epoch": 0.01, + "learning_rate": 4.5741445514599084e-05, + "loss": 4.3106, + "step": 260096 + }, + { + "epoch": 0.01, + "learning_rate": 4.5733059567088564e-05, + "loss": 4.3151, + "step": 260608 + }, + { + "epoch": 0.01, + "learning_rate": 4.5724673619578044e-05, + "loss": 4.2894, + "step": 261120 + }, + { + "epoch": 0.01, + "learning_rate": 4.5716287672067524e-05, + "loss": 4.3064, + "step": 261632 + }, + { + "epoch": 0.01, + "learning_rate": 4.570791810336074e-05, + "loss": 4.3133, + "step": 262144 + }, + { + "epoch": 0.01, + "learning_rate": 4.569953215585022e-05, + "loss": 4.3085, + "step": 262656 + }, + { + "epoch": 0.01, + "learning_rate": 4.56911462083397e-05, + "loss": 4.3005, + "step": 263168 + }, + { + "epoch": 0.01, + "learning_rate": 4.568276026082918e-05, + "loss": 4.2996, + "step": 263680 + }, + { + "epoch": 0.01, + "learning_rate": 4.567437431331866e-05, + "loss": 4.2969, + "step": 264192 + }, + { + "epoch": 0.01, + "learning_rate": 4.566598836580814e-05, + "loss": 4.3105, + "step": 264704 + }, + { + "epoch": 0.01, + "learning_rate": 4.565760241829762e-05, + "loss": 4.3162, + "step": 265216 + }, + { + "epoch": 0.01, + "learning_rate": 4.564921647078709e-05, + "loss": 4.3011, + "step": 265728 + }, + { + "epoch": 0.01, + "learning_rate": 4.564084690208031e-05, + "loss": 4.3141, + "step": 266240 + }, + { + "epoch": 0.01, + "learning_rate": 4.563247733337352e-05, + "loss": 4.3199, + "step": 266752 + }, + { + "epoch": 0.01, + "learning_rate": 4.5624091385863e-05, + "loss": 4.3225, + "step": 267264 + }, + { + "epoch": 0.01, + "learning_rate": 4.561570543835248e-05, + "loss": 4.2844, + "step": 267776 + }, + { + "epoch": 0.01, + "learning_rate": 4.560731949084196e-05, + "loss": 4.3061, + "step": 268288 + }, + { + "epoch": 0.01, + "learning_rate": 4.559893354333144e-05, + "loss": 4.3072, + "step": 268800 + }, + { + "epoch": 0.01, + "learning_rate": 4.559054759582092e-05, + "loss": 4.2949, + "step": 269312 + }, + { + "epoch": 0.01, + "learning_rate": 4.558217802711413e-05, + "loss": 4.3042, + "step": 269824 + }, + { + "epoch": 0.01, + "learning_rate": 4.557379207960361e-05, + "loss": 4.3042, + "step": 270336 + }, + { + "epoch": 0.01, + "learning_rate": 4.556540613209309e-05, + "loss": 4.309, + "step": 270848 + }, + { + "epoch": 0.01, + "learning_rate": 4.5557020184582566e-05, + "loss": 4.2984, + "step": 271360 + }, + { + "epoch": 0.01, + "learning_rate": 4.5548634237072046e-05, + "loss": 4.2924, + "step": 271872 + }, + { + "epoch": 0.01, + "learning_rate": 4.554026466836526e-05, + "loss": 4.2946, + "step": 272384 + }, + { + "epoch": 0.01, + "learning_rate": 4.553187872085474e-05, + "loss": 4.2939, + "step": 272896 + }, + { + "epoch": 0.01, + "learning_rate": 4.5523492773344215e-05, + "loss": 4.3011, + "step": 273408 + }, + { + "epoch": 0.01, + "learning_rate": 4.5515106825833695e-05, + "loss": 4.3032, + "step": 273920 + }, + { + "epoch": 0.01, + "learning_rate": 4.550673725712691e-05, + "loss": 4.2879, + "step": 274432 + }, + { + "epoch": 0.02, + "learning_rate": 4.549835130961639e-05, + "loss": 4.2969, + "step": 274944 + }, + { + "epoch": 0.02, + "learning_rate": 4.548996536210587e-05, + "loss": 4.2848, + "step": 275456 + }, + { + "epoch": 0.02, + "learning_rate": 4.548157941459535e-05, + "loss": 4.294, + "step": 275968 + }, + { + "epoch": 0.02, + "learning_rate": 4.547319346708483e-05, + "loss": 4.2962, + "step": 276480 + }, + { + "epoch": 0.02, + "learning_rate": 4.546480751957431e-05, + "loss": 4.2902, + "step": 276992 + }, + { + "epoch": 0.02, + "learning_rate": 4.545643795086752e-05, + "loss": 4.3016, + "step": 277504 + }, + { + "epoch": 0.02, + "learning_rate": 4.5448052003357e-05, + "loss": 4.2947, + "step": 278016 + }, + { + "epoch": 0.02, + "learning_rate": 4.543966605584648e-05, + "loss": 4.2885, + "step": 278528 + }, + { + "epoch": 0.02, + "learning_rate": 4.543128010833596e-05, + "loss": 4.2925, + "step": 279040 + }, + { + "epoch": 0.02, + "learning_rate": 4.542289416082544e-05, + "loss": 4.2955, + "step": 279552 + }, + { + "epoch": 0.02, + "learning_rate": 4.541452459211865e-05, + "loss": 4.2965, + "step": 280064 + }, + { + "epoch": 0.02, + "learning_rate": 4.540613864460813e-05, + "loss": 4.2782, + "step": 280576 + }, + { + "epoch": 0.02, + "learning_rate": 4.539775269709761e-05, + "loss": 4.2883, + "step": 281088 + }, + { + "epoch": 0.02, + "learning_rate": 4.5389366749587095e-05, + "loss": 4.2925, + "step": 281600 + }, + { + "epoch": 0.02, + "learning_rate": 4.5380980802076575e-05, + "loss": 4.2926, + "step": 282112 + }, + { + "epoch": 0.02, + "learning_rate": 4.5372594854566055e-05, + "loss": 4.2727, + "step": 282624 + }, + { + "epoch": 0.02, + "learning_rate": 4.5364225285859264e-05, + "loss": 4.2787, + "step": 283136 + }, + { + "epoch": 0.02, + "learning_rate": 4.5355839338348744e-05, + "loss": 4.2918, + "step": 283648 + }, + { + "epoch": 0.02, + "learning_rate": 4.5347453390838224e-05, + "loss": 4.2817, + "step": 284160 + }, + { + "epoch": 0.02, + "learning_rate": 4.5339067443327704e-05, + "loss": 4.2802, + "step": 284672 + }, + { + "epoch": 0.02, + "learning_rate": 4.5330681495817184e-05, + "loss": 4.2808, + "step": 285184 + }, + { + "epoch": 0.02, + "learning_rate": 4.5322295548306664e-05, + "loss": 4.2803, + "step": 285696 + }, + { + "epoch": 0.02, + "learning_rate": 4.5313909600796144e-05, + "loss": 4.2835, + "step": 286208 + }, + { + "epoch": 0.02, + "learning_rate": 4.5305523653285624e-05, + "loss": 4.2799, + "step": 286720 + }, + { + "epoch": 0.02, + "learning_rate": 4.5297137705775104e-05, + "loss": 4.2774, + "step": 287232 + }, + { + "epoch": 0.02, + "learning_rate": 4.528880089467578e-05, + "loss": 4.2835, + "step": 287744 + }, + { + "epoch": 0.02, + "learning_rate": 4.528041494716526e-05, + "loss": 4.2875, + "step": 288256 + }, + { + "epoch": 0.02, + "learning_rate": 4.527202899965474e-05, + "loss": 4.2857, + "step": 288768 + }, + { + "epoch": 0.02, + "learning_rate": 4.526364305214422e-05, + "loss": 4.2763, + "step": 289280 + }, + { + "epoch": 0.02, + "learning_rate": 4.525527348343743e-05, + "loss": 4.2918, + "step": 289792 + }, + { + "epoch": 0.02, + "learning_rate": 4.524688753592691e-05, + "loss": 4.2842, + "step": 290304 + }, + { + "epoch": 0.02, + "learning_rate": 4.523850158841639e-05, + "loss": 4.2698, + "step": 290816 + }, + { + "epoch": 0.02, + "learning_rate": 4.523011564090587e-05, + "loss": 4.2756, + "step": 291328 + }, + { + "epoch": 0.02, + "learning_rate": 4.522172969339535e-05, + "loss": 4.2718, + "step": 291840 + }, + { + "epoch": 0.02, + "learning_rate": 4.521334374588483e-05, + "loss": 4.2778, + "step": 292352 + }, + { + "epoch": 0.02, + "learning_rate": 4.520495779837431e-05, + "loss": 4.2681, + "step": 292864 + }, + { + "epoch": 0.02, + "learning_rate": 4.519657185086379e-05, + "loss": 4.2782, + "step": 293376 + }, + { + "epoch": 0.02, + "learning_rate": 4.5188202282157e-05, + "loss": 4.2632, + "step": 293888 + }, + { + "epoch": 0.02, + "learning_rate": 4.517981633464648e-05, + "loss": 4.2706, + "step": 294400 + }, + { + "epoch": 0.02, + "learning_rate": 4.517143038713596e-05, + "loss": 4.2673, + "step": 294912 + }, + { + "epoch": 0.02, + "learning_rate": 4.516304443962544e-05, + "loss": 4.2864, + "step": 295424 + }, + { + "epoch": 0.02, + "learning_rate": 4.515465849211492e-05, + "loss": 4.2798, + "step": 295936 + }, + { + "epoch": 0.02, + "learning_rate": 4.514628892340813e-05, + "loss": 4.2795, + "step": 296448 + }, + { + "epoch": 0.02, + "learning_rate": 4.513790297589761e-05, + "loss": 4.2638, + "step": 296960 + }, + { + "epoch": 0.02, + "learning_rate": 4.512951702838709e-05, + "loss": 4.2741, + "step": 297472 + }, + { + "epoch": 0.02, + "learning_rate": 4.512113108087657e-05, + "loss": 4.2819, + "step": 297984 + }, + { + "epoch": 0.02, + "learning_rate": 4.5112745133366045e-05, + "loss": 4.273, + "step": 298496 + }, + { + "epoch": 0.02, + "learning_rate": 4.5104359185855525e-05, + "loss": 4.2707, + "step": 299008 + }, + { + "epoch": 0.02, + "learning_rate": 4.5095973238345005e-05, + "loss": 4.2785, + "step": 299520 + }, + { + "epoch": 0.02, + "learning_rate": 4.5087587290834485e-05, + "loss": 4.2708, + "step": 300032 + }, + { + "epoch": 0.02, + "learning_rate": 4.50792177221277e-05, + "loss": 4.2787, + "step": 300544 + }, + { + "epoch": 0.02, + "learning_rate": 4.507083177461718e-05, + "loss": 4.2578, + "step": 301056 + }, + { + "epoch": 0.02, + "learning_rate": 4.506244582710666e-05, + "loss": 4.2754, + "step": 301568 + }, + { + "epoch": 0.02, + "learning_rate": 4.505405987959614e-05, + "loss": 4.2647, + "step": 302080 + }, + { + "epoch": 0.02, + "learning_rate": 4.504569031088935e-05, + "loss": 4.2626, + "step": 302592 + }, + { + "epoch": 0.02, + "learning_rate": 4.503730436337883e-05, + "loss": 4.2666, + "step": 303104 + }, + { + "epoch": 0.02, + "learning_rate": 4.502891841586831e-05, + "loss": 4.2749, + "step": 303616 + }, + { + "epoch": 0.02, + "learning_rate": 4.502053246835779e-05, + "loss": 4.2678, + "step": 304128 + }, + { + "epoch": 0.02, + "learning_rate": 4.5012179278454734e-05, + "loss": 4.2608, + "step": 304640 + }, + { + "epoch": 0.02, + "learning_rate": 4.5003793330944214e-05, + "loss": 4.2646, + "step": 305152 + }, + { + "epoch": 0.03, + "eval_loss": 4.249505043029785, + "eval_runtime": 300.0913, + "eval_samples_per_second": 1271.583, + "eval_steps_per_second": 39.738, + "step": 305280 + }, + { + "epoch": 1.0, + "learning_rate": 4.4995407383433694e-05, + "loss": 4.2665, + "step": 305664 + }, + { + "epoch": 1.0, + "learning_rate": 4.4987021435923174e-05, + "loss": 4.2588, + "step": 306176 + }, + { + "epoch": 1.0, + "learning_rate": 4.4978635488412654e-05, + "loss": 4.269, + "step": 306688 + }, + { + "epoch": 1.0, + "learning_rate": 4.4970249540902134e-05, + "loss": 4.2612, + "step": 307200 + }, + { + "epoch": 1.0, + "learning_rate": 4.4961863593391614e-05, + "loss": 4.2748, + "step": 307712 + }, + { + "epoch": 1.0, + "learning_rate": 4.4953477645881094e-05, + "loss": 4.259, + "step": 308224 + }, + { + "epoch": 1.0, + "learning_rate": 4.49451080771743e-05, + "loss": 4.2646, + "step": 308736 + }, + { + "epoch": 1.0, + "learning_rate": 4.493672212966378e-05, + "loss": 4.2557, + "step": 309248 + }, + { + "epoch": 1.0, + "learning_rate": 4.492833618215326e-05, + "loss": 4.2646, + "step": 309760 + }, + { + "epoch": 1.0, + "learning_rate": 4.491995023464274e-05, + "loss": 4.2671, + "step": 310272 + }, + { + "epoch": 1.0, + "learning_rate": 4.491158066593595e-05, + "loss": 4.2622, + "step": 310784 + }, + { + "epoch": 1.0, + "learning_rate": 4.490319471842543e-05, + "loss": 4.2652, + "step": 311296 + }, + { + "epoch": 1.0, + "learning_rate": 4.489482514971865e-05, + "loss": 4.2512, + "step": 311808 + }, + { + "epoch": 1.0, + "learning_rate": 4.488643920220813e-05, + "loss": 4.2573, + "step": 312320 + }, + { + "epoch": 1.0, + "learning_rate": 4.487805325469761e-05, + "loss": 4.2555, + "step": 312832 + }, + { + "epoch": 1.0, + "learning_rate": 4.486966730718709e-05, + "loss": 4.2533, + "step": 313344 + }, + { + "epoch": 1.0, + "learning_rate": 4.486128135967657e-05, + "loss": 4.2554, + "step": 313856 + }, + { + "epoch": 1.0, + "learning_rate": 4.485289541216605e-05, + "loss": 4.2541, + "step": 314368 + }, + { + "epoch": 1.0, + "learning_rate": 4.484450946465553e-05, + "loss": 4.2545, + "step": 314880 + }, + { + "epoch": 1.0, + "learning_rate": 4.483612351714501e-05, + "loss": 4.267, + "step": 315392 + }, + { + "epoch": 1.0, + "learning_rate": 4.482773756963449e-05, + "loss": 4.262, + "step": 315904 + }, + { + "epoch": 1.0, + "learning_rate": 4.481935162212397e-05, + "loss": 4.2558, + "step": 316416 + }, + { + "epoch": 1.0, + "learning_rate": 4.481096567461345e-05, + "loss": 4.2619, + "step": 316928 + }, + { + "epoch": 1.0, + "learning_rate": 4.480257972710293e-05, + "loss": 4.2616, + "step": 317440 + }, + { + "epoch": 1.0, + "learning_rate": 4.4794226537199866e-05, + "loss": 4.2411, + "step": 317952 + }, + { + "epoch": 1.0, + "learning_rate": 4.4785840589689346e-05, + "loss": 4.2596, + "step": 318464 + }, + { + "epoch": 1.0, + "learning_rate": 4.4777454642178825e-05, + "loss": 4.2468, + "step": 318976 + }, + { + "epoch": 1.0, + "learning_rate": 4.476906869466831e-05, + "loss": 4.2453, + "step": 319488 + }, + { + "epoch": 1.0, + "learning_rate": 4.476068274715779e-05, + "loss": 4.2413, + "step": 320000 + }, + { + "epoch": 1.0, + "learning_rate": 4.475229679964727e-05, + "loss": 4.2509, + "step": 320512 + }, + { + "epoch": 1.01, + "learning_rate": 4.474392723094048e-05, + "loss": 4.2484, + "step": 321024 + }, + { + "epoch": 1.01, + "learning_rate": 4.473554128342996e-05, + "loss": 4.2603, + "step": 321536 + }, + { + "epoch": 1.01, + "learning_rate": 4.472715533591944e-05, + "loss": 4.2528, + "step": 322048 + }, + { + "epoch": 1.01, + "learning_rate": 4.471876938840892e-05, + "loss": 4.2506, + "step": 322560 + }, + { + "epoch": 1.01, + "learning_rate": 4.47103834408984e-05, + "loss": 4.2445, + "step": 323072 + }, + { + "epoch": 1.01, + "learning_rate": 4.470201387219161e-05, + "loss": 4.2517, + "step": 323584 + }, + { + "epoch": 1.01, + "learning_rate": 4.469362792468109e-05, + "loss": 4.2425, + "step": 324096 + }, + { + "epoch": 1.01, + "learning_rate": 4.468524197717057e-05, + "loss": 4.2524, + "step": 324608 + }, + { + "epoch": 1.01, + "learning_rate": 4.467685602966005e-05, + "loss": 4.2307, + "step": 325120 + }, + { + "epoch": 1.01, + "learning_rate": 4.4668486460953266e-05, + "loss": 4.2388, + "step": 325632 + }, + { + "epoch": 1.01, + "learning_rate": 4.4660100513442746e-05, + "loss": 4.2426, + "step": 326144 + }, + { + "epoch": 1.01, + "learning_rate": 4.4651714565932226e-05, + "loss": 4.2553, + "step": 326656 + }, + { + "epoch": 1.01, + "learning_rate": 4.4643328618421706e-05, + "loss": 4.2399, + "step": 327168 + }, + { + "epoch": 1.01, + "learning_rate": 4.463494267091118e-05, + "loss": 4.2423, + "step": 327680 + }, + { + "epoch": 1.01, + "learning_rate": 4.462655672340066e-05, + "loss": 4.2449, + "step": 328192 + }, + { + "epoch": 1.01, + "learning_rate": 4.461817077589014e-05, + "loss": 4.2402, + "step": 328704 + }, + { + "epoch": 1.01, + "learning_rate": 4.460978482837962e-05, + "loss": 4.2495, + "step": 329216 + }, + { + "epoch": 1.01, + "learning_rate": 4.46013988808691e-05, + "loss": 4.2368, + "step": 329728 + }, + { + "epoch": 1.01, + "learning_rate": 4.459301293335858e-05, + "loss": 4.2253, + "step": 330240 + }, + { + "epoch": 1.01, + "learning_rate": 4.458462698584806e-05, + "loss": 4.2455, + "step": 330752 + }, + { + "epoch": 1.01, + "learning_rate": 4.457624103833754e-05, + "loss": 4.2352, + "step": 331264 + }, + { + "epoch": 1.01, + "learning_rate": 4.456787146963075e-05, + "loss": 4.2382, + "step": 331776 + }, + { + "epoch": 1.01, + "learning_rate": 4.4559485522120234e-05, + "loss": 4.2328, + "step": 332288 + }, + { + "epoch": 1.01, + "learning_rate": 4.4551099574609714e-05, + "loss": 4.2415, + "step": 332800 + }, + { + "epoch": 1.01, + "learning_rate": 4.4542713627099194e-05, + "loss": 4.2265, + "step": 333312 + }, + { + "epoch": 1.01, + "learning_rate": 4.453436043719613e-05, + "loss": 4.2403, + "step": 333824 + }, + { + "epoch": 1.01, + "learning_rate": 4.452597448968561e-05, + "loss": 4.2231, + "step": 334336 + }, + { + "epoch": 1.01, + "learning_rate": 4.451758854217509e-05, + "loss": 4.2318, + "step": 334848 + }, + { + "epoch": 1.01, + "learning_rate": 4.450920259466457e-05, + "loss": 4.2358, + "step": 335360 + }, + { + "epoch": 1.01, + "learning_rate": 4.450081664715405e-05, + "loss": 4.2348, + "step": 335872 + }, + { + "epoch": 1.01, + "learning_rate": 4.449243069964353e-05, + "loss": 4.2316, + "step": 336384 + }, + { + "epoch": 1.01, + "learning_rate": 4.448404475213301e-05, + "loss": 4.2411, + "step": 336896 + }, + { + "epoch": 1.01, + "learning_rate": 4.447565880462249e-05, + "loss": 4.2141, + "step": 337408 + }, + { + "epoch": 1.01, + "learning_rate": 4.44672892359157e-05, + "loss": 4.2253, + "step": 337920 + }, + { + "epoch": 1.01, + "learning_rate": 4.445890328840519e-05, + "loss": 4.2358, + "step": 338432 + }, + { + "epoch": 1.01, + "learning_rate": 4.44505337196984e-05, + "loss": 4.2297, + "step": 338944 + }, + { + "epoch": 1.01, + "learning_rate": 4.444214777218788e-05, + "loss": 4.2284, + "step": 339456 + }, + { + "epoch": 1.01, + "learning_rate": 4.443376182467736e-05, + "loss": 4.2198, + "step": 339968 + }, + { + "epoch": 1.01, + "learning_rate": 4.442537587716684e-05, + "loss": 4.2204, + "step": 340480 + }, + { + "epoch": 1.01, + "learning_rate": 4.441698992965632e-05, + "loss": 4.2344, + "step": 340992 + }, + { + "epoch": 1.01, + "learning_rate": 4.44086039821458e-05, + "loss": 4.2384, + "step": 341504 + }, + { + "epoch": 1.01, + "learning_rate": 4.440021803463528e-05, + "loss": 4.2296, + "step": 342016 + }, + { + "epoch": 1.01, + "learning_rate": 4.439183208712476e-05, + "loss": 4.2342, + "step": 342528 + }, + { + "epoch": 1.01, + "learning_rate": 4.4383462518417966e-05, + "loss": 4.2422, + "step": 343040 + }, + { + "epoch": 1.01, + "learning_rate": 4.4375092949711175e-05, + "loss": 4.2489, + "step": 343552 + }, + { + "epoch": 1.01, + "learning_rate": 4.4366707002200655e-05, + "loss": 4.2144, + "step": 344064 + }, + { + "epoch": 1.01, + "learning_rate": 4.435832105469014e-05, + "loss": 4.226, + "step": 344576 + }, + { + "epoch": 1.01, + "learning_rate": 4.434993510717962e-05, + "loss": 4.2369, + "step": 345088 + }, + { + "epoch": 1.01, + "learning_rate": 4.43415491596691e-05, + "loss": 4.2153, + "step": 345600 + }, + { + "epoch": 1.01, + "learning_rate": 4.433317959096231e-05, + "loss": 4.2324, + "step": 346112 + }, + { + "epoch": 1.01, + "learning_rate": 4.432479364345179e-05, + "loss": 4.228, + "step": 346624 + }, + { + "epoch": 1.01, + "learning_rate": 4.431640769594127e-05, + "loss": 4.2336, + "step": 347136 + }, + { + "epoch": 1.01, + "learning_rate": 4.430802174843075e-05, + "loss": 4.229, + "step": 347648 + }, + { + "epoch": 1.01, + "learning_rate": 4.429963580092023e-05, + "loss": 4.2157, + "step": 348160 + }, + { + "epoch": 1.01, + "learning_rate": 4.429124985340971e-05, + "loss": 4.2225, + "step": 348672 + }, + { + "epoch": 1.01, + "learning_rate": 4.428288028470292e-05, + "loss": 4.2189, + "step": 349184 + }, + { + "epoch": 1.01, + "learning_rate": 4.42744943371924e-05, + "loss": 4.2256, + "step": 349696 + }, + { + "epoch": 1.01, + "learning_rate": 4.426610838968188e-05, + "loss": 4.2328, + "step": 350208 + }, + { + "epoch": 1.01, + "learning_rate": 4.425772244217136e-05, + "loss": 4.2143, + "step": 350720 + }, + { + "epoch": 1.02, + "learning_rate": 4.424933649466084e-05, + "loss": 4.2222, + "step": 351232 + }, + { + "epoch": 1.02, + "learning_rate": 4.424095054715032e-05, + "loss": 4.213, + "step": 351744 + }, + { + "epoch": 1.02, + "learning_rate": 4.42325645996398e-05, + "loss": 4.2199, + "step": 352256 + }, + { + "epoch": 1.02, + "learning_rate": 4.422417865212928e-05, + "loss": 4.2233, + "step": 352768 + }, + { + "epoch": 1.02, + "learning_rate": 4.421580908342249e-05, + "loss": 4.2204, + "step": 353280 + }, + { + "epoch": 1.02, + "learning_rate": 4.420742313591197e-05, + "loss": 4.2297, + "step": 353792 + }, + { + "epoch": 1.02, + "learning_rate": 4.419903718840145e-05, + "loss": 4.2202, + "step": 354304 + }, + { + "epoch": 1.02, + "learning_rate": 4.419065124089093e-05, + "loss": 4.2173, + "step": 354816 + }, + { + "epoch": 1.02, + "learning_rate": 4.418226529338041e-05, + "loss": 4.2189, + "step": 355328 + }, + { + "epoch": 1.02, + "learning_rate": 4.417389572467362e-05, + "loss": 4.22, + "step": 355840 + }, + { + "epoch": 1.02, + "learning_rate": 4.41655097771631e-05, + "loss": 4.2263, + "step": 356352 + }, + { + "epoch": 1.02, + "learning_rate": 4.415712382965258e-05, + "loss": 4.2083, + "step": 356864 + }, + { + "epoch": 1.02, + "learning_rate": 4.414873788214206e-05, + "loss": 4.2174, + "step": 357376 + }, + { + "epoch": 1.02, + "learning_rate": 4.414036831343527e-05, + "loss": 4.2205, + "step": 357888 + }, + { + "epoch": 1.02, + "learning_rate": 4.413198236592475e-05, + "loss": 4.2215, + "step": 358400 + }, + { + "epoch": 1.02, + "learning_rate": 4.412359641841423e-05, + "loss": 4.2025, + "step": 358912 + }, + { + "epoch": 1.02, + "learning_rate": 4.411521047090371e-05, + "loss": 4.2087, + "step": 359424 + }, + { + "epoch": 1.02, + "learning_rate": 4.410684090219692e-05, + "loss": 4.2195, + "step": 359936 + }, + { + "epoch": 1.02, + "learning_rate": 4.40984549546864e-05, + "loss": 4.2128, + "step": 360448 + }, + { + "epoch": 1.02, + "learning_rate": 4.409006900717588e-05, + "loss": 4.2063, + "step": 360960 + }, + { + "epoch": 1.02, + "learning_rate": 4.408168305966536e-05, + "loss": 4.2169, + "step": 361472 + }, + { + "epoch": 1.02, + "learning_rate": 4.407329711215484e-05, + "loss": 4.206, + "step": 361984 + }, + { + "epoch": 1.02, + "learning_rate": 4.406491116464432e-05, + "loss": 4.2188, + "step": 362496 + }, + { + "epoch": 1.02, + "learning_rate": 4.405654159593753e-05, + "loss": 4.2092, + "step": 363008 + }, + { + "epoch": 1.02, + "learning_rate": 4.404815564842701e-05, + "loss": 4.2032, + "step": 363520 + }, + { + "epoch": 1.02, + "learning_rate": 4.40397697009165e-05, + "loss": 4.2172, + "step": 364032 + }, + { + "epoch": 1.02, + "learning_rate": 4.403138375340598e-05, + "loss": 4.2238, + "step": 364544 + }, + { + "epoch": 1.02, + "learning_rate": 4.402299780589546e-05, + "loss": 4.2137, + "step": 365056 + }, + { + "epoch": 1.02, + "learning_rate": 4.401461185838494e-05, + "loss": 4.2102, + "step": 365568 + }, + { + "epoch": 1.02, + "learning_rate": 4.400622591087442e-05, + "loss": 4.2156, + "step": 366080 + }, + { + "epoch": 1.02, + "learning_rate": 4.39978399633639e-05, + "loss": 4.2145, + "step": 366592 + }, + { + "epoch": 1.02, + "learning_rate": 4.3989470394657106e-05, + "loss": 4.2047, + "step": 367104 + }, + { + "epoch": 1.02, + "learning_rate": 4.3981100825950316e-05, + "loss": 4.2131, + "step": 367616 + }, + { + "epoch": 1.02, + "learning_rate": 4.3972714878439796e-05, + "loss": 4.2034, + "step": 368128 + }, + { + "epoch": 1.02, + "learning_rate": 4.3964328930929276e-05, + "loss": 4.2073, + "step": 368640 + }, + { + "epoch": 1.02, + "learning_rate": 4.3955942983418755e-05, + "loss": 4.2025, + "step": 369152 + }, + { + "epoch": 1.02, + "learning_rate": 4.3947557035908235e-05, + "loss": 4.2089, + "step": 369664 + }, + { + "epoch": 1.02, + "learning_rate": 4.3939171088397715e-05, + "loss": 4.1981, + "step": 370176 + }, + { + "epoch": 1.02, + "learning_rate": 4.393080151969093e-05, + "loss": 4.1974, + "step": 370688 + }, + { + "epoch": 1.02, + "learning_rate": 4.392241557218041e-05, + "loss": 4.2042, + "step": 371200 + }, + { + "epoch": 1.02, + "learning_rate": 4.391402962466989e-05, + "loss": 4.2153, + "step": 371712 + }, + { + "epoch": 1.02, + "learning_rate": 4.390564367715937e-05, + "loss": 4.2138, + "step": 372224 + }, + { + "epoch": 1.02, + "learning_rate": 4.389725772964885e-05, + "loss": 4.2118, + "step": 372736 + }, + { + "epoch": 1.02, + "learning_rate": 4.3888871782138324e-05, + "loss": 4.1939, + "step": 373248 + }, + { + "epoch": 1.02, + "learning_rate": 4.3880485834627804e-05, + "loss": 4.2115, + "step": 373760 + }, + { + "epoch": 1.02, + "learning_rate": 4.3872099887117284e-05, + "loss": 4.2145, + "step": 374272 + }, + { + "epoch": 1.02, + "learning_rate": 4.3863713939606764e-05, + "loss": 4.2083, + "step": 374784 + }, + { + "epoch": 1.02, + "learning_rate": 4.385536074970371e-05, + "loss": 4.2026, + "step": 375296 + }, + { + "epoch": 1.02, + "learning_rate": 4.384697480219319e-05, + "loss": 4.2153, + "step": 375808 + }, + { + "epoch": 1.02, + "learning_rate": 4.383858885468267e-05, + "loss": 4.202, + "step": 376320 + }, + { + "epoch": 1.02, + "learning_rate": 4.383020290717215e-05, + "loss": 4.2136, + "step": 376832 + }, + { + "epoch": 1.02, + "learning_rate": 4.382181695966163e-05, + "loss": 4.1886, + "step": 377344 + }, + { + "epoch": 1.02, + "learning_rate": 4.381343101215111e-05, + "loss": 4.2144, + "step": 377856 + }, + { + "epoch": 1.02, + "learning_rate": 4.3805061443444325e-05, + "loss": 4.1962, + "step": 378368 + }, + { + "epoch": 1.02, + "learning_rate": 4.37966754959338e-05, + "loss": 4.1979, + "step": 378880 + }, + { + "epoch": 1.02, + "learning_rate": 4.378828954842328e-05, + "loss": 4.2045, + "step": 379392 + }, + { + "epoch": 1.02, + "learning_rate": 4.377990360091276e-05, + "loss": 4.2037, + "step": 379904 + }, + { + "epoch": 1.02, + "learning_rate": 4.377151765340224e-05, + "loss": 4.2062, + "step": 380416 + }, + { + "epoch": 1.02, + "learning_rate": 4.376314808469545e-05, + "loss": 4.1917, + "step": 380928 + }, + { + "epoch": 1.02, + "learning_rate": 4.375476213718493e-05, + "loss": 4.2051, + "step": 381440 + }, + { + "epoch": 1.03, + "eval_loss": 4.193454742431641, + "eval_runtime": 296.9368, + "eval_samples_per_second": 1285.092, + "eval_steps_per_second": 40.16, + "step": 381600 + }, + { + "epoch": 0.0, + "learning_rate": 4.374637618967441e-05, + "loss": 4.1999, + "step": 381952 + }, + { + "epoch": 0.0, + "learning_rate": 4.373799024216389e-05, + "loss": 4.1953, + "step": 382464 + }, + { + "epoch": 0.0, + "learning_rate": 4.3729604294653374e-05, + "loss": 4.205, + "step": 382976 + }, + { + "epoch": 0.0, + "learning_rate": 4.3721218347142853e-05, + "loss": 4.1977, + "step": 383488 + }, + { + "epoch": 0.0, + "learning_rate": 4.3712832399632333e-05, + "loss": 4.209, + "step": 384000 + }, + { + "epoch": 0.0, + "learning_rate": 4.3704446452121813e-05, + "loss": 4.1949, + "step": 384512 + }, + { + "epoch": 0.0, + "learning_rate": 4.369606050461129e-05, + "loss": 4.1956, + "step": 385024 + }, + { + "epoch": 0.0, + "learning_rate": 4.368767455710077e-05, + "loss": 4.1957, + "step": 385536 + }, + { + "epoch": 0.0, + "learning_rate": 4.367928860959025e-05, + "loss": 4.1992, + "step": 386048 + }, + { + "epoch": 0.0, + "learning_rate": 4.367090266207973e-05, + "loss": 4.2023, + "step": 386560 + }, + { + "epoch": 0.0, + "learning_rate": 4.366251671456921e-05, + "loss": 4.1998, + "step": 387072 + }, + { + "epoch": 0.0, + "learning_rate": 4.3654130767058686e-05, + "loss": 4.205, + "step": 387584 + }, + { + "epoch": 0.0, + "learning_rate": 4.36457611983519e-05, + "loss": 4.1911, + "step": 388096 + }, + { + "epoch": 0.0, + "learning_rate": 4.363737525084138e-05, + "loss": 4.194, + "step": 388608 + }, + { + "epoch": 0.0, + "learning_rate": 4.362898930333086e-05, + "loss": 4.1958, + "step": 389120 + }, + { + "epoch": 0.0, + "learning_rate": 4.3620603355820335e-05, + "loss": 4.1857, + "step": 389632 + }, + { + "epoch": 0.0, + "learning_rate": 4.361221740830982e-05, + "loss": 4.1952, + "step": 390144 + }, + { + "epoch": 0.0, + "learning_rate": 4.36038314607993e-05, + "loss": 4.1888, + "step": 390656 + }, + { + "epoch": 0.0, + "learning_rate": 4.359544551328878e-05, + "loss": 4.1898, + "step": 391168 + }, + { + "epoch": 0.0, + "learning_rate": 4.358705956577826e-05, + "loss": 4.2078, + "step": 391680 + }, + { + "epoch": 0.0, + "learning_rate": 4.357867361826774e-05, + "loss": 4.1999, + "step": 392192 + }, + { + "epoch": 0.0, + "learning_rate": 4.357028767075722e-05, + "loss": 4.2012, + "step": 392704 + }, + { + "epoch": 0.0, + "learning_rate": 4.35619017232467e-05, + "loss": 4.1963, + "step": 393216 + }, + { + "epoch": 0.0, + "learning_rate": 4.355351577573618e-05, + "loss": 4.1983, + "step": 393728 + }, + { + "epoch": 0.0, + "learning_rate": 4.354514620702939e-05, + "loss": 4.1802, + "step": 394240 + }, + { + "epoch": 0.0, + "learning_rate": 4.353676025951887e-05, + "loss": 4.199, + "step": 394752 + }, + { + "epoch": 0.0, + "learning_rate": 4.352837431200835e-05, + "loss": 4.187, + "step": 395264 + }, + { + "epoch": 0.0, + "learning_rate": 4.351998836449783e-05, + "loss": 4.1799, + "step": 395776 + }, + { + "epoch": 0.0, + "learning_rate": 4.351161879579104e-05, + "loss": 4.1828, + "step": 396288 + }, + { + "epoch": 0.0, + "learning_rate": 4.350323284828052e-05, + "loss": 4.1876, + "step": 396800 + }, + { + "epoch": 0.01, + "learning_rate": 4.3494846900770006e-05, + "loss": 4.1896, + "step": 397312 + }, + { + "epoch": 0.01, + "learning_rate": 4.3486460953259486e-05, + "loss": 4.1994, + "step": 397824 + }, + { + "epoch": 0.01, + "learning_rate": 4.3478091384552696e-05, + "loss": 4.196, + "step": 398336 + }, + { + "epoch": 0.01, + "learning_rate": 4.3469705437042175e-05, + "loss": 4.19, + "step": 398848 + }, + { + "epoch": 0.01, + "learning_rate": 4.3461335868335385e-05, + "loss": 4.1859, + "step": 399360 + }, + { + "epoch": 0.01, + "learning_rate": 4.3452949920824865e-05, + "loss": 4.1882, + "step": 399872 + }, + { + "epoch": 0.01, + "learning_rate": 4.3444563973314344e-05, + "loss": 4.1851, + "step": 400384 + }, + { + "epoch": 0.01, + "learning_rate": 4.3436178025803824e-05, + "loss": 4.1905, + "step": 400896 + }, + { + "epoch": 0.01, + "learning_rate": 4.3427792078293304e-05, + "loss": 4.1765, + "step": 401408 + }, + { + "epoch": 0.01, + "learning_rate": 4.3419422509586514e-05, + "loss": 4.1758, + "step": 401920 + }, + { + "epoch": 0.01, + "learning_rate": 4.3411036562075993e-05, + "loss": 4.1832, + "step": 402432 + }, + { + "epoch": 0.01, + "learning_rate": 4.3402650614565473e-05, + "loss": 4.1952, + "step": 402944 + }, + { + "epoch": 0.01, + "learning_rate": 4.339426466705496e-05, + "loss": 4.184, + "step": 403456 + }, + { + "epoch": 0.01, + "learning_rate": 4.338589509834817e-05, + "loss": 4.1806, + "step": 403968 + }, + { + "epoch": 0.01, + "learning_rate": 4.337750915083765e-05, + "loss": 4.1866, + "step": 404480 + }, + { + "epoch": 0.01, + "learning_rate": 4.336912320332713e-05, + "loss": 4.1804, + "step": 404992 + }, + { + "epoch": 0.01, + "learning_rate": 4.336073725581661e-05, + "loss": 4.1909, + "step": 405504 + }, + { + "epoch": 0.01, + "learning_rate": 4.335235130830609e-05, + "loss": 4.178, + "step": 406016 + }, + { + "epoch": 0.01, + "learning_rate": 4.334396536079557e-05, + "loss": 4.1686, + "step": 406528 + }, + { + "epoch": 0.01, + "learning_rate": 4.333557941328505e-05, + "loss": 4.1857, + "step": 407040 + }, + { + "epoch": 0.01, + "learning_rate": 4.332719346577452e-05, + "loss": 4.18, + "step": 407552 + }, + { + "epoch": 0.01, + "learning_rate": 4.331882389706774e-05, + "loss": 4.1774, + "step": 408064 + }, + { + "epoch": 0.01, + "learning_rate": 4.331043794955722e-05, + "loss": 4.1797, + "step": 408576 + }, + { + "epoch": 0.01, + "learning_rate": 4.330206838085043e-05, + "loss": 4.1784, + "step": 409088 + }, + { + "epoch": 0.01, + "learning_rate": 4.3293682433339914e-05, + "loss": 4.1708, + "step": 409600 + }, + { + "epoch": 0.01, + "learning_rate": 4.3285296485829394e-05, + "loss": 4.1775, + "step": 410112 + }, + { + "epoch": 0.01, + "learning_rate": 4.3276910538318874e-05, + "loss": 4.1701, + "step": 410624 + }, + { + "epoch": 0.01, + "learning_rate": 4.326852459080835e-05, + "loss": 4.1728, + "step": 411136 + }, + { + "epoch": 0.01, + "learning_rate": 4.326013864329783e-05, + "loss": 4.183, + "step": 411648 + }, + { + "epoch": 0.01, + "learning_rate": 4.325175269578731e-05, + "loss": 4.1727, + "step": 412160 + }, + { + "epoch": 0.01, + "learning_rate": 4.324336674827679e-05, + "loss": 4.1769, + "step": 412672 + }, + { + "epoch": 0.01, + "learning_rate": 4.3234997179569996e-05, + "loss": 4.1843, + "step": 413184 + }, + { + "epoch": 0.01, + "learning_rate": 4.3226611232059476e-05, + "loss": 4.1603, + "step": 413696 + }, + { + "epoch": 0.01, + "learning_rate": 4.3218225284548956e-05, + "loss": 4.1663, + "step": 414208 + }, + { + "epoch": 0.01, + "learning_rate": 4.3209839337038436e-05, + "loss": 4.1739, + "step": 414720 + }, + { + "epoch": 0.01, + "learning_rate": 4.3201453389527916e-05, + "loss": 4.1779, + "step": 415232 + }, + { + "epoch": 0.01, + "learning_rate": 4.319310019962487e-05, + "loss": 4.1687, + "step": 415744 + }, + { + "epoch": 0.01, + "learning_rate": 4.318471425211435e-05, + "loss": 4.1682, + "step": 416256 + }, + { + "epoch": 0.01, + "learning_rate": 4.317632830460382e-05, + "loss": 4.1598, + "step": 416768 + }, + { + "epoch": 0.01, + "learning_rate": 4.31679423570933e-05, + "loss": 4.1773, + "step": 417280 + }, + { + "epoch": 0.01, + "learning_rate": 4.315955640958278e-05, + "loss": 4.1812, + "step": 417792 + }, + { + "epoch": 0.01, + "learning_rate": 4.315117046207226e-05, + "loss": 4.1758, + "step": 418304 + }, + { + "epoch": 0.01, + "learning_rate": 4.314278451456174e-05, + "loss": 4.1801, + "step": 418816 + }, + { + "epoch": 0.01, + "learning_rate": 4.313439856705122e-05, + "loss": 4.1792, + "step": 419328 + }, + { + "epoch": 0.01, + "learning_rate": 4.312602899834443e-05, + "loss": 4.2004, + "step": 419840 + }, + { + "epoch": 0.01, + "learning_rate": 4.311764305083391e-05, + "loss": 4.16, + "step": 420352 + }, + { + "epoch": 0.01, + "learning_rate": 4.310925710332339e-05, + "loss": 4.1698, + "step": 420864 + }, + { + "epoch": 0.01, + "learning_rate": 4.310087115581287e-05, + "loss": 4.1825, + "step": 421376 + }, + { + "epoch": 0.01, + "learning_rate": 4.3092501587106085e-05, + "loss": 4.1592, + "step": 421888 + }, + { + "epoch": 0.01, + "learning_rate": 4.3084115639595565e-05, + "loss": 4.1772, + "step": 422400 + }, + { + "epoch": 0.01, + "learning_rate": 4.3075729692085045e-05, + "loss": 4.1743, + "step": 422912 + }, + { + "epoch": 0.01, + "learning_rate": 4.3067343744574525e-05, + "loss": 4.1771, + "step": 423424 + }, + { + "epoch": 0.01, + "learning_rate": 4.3058974175867734e-05, + "loss": 4.1733, + "step": 423936 + }, + { + "epoch": 0.01, + "learning_rate": 4.305060460716094e-05, + "loss": 4.1603, + "step": 424448 + }, + { + "epoch": 0.01, + "learning_rate": 4.304221865965042e-05, + "loss": 4.1745, + "step": 424960 + }, + { + "epoch": 0.01, + "learning_rate": 4.30338327121399e-05, + "loss": 4.1585, + "step": 425472 + }, + { + "epoch": 0.01, + "learning_rate": 4.302544676462938e-05, + "loss": 4.1736, + "step": 425984 + }, + { + "epoch": 0.01, + "learning_rate": 4.301707719592259e-05, + "loss": 4.1793, + "step": 426496 + }, + { + "epoch": 0.01, + "learning_rate": 4.300869124841207e-05, + "loss": 4.1558, + "step": 427008 + }, + { + "epoch": 0.02, + "learning_rate": 4.300030530090155e-05, + "loss": 4.1702, + "step": 427520 + }, + { + "epoch": 0.02, + "learning_rate": 4.299191935339104e-05, + "loss": 4.1615, + "step": 428032 + }, + { + "epoch": 0.02, + "learning_rate": 4.298354978468425e-05, + "loss": 4.1638, + "step": 428544 + }, + { + "epoch": 0.02, + "learning_rate": 4.297516383717373e-05, + "loss": 4.1644, + "step": 429056 + }, + { + "epoch": 0.02, + "learning_rate": 4.296677788966321e-05, + "loss": 4.175, + "step": 429568 + }, + { + "epoch": 0.02, + "learning_rate": 4.295839194215269e-05, + "loss": 4.1786, + "step": 430080 + }, + { + "epoch": 0.02, + "learning_rate": 4.29500223734459e-05, + "loss": 4.1623, + "step": 430592 + }, + { + "epoch": 0.02, + "learning_rate": 4.294163642593538e-05, + "loss": 4.1618, + "step": 431104 + }, + { + "epoch": 0.02, + "learning_rate": 4.293325047842486e-05, + "loss": 4.1696, + "step": 431616 + }, + { + "epoch": 0.02, + "learning_rate": 4.292486453091434e-05, + "loss": 4.1642, + "step": 432128 + }, + { + "epoch": 0.02, + "learning_rate": 4.291647858340382e-05, + "loss": 4.1761, + "step": 432640 + }, + { + "epoch": 0.02, + "learning_rate": 4.29080926358933e-05, + "loss": 4.1577, + "step": 433152 + }, + { + "epoch": 0.02, + "learning_rate": 4.289970668838278e-05, + "loss": 4.1624, + "step": 433664 + }, + { + "epoch": 0.02, + "learning_rate": 4.289133711967599e-05, + "loss": 4.1679, + "step": 434176 + }, + { + "epoch": 0.02, + "learning_rate": 4.288295117216547e-05, + "loss": 4.171, + "step": 434688 + }, + { + "epoch": 0.02, + "learning_rate": 4.287456522465495e-05, + "loss": 4.1483, + "step": 435200 + }, + { + "epoch": 0.02, + "learning_rate": 4.286617927714443e-05, + "loss": 4.1568, + "step": 435712 + }, + { + "epoch": 0.02, + "learning_rate": 4.285779332963391e-05, + "loss": 4.1643, + "step": 436224 + }, + { + "epoch": 0.02, + "learning_rate": 4.284940738212339e-05, + "loss": 4.1625, + "step": 436736 + }, + { + "epoch": 0.02, + "learning_rate": 4.284102143461287e-05, + "loss": 4.1515, + "step": 437248 + }, + { + "epoch": 0.02, + "learning_rate": 4.283263548710235e-05, + "loss": 4.1706, + "step": 437760 + }, + { + "epoch": 0.02, + "learning_rate": 4.282426591839556e-05, + "loss": 4.1512, + "step": 438272 + }, + { + "epoch": 0.02, + "learning_rate": 4.281587997088504e-05, + "loss": 4.1618, + "step": 438784 + }, + { + "epoch": 0.02, + "learning_rate": 4.280749402337452e-05, + "loss": 4.1604, + "step": 439296 + }, + { + "epoch": 0.02, + "learning_rate": 4.279912445466773e-05, + "loss": 4.1536, + "step": 439808 + }, + { + "epoch": 0.02, + "learning_rate": 4.279073850715721e-05, + "loss": 4.1645, + "step": 440320 + }, + { + "epoch": 0.02, + "learning_rate": 4.278235255964669e-05, + "loss": 4.1732, + "step": 440832 + }, + { + "epoch": 0.02, + "learning_rate": 4.277396661213618e-05, + "loss": 4.1603, + "step": 441344 + }, + { + "epoch": 0.02, + "learning_rate": 4.276558066462566e-05, + "loss": 4.1591, + "step": 441856 + }, + { + "epoch": 0.02, + "learning_rate": 4.275719471711513e-05, + "loss": 4.1647, + "step": 442368 + }, + { + "epoch": 0.02, + "learning_rate": 4.274880876960461e-05, + "loss": 4.1648, + "step": 442880 + }, + { + "epoch": 0.02, + "learning_rate": 4.2740439200897826e-05, + "loss": 4.1535, + "step": 443392 + }, + { + "epoch": 0.02, + "learning_rate": 4.2732069632191035e-05, + "loss": 4.1593, + "step": 443904 + }, + { + "epoch": 0.02, + "learning_rate": 4.2723683684680515e-05, + "loss": 4.1537, + "step": 444416 + }, + { + "epoch": 0.02, + "learning_rate": 4.2715297737169995e-05, + "loss": 4.1544, + "step": 444928 + }, + { + "epoch": 0.02, + "learning_rate": 4.2706911789659475e-05, + "loss": 4.1568, + "step": 445440 + }, + { + "epoch": 0.02, + "learning_rate": 4.269852584214895e-05, + "loss": 4.1534, + "step": 445952 + }, + { + "epoch": 0.02, + "learning_rate": 4.269013989463843e-05, + "loss": 4.1513, + "step": 446464 + }, + { + "epoch": 0.02, + "learning_rate": 4.2681753947127915e-05, + "loss": 4.1464, + "step": 446976 + }, + { + "epoch": 0.02, + "learning_rate": 4.267338437842113e-05, + "loss": 4.1558, + "step": 447488 + }, + { + "epoch": 0.02, + "learning_rate": 4.2664998430910604e-05, + "loss": 4.1642, + "step": 448000 + }, + { + "epoch": 0.02, + "learning_rate": 4.2656612483400084e-05, + "loss": 4.162, + "step": 448512 + }, + { + "epoch": 0.02, + "learning_rate": 4.26482429146933e-05, + "loss": 4.163, + "step": 449024 + }, + { + "epoch": 0.02, + "learning_rate": 4.263985696718277e-05, + "loss": 4.1437, + "step": 449536 + }, + { + "epoch": 0.02, + "learning_rate": 4.263147101967225e-05, + "loss": 4.1652, + "step": 450048 + }, + { + "epoch": 0.02, + "learning_rate": 4.262308507216173e-05, + "loss": 4.1627, + "step": 450560 + }, + { + "epoch": 0.02, + "learning_rate": 4.261469912465121e-05, + "loss": 4.1565, + "step": 451072 + }, + { + "epoch": 0.02, + "learning_rate": 4.260631317714069e-05, + "loss": 4.1574, + "step": 451584 + }, + { + "epoch": 0.02, + "learning_rate": 4.25979436084339e-05, + "loss": 4.1614, + "step": 452096 + }, + { + "epoch": 0.02, + "learning_rate": 4.258955766092338e-05, + "loss": 4.1528, + "step": 452608 + }, + { + "epoch": 0.02, + "learning_rate": 4.258117171341287e-05, + "loss": 4.1689, + "step": 453120 + }, + { + "epoch": 0.02, + "learning_rate": 4.257278576590235e-05, + "loss": 4.1384, + "step": 453632 + }, + { + "epoch": 0.02, + "learning_rate": 4.256439981839183e-05, + "loss": 4.1637, + "step": 454144 + }, + { + "epoch": 0.02, + "learning_rate": 4.255601387088131e-05, + "loss": 4.1462, + "step": 454656 + }, + { + "epoch": 0.02, + "learning_rate": 4.254764430217452e-05, + "loss": 4.1492, + "step": 455168 + }, + { + "epoch": 0.02, + "learning_rate": 4.2539258354664e-05, + "loss": 4.1557, + "step": 455680 + }, + { + "epoch": 0.02, + "learning_rate": 4.253087240715348e-05, + "loss": 4.151, + "step": 456192 + }, + { + "epoch": 0.02, + "learning_rate": 4.252248645964296e-05, + "loss": 4.1633, + "step": 456704 + }, + { + "epoch": 0.02, + "learning_rate": 4.251410051213244e-05, + "loss": 4.139, + "step": 457216 + }, + { + "epoch": 0.02, + "learning_rate": 4.250571456462192e-05, + "loss": 4.1582, + "step": 457728 + }, + { + "epoch": 0.03, + "eval_loss": 4.1527581214904785, + "eval_runtime": 288.3532, + "eval_samples_per_second": 1323.346, + "eval_steps_per_second": 41.356, + "step": 457920 + }, + { + "epoch": 1.0, + "learning_rate": 4.24973286171114e-05, + "loss": 4.1528, + "step": 458240 + }, + { + "epoch": 1.0, + "learning_rate": 4.248894266960088e-05, + "loss": 4.1439, + "step": 458752 + }, + { + "epoch": 1.0, + "learning_rate": 4.248058947969782e-05, + "loss": 4.1566, + "step": 459264 + }, + { + "epoch": 1.0, + "learning_rate": 4.24722035321873e-05, + "loss": 4.1499, + "step": 459776 + }, + { + "epoch": 1.0, + "learning_rate": 4.246381758467678e-05, + "loss": 4.1563, + "step": 460288 + }, + { + "epoch": 1.0, + "learning_rate": 4.245543163716626e-05, + "loss": 4.1485, + "step": 460800 + }, + { + "epoch": 1.0, + "learning_rate": 4.244704568965574e-05, + "loss": 4.1448, + "step": 461312 + }, + { + "epoch": 1.0, + "learning_rate": 4.243865974214522e-05, + "loss": 4.1497, + "step": 461824 + }, + { + "epoch": 1.0, + "learning_rate": 4.243029017343843e-05, + "loss": 4.1498, + "step": 462336 + }, + { + "epoch": 1.0, + "learning_rate": 4.242190422592791e-05, + "loss": 4.1534, + "step": 462848 + }, + { + "epoch": 1.0, + "learning_rate": 4.241351827841739e-05, + "loss": 4.1538, + "step": 463360 + }, + { + "epoch": 1.0, + "learning_rate": 4.240513233090687e-05, + "loss": 4.1522, + "step": 463872 + }, + { + "epoch": 1.0, + "learning_rate": 4.239676276220008e-05, + "loss": 4.1478, + "step": 464384 + }, + { + "epoch": 1.0, + "learning_rate": 4.238837681468956e-05, + "loss": 4.1465, + "step": 464896 + }, + { + "epoch": 1.0, + "learning_rate": 4.237999086717904e-05, + "loss": 4.1473, + "step": 465408 + }, + { + "epoch": 1.0, + "learning_rate": 4.237160491966852e-05, + "loss": 4.1373, + "step": 465920 + }, + { + "epoch": 1.0, + "learning_rate": 4.2363218972158e-05, + "loss": 4.1462, + "step": 466432 + }, + { + "epoch": 1.0, + "learning_rate": 4.2354833024647487e-05, + "loss": 4.1415, + "step": 466944 + }, + { + "epoch": 1.0, + "learning_rate": 4.2346447077136966e-05, + "loss": 4.1426, + "step": 467456 + }, + { + "epoch": 1.0, + "learning_rate": 4.233806112962644e-05, + "loss": 4.1593, + "step": 467968 + }, + { + "epoch": 1.0, + "learning_rate": 4.2329691560919656e-05, + "loss": 4.1534, + "step": 468480 + }, + { + "epoch": 1.0, + "learning_rate": 4.2321305613409135e-05, + "loss": 4.1524, + "step": 468992 + }, + { + "epoch": 1.0, + "learning_rate": 4.231291966589861e-05, + "loss": 4.1476, + "step": 469504 + }, + { + "epoch": 1.0, + "learning_rate": 4.230453371838809e-05, + "loss": 4.1536, + "step": 470016 + }, + { + "epoch": 1.0, + "learning_rate": 4.229614777087757e-05, + "loss": 4.1324, + "step": 470528 + }, + { + "epoch": 1.0, + "learning_rate": 4.2287778202170784e-05, + "loss": 4.1524, + "step": 471040 + }, + { + "epoch": 1.0, + "learning_rate": 4.227939225466026e-05, + "loss": 4.1387, + "step": 471552 + }, + { + "epoch": 1.0, + "learning_rate": 4.227100630714974e-05, + "loss": 4.1328, + "step": 472064 + }, + { + "epoch": 1.0, + "learning_rate": 4.2262620359639224e-05, + "loss": 4.1394, + "step": 472576 + }, + { + "epoch": 1.0, + "learning_rate": 4.2254234412128704e-05, + "loss": 4.1416, + "step": 473088 + }, + { + "epoch": 1.01, + "learning_rate": 4.2245848464618184e-05, + "loss": 4.1425, + "step": 473600 + }, + { + "epoch": 1.01, + "learning_rate": 4.2237462517107664e-05, + "loss": 4.1525, + "step": 474112 + }, + { + "epoch": 1.01, + "learning_rate": 4.222909294840087e-05, + "loss": 4.1461, + "step": 474624 + }, + { + "epoch": 1.01, + "learning_rate": 4.222070700089035e-05, + "loss": 4.1451, + "step": 475136 + }, + { + "epoch": 1.01, + "learning_rate": 4.221233743218356e-05, + "loss": 4.1334, + "step": 475648 + }, + { + "epoch": 1.01, + "learning_rate": 4.220395148467304e-05, + "loss": 4.1448, + "step": 476160 + }, + { + "epoch": 1.01, + "learning_rate": 4.219558191596626e-05, + "loss": 4.142, + "step": 476672 + }, + { + "epoch": 1.01, + "learning_rate": 4.218719596845573e-05, + "loss": 4.1364, + "step": 477184 + }, + { + "epoch": 1.01, + "learning_rate": 4.217881002094521e-05, + "loss": 4.1328, + "step": 477696 + }, + { + "epoch": 1.01, + "learning_rate": 4.217042407343469e-05, + "loss": 4.1284, + "step": 478208 + }, + { + "epoch": 1.01, + "learning_rate": 4.216203812592418e-05, + "loss": 4.1392, + "step": 478720 + }, + { + "epoch": 1.01, + "learning_rate": 4.215365217841366e-05, + "loss": 4.1456, + "step": 479232 + }, + { + "epoch": 1.01, + "learning_rate": 4.214526623090314e-05, + "loss": 4.141, + "step": 479744 + }, + { + "epoch": 1.01, + "learning_rate": 4.213688028339262e-05, + "loss": 4.1335, + "step": 480256 + }, + { + "epoch": 1.01, + "learning_rate": 4.212851071468583e-05, + "loss": 4.1432, + "step": 480768 + }, + { + "epoch": 1.01, + "learning_rate": 4.212012476717531e-05, + "loss": 4.1327, + "step": 481280 + }, + { + "epoch": 1.01, + "learning_rate": 4.211173881966479e-05, + "loss": 4.146, + "step": 481792 + }, + { + "epoch": 1.01, + "learning_rate": 4.210335287215427e-05, + "loss": 4.1326, + "step": 482304 + }, + { + "epoch": 1.01, + "learning_rate": 4.2094983303447476e-05, + "loss": 4.1183, + "step": 482816 + }, + { + "epoch": 1.01, + "learning_rate": 4.2086597355936956e-05, + "loss": 4.1426, + "step": 483328 + }, + { + "epoch": 1.01, + "learning_rate": 4.2078211408426436e-05, + "loss": 4.1363, + "step": 483840 + }, + { + "epoch": 1.01, + "learning_rate": 4.2069825460915916e-05, + "loss": 4.1355, + "step": 484352 + }, + { + "epoch": 1.01, + "learning_rate": 4.2061439513405396e-05, + "loss": 4.1313, + "step": 484864 + }, + { + "epoch": 1.01, + "learning_rate": 4.2053053565894876e-05, + "loss": 4.1307, + "step": 485376 + }, + { + "epoch": 1.01, + "learning_rate": 4.204466761838436e-05, + "loss": 4.1282, + "step": 485888 + }, + { + "epoch": 1.01, + "learning_rate": 4.203629804967757e-05, + "loss": 4.1298, + "step": 486400 + }, + { + "epoch": 1.01, + "learning_rate": 4.202791210216705e-05, + "loss": 4.1262, + "step": 486912 + }, + { + "epoch": 1.01, + "learning_rate": 4.201952615465653e-05, + "loss": 4.131, + "step": 487424 + }, + { + "epoch": 1.01, + "learning_rate": 4.201114020714601e-05, + "loss": 4.1345, + "step": 487936 + }, + { + "epoch": 1.01, + "learning_rate": 4.200275425963549e-05, + "loss": 4.129, + "step": 488448 + }, + { + "epoch": 1.01, + "learning_rate": 4.199436831212497e-05, + "loss": 4.1283, + "step": 488960 + }, + { + "epoch": 1.01, + "learning_rate": 4.1985982364614444e-05, + "loss": 4.1466, + "step": 489472 + }, + { + "epoch": 1.01, + "learning_rate": 4.1977596417103924e-05, + "loss": 4.114, + "step": 489984 + }, + { + "epoch": 1.01, + "learning_rate": 4.1969210469593404e-05, + "loss": 4.1187, + "step": 490496 + }, + { + "epoch": 1.01, + "learning_rate": 4.1960824522082884e-05, + "loss": 4.13, + "step": 491008 + }, + { + "epoch": 1.01, + "learning_rate": 4.1952438574572364e-05, + "loss": 4.1368, + "step": 491520 + }, + { + "epoch": 1.01, + "learning_rate": 4.1944052627061844e-05, + "loss": 4.1245, + "step": 492032 + }, + { + "epoch": 1.01, + "learning_rate": 4.193568305835506e-05, + "loss": 4.1236, + "step": 492544 + }, + { + "epoch": 1.01, + "learning_rate": 4.192731348964827e-05, + "loss": 4.1165, + "step": 493056 + }, + { + "epoch": 1.01, + "learning_rate": 4.191892754213775e-05, + "loss": 4.1316, + "step": 493568 + }, + { + "epoch": 1.01, + "learning_rate": 4.191054159462723e-05, + "loss": 4.1391, + "step": 494080 + }, + { + "epoch": 1.01, + "learning_rate": 4.190215564711671e-05, + "loss": 4.1311, + "step": 494592 + }, + { + "epoch": 1.01, + "learning_rate": 4.189376969960619e-05, + "loss": 4.1306, + "step": 495104 + }, + { + "epoch": 1.01, + "learning_rate": 4.188538375209567e-05, + "loss": 4.1386, + "step": 495616 + }, + { + "epoch": 1.01, + "learning_rate": 4.187699780458515e-05, + "loss": 4.1518, + "step": 496128 + }, + { + "epoch": 1.01, + "learning_rate": 4.186862823587836e-05, + "loss": 4.119, + "step": 496640 + }, + { + "epoch": 1.01, + "learning_rate": 4.186024228836784e-05, + "loss": 4.1279, + "step": 497152 + }, + { + "epoch": 1.01, + "learning_rate": 4.185185634085732e-05, + "loss": 4.1366, + "step": 497664 + }, + { + "epoch": 1.01, + "learning_rate": 4.18434703933468e-05, + "loss": 4.1157, + "step": 498176 + }, + { + "epoch": 1.01, + "learning_rate": 4.183508444583628e-05, + "loss": 4.1324, + "step": 498688 + }, + { + "epoch": 1.01, + "learning_rate": 4.1826698498325765e-05, + "loss": 4.1314, + "step": 499200 + }, + { + "epoch": 1.01, + "learning_rate": 4.1818312550815245e-05, + "loss": 4.1335, + "step": 499712 + }, + { + "epoch": 1.01, + "learning_rate": 4.1809926603304725e-05, + "loss": 4.1335, + "step": 500224 + }, + { + "epoch": 1.01, + "learning_rate": 4.1801557034597934e-05, + "loss": 4.1175, + "step": 500736 + }, + { + "epoch": 1.01, + "learning_rate": 4.1793171087087414e-05, + "loss": 4.1299, + "step": 501248 + }, + { + "epoch": 1.01, + "learning_rate": 4.1784785139576894e-05, + "loss": 4.1209, + "step": 501760 + }, + { + "epoch": 1.01, + "learning_rate": 4.17764155708701e-05, + "loss": 4.1274, + "step": 502272 + }, + { + "epoch": 1.01, + "learning_rate": 4.176802962335958e-05, + "loss": 4.1334, + "step": 502784 + }, + { + "epoch": 1.01, + "learning_rate": 4.175964367584906e-05, + "loss": 4.1158, + "step": 503296 + }, + { + "epoch": 1.02, + "learning_rate": 4.175125772833854e-05, + "loss": 4.1269, + "step": 503808 + }, + { + "epoch": 1.02, + "learning_rate": 4.174287178082802e-05, + "loss": 4.1202, + "step": 504320 + }, + { + "epoch": 1.02, + "learning_rate": 4.17344858333175e-05, + "loss": 4.1172, + "step": 504832 + }, + { + "epoch": 1.02, + "learning_rate": 4.172609988580698e-05, + "loss": 4.1275, + "step": 505344 + }, + { + "epoch": 1.02, + "learning_rate": 4.171771393829646e-05, + "loss": 4.1291, + "step": 505856 + }, + { + "epoch": 1.02, + "learning_rate": 4.170934436958968e-05, + "loss": 4.1371, + "step": 506368 + }, + { + "epoch": 1.02, + "learning_rate": 4.170095842207916e-05, + "loss": 4.1226, + "step": 506880 + }, + { + "epoch": 1.02, + "learning_rate": 4.169257247456863e-05, + "loss": 4.1199, + "step": 507392 + }, + { + "epoch": 1.02, + "learning_rate": 4.168418652705811e-05, + "loss": 4.1241, + "step": 507904 + }, + { + "epoch": 1.02, + "learning_rate": 4.167581695835133e-05, + "loss": 4.1252, + "step": 508416 + }, + { + "epoch": 1.02, + "learning_rate": 4.166743101084081e-05, + "loss": 4.1314, + "step": 508928 + }, + { + "epoch": 1.02, + "learning_rate": 4.165904506333028e-05, + "loss": 4.1193, + "step": 509440 + }, + { + "epoch": 1.02, + "learning_rate": 4.165065911581976e-05, + "loss": 4.1193, + "step": 509952 + }, + { + "epoch": 1.02, + "learning_rate": 4.1642289547112976e-05, + "loss": 4.1245, + "step": 510464 + }, + { + "epoch": 1.02, + "learning_rate": 4.1633903599602456e-05, + "loss": 4.1337, + "step": 510976 + }, + { + "epoch": 1.02, + "learning_rate": 4.1625517652091936e-05, + "loss": 4.1033, + "step": 511488 + }, + { + "epoch": 1.02, + "learning_rate": 4.1617131704581416e-05, + "loss": 4.1202, + "step": 512000 + }, + { + "epoch": 1.02, + "learning_rate": 4.160876213587463e-05, + "loss": 4.1206, + "step": 512512 + }, + { + "epoch": 1.02, + "learning_rate": 4.1600376188364105e-05, + "loss": 4.122, + "step": 513024 + }, + { + "epoch": 1.02, + "learning_rate": 4.1591990240853585e-05, + "loss": 4.1088, + "step": 513536 + }, + { + "epoch": 1.02, + "learning_rate": 4.1583604293343065e-05, + "loss": 4.1259, + "step": 514048 + }, + { + "epoch": 1.02, + "learning_rate": 4.1575218345832545e-05, + "loss": 4.1184, + "step": 514560 + }, + { + "epoch": 1.02, + "learning_rate": 4.1566832398322025e-05, + "loss": 4.1164, + "step": 515072 + }, + { + "epoch": 1.02, + "learning_rate": 4.1558462829615234e-05, + "loss": 4.124, + "step": 515584 + }, + { + "epoch": 1.02, + "learning_rate": 4.1550076882104714e-05, + "loss": 4.1123, + "step": 516096 + }, + { + "epoch": 1.02, + "learning_rate": 4.1541690934594194e-05, + "loss": 4.1172, + "step": 516608 + }, + { + "epoch": 1.02, + "learning_rate": 4.1533304987083674e-05, + "loss": 4.1325, + "step": 517120 + }, + { + "epoch": 1.02, + "learning_rate": 4.1524919039573154e-05, + "loss": 4.1211, + "step": 517632 + }, + { + "epoch": 1.02, + "learning_rate": 4.151653309206264e-05, + "loss": 4.1141, + "step": 518144 + }, + { + "epoch": 1.02, + "learning_rate": 4.150814714455212e-05, + "loss": 4.1265, + "step": 518656 + }, + { + "epoch": 1.02, + "learning_rate": 4.14997611970416e-05, + "loss": 4.1243, + "step": 519168 + }, + { + "epoch": 1.02, + "learning_rate": 4.149139162833481e-05, + "loss": 4.1083, + "step": 519680 + }, + { + "epoch": 1.02, + "learning_rate": 4.1483038438431755e-05, + "loss": 4.123, + "step": 520192 + }, + { + "epoch": 1.02, + "learning_rate": 4.147465249092123e-05, + "loss": 4.1125, + "step": 520704 + }, + { + "epoch": 1.02, + "learning_rate": 4.146626654341071e-05, + "loss": 4.1122, + "step": 521216 + }, + { + "epoch": 1.02, + "learning_rate": 4.145788059590019e-05, + "loss": 4.1157, + "step": 521728 + }, + { + "epoch": 1.02, + "learning_rate": 4.144949464838967e-05, + "loss": 4.1144, + "step": 522240 + }, + { + "epoch": 1.02, + "learning_rate": 4.144110870087915e-05, + "loss": 4.1121, + "step": 522752 + }, + { + "epoch": 1.02, + "learning_rate": 4.143272275336863e-05, + "loss": 4.1096, + "step": 523264 + }, + { + "epoch": 1.02, + "learning_rate": 4.142433680585811e-05, + "loss": 4.1109, + "step": 523776 + }, + { + "epoch": 1.02, + "learning_rate": 4.1415950858347594e-05, + "loss": 4.1259, + "step": 524288 + }, + { + "epoch": 1.02, + "learning_rate": 4.1407564910837074e-05, + "loss": 4.1188, + "step": 524800 + }, + { + "epoch": 1.02, + "learning_rate": 4.1399178963326554e-05, + "loss": 4.1216, + "step": 525312 + }, + { + "epoch": 1.02, + "learning_rate": 4.1390793015816034e-05, + "loss": 4.1032, + "step": 525824 + }, + { + "epoch": 1.02, + "learning_rate": 4.138242344710924e-05, + "loss": 4.1296, + "step": 526336 + }, + { + "epoch": 1.02, + "learning_rate": 4.137403749959872e-05, + "loss": 4.1204, + "step": 526848 + }, + { + "epoch": 1.02, + "learning_rate": 4.13656515520882e-05, + "loss": 4.1189, + "step": 527360 + }, + { + "epoch": 1.02, + "learning_rate": 4.135726560457768e-05, + "loss": 4.1187, + "step": 527872 + }, + { + "epoch": 1.02, + "learning_rate": 4.134887965706716e-05, + "loss": 4.1206, + "step": 528384 + }, + { + "epoch": 1.02, + "learning_rate": 4.134051008836037e-05, + "loss": 4.1109, + "step": 528896 + }, + { + "epoch": 1.02, + "learning_rate": 4.133212414084985e-05, + "loss": 4.1314, + "step": 529408 + }, + { + "epoch": 1.02, + "learning_rate": 4.132375457214306e-05, + "loss": 4.0986, + "step": 529920 + }, + { + "epoch": 1.02, + "learning_rate": 4.131536862463254e-05, + "loss": 4.1218, + "step": 530432 + }, + { + "epoch": 1.02, + "learning_rate": 4.130698267712203e-05, + "loss": 4.1102, + "step": 530944 + }, + { + "epoch": 1.02, + "learning_rate": 4.129859672961151e-05, + "loss": 4.1103, + "step": 531456 + }, + { + "epoch": 1.02, + "learning_rate": 4.129021078210099e-05, + "loss": 4.1124, + "step": 531968 + }, + { + "epoch": 1.02, + "learning_rate": 4.128182483459047e-05, + "loss": 4.1078, + "step": 532480 + }, + { + "epoch": 1.02, + "learning_rate": 4.127343888707994e-05, + "loss": 4.1243, + "step": 532992 + }, + { + "epoch": 1.02, + "learning_rate": 4.126506931837316e-05, + "loss": 4.1042, + "step": 533504 + }, + { + "epoch": 1.02, + "learning_rate": 4.125668337086264e-05, + "loss": 4.1191, + "step": 534016 + }, + { + "epoch": 1.03, + "eval_loss": 4.121633529663086, + "eval_runtime": 286.9116, + "eval_samples_per_second": 1329.995, + "eval_steps_per_second": 41.563, + "step": 534240 + }, + { + "epoch": 0.0, + "learning_rate": 4.124829742335212e-05, + "loss": 4.1174, + "step": 534528 + }, + { + "epoch": 0.0, + "learning_rate": 4.123991147584159e-05, + "loss": 4.1042, + "step": 535040 + }, + { + "epoch": 0.0, + "learning_rate": 4.123152552833107e-05, + "loss": 4.1179, + "step": 535552 + }, + { + "epoch": 0.0, + "learning_rate": 4.122313958082055e-05, + "loss": 4.1117, + "step": 536064 + }, + { + "epoch": 0.0, + "learning_rate": 4.121475363331003e-05, + "loss": 4.1152, + "step": 536576 + }, + { + "epoch": 0.0, + "learning_rate": 4.120636768579951e-05, + "loss": 4.1089, + "step": 537088 + }, + { + "epoch": 0.0, + "learning_rate": 4.1197981738288996e-05, + "loss": 4.1107, + "step": 537600 + }, + { + "epoch": 0.0, + "learning_rate": 4.1189595790778476e-05, + "loss": 4.107, + "step": 538112 + }, + { + "epoch": 0.0, + "learning_rate": 4.1181209843267956e-05, + "loss": 4.1136, + "step": 538624 + }, + { + "epoch": 0.0, + "learning_rate": 4.1172823895757436e-05, + "loss": 4.1172, + "step": 539136 + }, + { + "epoch": 0.0, + "learning_rate": 4.1164437948246916e-05, + "loss": 4.1144, + "step": 539648 + }, + { + "epoch": 0.0, + "learning_rate": 4.1156052000736396e-05, + "loss": 4.1111, + "step": 540160 + }, + { + "epoch": 0.0, + "learning_rate": 4.1147682432029605e-05, + "loss": 4.1082, + "step": 540672 + }, + { + "epoch": 0.0, + "learning_rate": 4.1139296484519085e-05, + "loss": 4.1075, + "step": 541184 + }, + { + "epoch": 0.0, + "learning_rate": 4.1130910537008565e-05, + "loss": 4.1111, + "step": 541696 + }, + { + "epoch": 0.0, + "learning_rate": 4.1122524589498045e-05, + "loss": 4.0993, + "step": 542208 + }, + { + "epoch": 0.0, + "learning_rate": 4.1114138641987525e-05, + "loss": 4.1078, + "step": 542720 + }, + { + "epoch": 0.0, + "learning_rate": 4.1105752694477005e-05, + "loss": 4.1048, + "step": 543232 + }, + { + "epoch": 0.0, + "learning_rate": 4.109736674696648e-05, + "loss": 4.1063, + "step": 543744 + }, + { + "epoch": 0.0, + "learning_rate": 4.1088980799455965e-05, + "loss": 4.1164, + "step": 544256 + }, + { + "epoch": 0.0, + "learning_rate": 4.1080594851945445e-05, + "loss": 4.1169, + "step": 544768 + }, + { + "epoch": 0.0, + "learning_rate": 4.1072208904434925e-05, + "loss": 4.1162, + "step": 545280 + }, + { + "epoch": 0.0, + "learning_rate": 4.1063822956924405e-05, + "loss": 4.11, + "step": 545792 + }, + { + "epoch": 0.0, + "learning_rate": 4.1055437009413885e-05, + "loss": 4.1121, + "step": 546304 + }, + { + "epoch": 0.0, + "learning_rate": 4.1047067440707094e-05, + "loss": 4.0982, + "step": 546816 + }, + { + "epoch": 0.0, + "learning_rate": 4.1038681493196574e-05, + "loss": 4.1164, + "step": 547328 + }, + { + "epoch": 0.0, + "learning_rate": 4.1030295545686054e-05, + "loss": 4.1012, + "step": 547840 + }, + { + "epoch": 0.0, + "learning_rate": 4.1021909598175534e-05, + "loss": 4.0966, + "step": 548352 + }, + { + "epoch": 0.0, + "learning_rate": 4.101354002946874e-05, + "loss": 4.1026, + "step": 548864 + }, + { + "epoch": 0.0, + "learning_rate": 4.100515408195822e-05, + "loss": 4.1063, + "step": 549376 + }, + { + "epoch": 0.01, + "learning_rate": 4.09967681344477e-05, + "loss": 4.1045, + "step": 549888 + }, + { + "epoch": 0.01, + "learning_rate": 4.098839856574092e-05, + "loss": 4.1144, + "step": 550400 + }, + { + "epoch": 0.01, + "learning_rate": 4.09800126182304e-05, + "loss": 4.1107, + "step": 550912 + }, + { + "epoch": 0.01, + "learning_rate": 4.097162667071988e-05, + "loss": 4.1022, + "step": 551424 + }, + { + "epoch": 0.01, + "learning_rate": 4.096324072320936e-05, + "loss": 4.1001, + "step": 551936 + }, + { + "epoch": 0.01, + "learning_rate": 4.095485477569884e-05, + "loss": 4.1094, + "step": 552448 + }, + { + "epoch": 0.01, + "learning_rate": 4.094646882818832e-05, + "loss": 4.1051, + "step": 552960 + }, + { + "epoch": 0.01, + "learning_rate": 4.09380828806778e-05, + "loss": 4.0983, + "step": 553472 + }, + { + "epoch": 0.01, + "learning_rate": 4.092971331197101e-05, + "loss": 4.0988, + "step": 553984 + }, + { + "epoch": 0.01, + "learning_rate": 4.0921343743264217e-05, + "loss": 4.0908, + "step": 554496 + }, + { + "epoch": 0.01, + "learning_rate": 4.0912957795753696e-05, + "loss": 4.0997, + "step": 555008 + }, + { + "epoch": 0.01, + "learning_rate": 4.0904571848243176e-05, + "loss": 4.1111, + "step": 555520 + }, + { + "epoch": 0.01, + "learning_rate": 4.0896185900732656e-05, + "loss": 4.1038, + "step": 556032 + }, + { + "epoch": 0.01, + "learning_rate": 4.0887799953222136e-05, + "loss": 4.0965, + "step": 556544 + }, + { + "epoch": 0.01, + "learning_rate": 4.0879414005711616e-05, + "loss": 4.1062, + "step": 557056 + }, + { + "epoch": 0.01, + "learning_rate": 4.0871028058201096e-05, + "loss": 4.0951, + "step": 557568 + }, + { + "epoch": 0.01, + "learning_rate": 4.086264211069058e-05, + "loss": 4.1088, + "step": 558080 + }, + { + "epoch": 0.01, + "learning_rate": 4.085425616318006e-05, + "loss": 4.0994, + "step": 558592 + }, + { + "epoch": 0.01, + "learning_rate": 4.084587021566954e-05, + "loss": 4.0787, + "step": 559104 + }, + { + "epoch": 0.01, + "learning_rate": 4.0837484268159016e-05, + "loss": 4.1054, + "step": 559616 + }, + { + "epoch": 0.01, + "learning_rate": 4.0829098320648496e-05, + "loss": 4.0987, + "step": 560128 + }, + { + "epoch": 0.01, + "learning_rate": 4.082072875194171e-05, + "loss": 4.1022, + "step": 560640 + }, + { + "epoch": 0.01, + "learning_rate": 4.081234280443119e-05, + "loss": 4.0938, + "step": 561152 + }, + { + "epoch": 0.01, + "learning_rate": 4.0803956856920665e-05, + "loss": 4.0946, + "step": 561664 + }, + { + "epoch": 0.01, + "learning_rate": 4.079558728821388e-05, + "loss": 4.0918, + "step": 562176 + }, + { + "epoch": 0.01, + "learning_rate": 4.078720134070336e-05, + "loss": 4.0923, + "step": 562688 + }, + { + "epoch": 0.01, + "learning_rate": 4.0778815393192834e-05, + "loss": 4.0938, + "step": 563200 + }, + { + "epoch": 0.01, + "learning_rate": 4.077042944568232e-05, + "loss": 4.0923, + "step": 563712 + }, + { + "epoch": 0.01, + "learning_rate": 4.07620434981718e-05, + "loss": 4.1061, + "step": 564224 + }, + { + "epoch": 0.01, + "learning_rate": 4.075365755066128e-05, + "loss": 4.0887, + "step": 564736 + }, + { + "epoch": 0.01, + "learning_rate": 4.074527160315076e-05, + "loss": 4.095, + "step": 565248 + }, + { + "epoch": 0.01, + "learning_rate": 4.073688565564024e-05, + "loss": 4.1073, + "step": 565760 + }, + { + "epoch": 0.01, + "learning_rate": 4.072851608693345e-05, + "loss": 4.0788, + "step": 566272 + }, + { + "epoch": 0.01, + "learning_rate": 4.072013013942293e-05, + "loss": 4.0841, + "step": 566784 + }, + { + "epoch": 0.01, + "learning_rate": 4.071176057071614e-05, + "loss": 4.0991, + "step": 567296 + }, + { + "epoch": 0.01, + "learning_rate": 4.070337462320562e-05, + "loss": 4.0972, + "step": 567808 + }, + { + "epoch": 0.01, + "learning_rate": 4.06949886756951e-05, + "loss": 4.0878, + "step": 568320 + }, + { + "epoch": 0.01, + "learning_rate": 4.068660272818458e-05, + "loss": 4.0901, + "step": 568832 + }, + { + "epoch": 0.01, + "learning_rate": 4.067821678067406e-05, + "loss": 4.0792, + "step": 569344 + }, + { + "epoch": 0.01, + "learning_rate": 4.066983083316354e-05, + "loss": 4.0984, + "step": 569856 + }, + { + "epoch": 0.01, + "learning_rate": 4.066144488565302e-05, + "loss": 4.1008, + "step": 570368 + }, + { + "epoch": 0.01, + "learning_rate": 4.0653058938142505e-05, + "loss": 4.0973, + "step": 570880 + }, + { + "epoch": 0.01, + "learning_rate": 4.0644689369435714e-05, + "loss": 4.0947, + "step": 571392 + }, + { + "epoch": 0.01, + "learning_rate": 4.0636319800728923e-05, + "loss": 4.1047, + "step": 571904 + }, + { + "epoch": 0.01, + "learning_rate": 4.06279338532184e-05, + "loss": 4.1158, + "step": 572416 + }, + { + "epoch": 0.01, + "learning_rate": 4.061954790570788e-05, + "loss": 4.0846, + "step": 572928 + }, + { + "epoch": 0.01, + "learning_rate": 4.061116195819736e-05, + "loss": 4.091, + "step": 573440 + }, + { + "epoch": 0.01, + "learning_rate": 4.060277601068684e-05, + "loss": 4.1027, + "step": 573952 + }, + { + "epoch": 0.01, + "learning_rate": 4.059439006317632e-05, + "loss": 4.0838, + "step": 574464 + }, + { + "epoch": 0.01, + "learning_rate": 4.058602049446953e-05, + "loss": 4.095, + "step": 574976 + }, + { + "epoch": 0.01, + "learning_rate": 4.057763454695901e-05, + "loss": 4.098, + "step": 575488 + }, + { + "epoch": 0.01, + "learning_rate": 4.056924859944849e-05, + "loss": 4.0998, + "step": 576000 + }, + { + "epoch": 0.01, + "learning_rate": 4.056086265193797e-05, + "loss": 4.1017, + "step": 576512 + }, + { + "epoch": 0.01, + "learning_rate": 4.055247670442746e-05, + "loss": 4.0835, + "step": 577024 + }, + { + "epoch": 0.01, + "learning_rate": 4.054410713572067e-05, + "loss": 4.0915, + "step": 577536 + }, + { + "epoch": 0.01, + "learning_rate": 4.053572118821015e-05, + "loss": 4.0881, + "step": 578048 + }, + { + "epoch": 0.01, + "learning_rate": 4.052733524069963e-05, + "loss": 4.0924, + "step": 578560 + }, + { + "epoch": 0.01, + "learning_rate": 4.051894929318911e-05, + "loss": 4.0956, + "step": 579072 + }, + { + "epoch": 0.01, + "learning_rate": 4.051056334567859e-05, + "loss": 4.0836, + "step": 579584 + }, + { + "epoch": 0.02, + "learning_rate": 4.050217739816807e-05, + "loss": 4.091, + "step": 580096 + }, + { + "epoch": 0.02, + "learning_rate": 4.049380782946128e-05, + "loss": 4.0866, + "step": 580608 + }, + { + "epoch": 0.02, + "learning_rate": 4.048542188195076e-05, + "loss": 4.0837, + "step": 581120 + }, + { + "epoch": 0.02, + "learning_rate": 4.047703593444024e-05, + "loss": 4.0915, + "step": 581632 + }, + { + "epoch": 0.02, + "learning_rate": 4.046864998692972e-05, + "loss": 4.0951, + "step": 582144 + }, + { + "epoch": 0.02, + "learning_rate": 4.04602640394192e-05, + "loss": 4.1021, + "step": 582656 + }, + { + "epoch": 0.02, + "learning_rate": 4.0451878091908677e-05, + "loss": 4.0921, + "step": 583168 + }, + { + "epoch": 0.02, + "learning_rate": 4.0443492144398157e-05, + "loss": 4.0821, + "step": 583680 + }, + { + "epoch": 0.02, + "learning_rate": 4.043512257569137e-05, + "loss": 4.0927, + "step": 584192 + }, + { + "epoch": 0.02, + "learning_rate": 4.042673662818085e-05, + "loss": 4.091, + "step": 584704 + }, + { + "epoch": 0.02, + "learning_rate": 4.0418350680670326e-05, + "loss": 4.0937, + "step": 585216 + }, + { + "epoch": 0.02, + "learning_rate": 4.0409964733159806e-05, + "loss": 4.0885, + "step": 585728 + }, + { + "epoch": 0.02, + "learning_rate": 4.0401578785649285e-05, + "loss": 4.0859, + "step": 586240 + }, + { + "epoch": 0.02, + "learning_rate": 4.0393209216942495e-05, + "loss": 4.0882, + "step": 586752 + }, + { + "epoch": 0.02, + "learning_rate": 4.0384823269431975e-05, + "loss": 4.1, + "step": 587264 + }, + { + "epoch": 0.02, + "learning_rate": 4.0376437321921454e-05, + "loss": 4.0717, + "step": 587776 + }, + { + "epoch": 0.02, + "learning_rate": 4.0368051374410934e-05, + "loss": 4.0861, + "step": 588288 + }, + { + "epoch": 0.02, + "learning_rate": 4.0359665426900414e-05, + "loss": 4.0829, + "step": 588800 + }, + { + "epoch": 0.02, + "learning_rate": 4.0351279479389894e-05, + "loss": 4.0883, + "step": 589312 + }, + { + "epoch": 0.02, + "learning_rate": 4.0342893531879374e-05, + "loss": 4.0792, + "step": 589824 + }, + { + "epoch": 0.02, + "learning_rate": 4.033452396317259e-05, + "loss": 4.0936, + "step": 590336 + }, + { + "epoch": 0.02, + "learning_rate": 4.032613801566207e-05, + "loss": 4.0794, + "step": 590848 + }, + { + "epoch": 0.02, + "learning_rate": 4.031775206815155e-05, + "loss": 4.0855, + "step": 591360 + }, + { + "epoch": 0.02, + "learning_rate": 4.030936612064103e-05, + "loss": 4.093, + "step": 591872 + }, + { + "epoch": 0.02, + "learning_rate": 4.030099655193424e-05, + "loss": 4.0779, + "step": 592384 + }, + { + "epoch": 0.02, + "learning_rate": 4.029261060442372e-05, + "loss": 4.0857, + "step": 592896 + }, + { + "epoch": 0.02, + "learning_rate": 4.02842246569132e-05, + "loss": 4.1009, + "step": 593408 + }, + { + "epoch": 0.02, + "learning_rate": 4.027583870940268e-05, + "loss": 4.0881, + "step": 593920 + }, + { + "epoch": 0.02, + "learning_rate": 4.026745276189216e-05, + "loss": 4.0824, + "step": 594432 + }, + { + "epoch": 0.02, + "learning_rate": 4.025906681438164e-05, + "loss": 4.0903, + "step": 594944 + }, + { + "epoch": 0.02, + "learning_rate": 4.025068086687112e-05, + "loss": 4.0954, + "step": 595456 + }, + { + "epoch": 0.02, + "learning_rate": 4.02422949193606e-05, + "loss": 4.0796, + "step": 595968 + }, + { + "epoch": 0.02, + "learning_rate": 4.0233925350653815e-05, + "loss": 4.089, + "step": 596480 + }, + { + "epoch": 0.02, + "learning_rate": 4.0225539403143295e-05, + "loss": 4.0739, + "step": 596992 + }, + { + "epoch": 0.02, + "learning_rate": 4.0217153455632775e-05, + "loss": 4.082, + "step": 597504 + }, + { + "epoch": 0.02, + "learning_rate": 4.0208767508122255e-05, + "loss": 4.0808, + "step": 598016 + }, + { + "epoch": 0.02, + "learning_rate": 4.0200397939415464e-05, + "loss": 4.0833, + "step": 598528 + }, + { + "epoch": 0.02, + "learning_rate": 4.0192011991904944e-05, + "loss": 4.0792, + "step": 599040 + }, + { + "epoch": 0.02, + "learning_rate": 4.0183626044394424e-05, + "loss": 4.0797, + "step": 599552 + }, + { + "epoch": 0.02, + "learning_rate": 4.0175240096883904e-05, + "loss": 4.076, + "step": 600064 + }, + { + "epoch": 0.02, + "learning_rate": 4.0166854149373383e-05, + "loss": 4.0949, + "step": 600576 + }, + { + "epoch": 0.02, + "learning_rate": 4.015846820186286e-05, + "loss": 4.0888, + "step": 601088 + }, + { + "epoch": 0.02, + "learning_rate": 4.015009863315607e-05, + "loss": 4.0886, + "step": 601600 + }, + { + "epoch": 0.02, + "learning_rate": 4.014171268564555e-05, + "loss": 4.0728, + "step": 602112 + }, + { + "epoch": 0.02, + "learning_rate": 4.013332673813503e-05, + "loss": 4.0981, + "step": 602624 + }, + { + "epoch": 0.02, + "learning_rate": 4.012494079062451e-05, + "loss": 4.0837, + "step": 603136 + }, + { + "epoch": 0.02, + "learning_rate": 4.011655484311399e-05, + "loss": 4.0865, + "step": 603648 + }, + { + "epoch": 0.02, + "learning_rate": 4.010818527440721e-05, + "loss": 4.0898, + "step": 604160 + }, + { + "epoch": 0.02, + "learning_rate": 4.009979932689669e-05, + "loss": 4.0844, + "step": 604672 + }, + { + "epoch": 0.02, + "learning_rate": 4.009141337938616e-05, + "loss": 4.0792, + "step": 605184 + }, + { + "epoch": 0.02, + "learning_rate": 4.008302743187564e-05, + "loss": 4.0982, + "step": 605696 + }, + { + "epoch": 0.02, + "learning_rate": 4.007464148436512e-05, + "loss": 4.0716, + "step": 606208 + }, + { + "epoch": 0.02, + "learning_rate": 4.00662555368546e-05, + "loss": 4.0904, + "step": 606720 + }, + { + "epoch": 0.02, + "learning_rate": 4.005786958934408e-05, + "loss": 4.0777, + "step": 607232 + }, + { + "epoch": 0.02, + "learning_rate": 4.004948364183356e-05, + "loss": 4.0796, + "step": 607744 + }, + { + "epoch": 0.02, + "learning_rate": 4.004111407312677e-05, + "loss": 4.0789, + "step": 608256 + }, + { + "epoch": 0.02, + "learning_rate": 4.003272812561625e-05, + "loss": 4.078, + "step": 608768 + }, + { + "epoch": 0.02, + "learning_rate": 4.002434217810574e-05, + "loss": 4.0912, + "step": 609280 + }, + { + "epoch": 0.02, + "learning_rate": 4.001595623059522e-05, + "loss": 4.0779, + "step": 609792 + }, + { + "epoch": 0.02, + "learning_rate": 4.000760304069216e-05, + "loss": 4.0845, + "step": 610304 + }, + { + "epoch": 0.03, + "eval_loss": 4.097892761230469, + "eval_runtime": 287.1157, + "eval_samples_per_second": 1329.05, + "eval_steps_per_second": 41.534, + "step": 610560 + }, + { + "epoch": 1.0, + "learning_rate": 3.9999217093181635e-05, + "loss": 4.0789, + "step": 610816 + }, + { + "epoch": 1.0, + "learning_rate": 3.9990831145671115e-05, + "loss": 4.0767, + "step": 611328 + }, + { + "epoch": 1.0, + "learning_rate": 3.9982445198160595e-05, + "loss": 4.0819, + "step": 611840 + }, + { + "epoch": 1.0, + "learning_rate": 3.9974059250650075e-05, + "loss": 4.0774, + "step": 612352 + }, + { + "epoch": 1.0, + "learning_rate": 3.9965673303139555e-05, + "loss": 4.0884, + "step": 612864 + }, + { + "epoch": 1.0, + "learning_rate": 3.9957287355629035e-05, + "loss": 4.0772, + "step": 613376 + }, + { + "epoch": 1.0, + "learning_rate": 3.9948901408118515e-05, + "loss": 4.0827, + "step": 613888 + }, + { + "epoch": 1.0, + "learning_rate": 3.9940515460607995e-05, + "loss": 4.078, + "step": 614400 + }, + { + "epoch": 1.0, + "learning_rate": 3.9932145891901204e-05, + "loss": 4.0779, + "step": 614912 + }, + { + "epoch": 1.0, + "learning_rate": 3.992377632319442e-05, + "loss": 4.0882, + "step": 615424 + }, + { + "epoch": 1.0, + "learning_rate": 3.99153903756839e-05, + "loss": 4.0819, + "step": 615936 + }, + { + "epoch": 1.0, + "learning_rate": 3.990700442817338e-05, + "loss": 4.0778, + "step": 616448 + }, + { + "epoch": 1.0, + "learning_rate": 3.989863485946659e-05, + "loss": 4.0857, + "step": 616960 + }, + { + "epoch": 1.0, + "learning_rate": 3.989024891195607e-05, + "loss": 4.0697, + "step": 617472 + }, + { + "epoch": 1.0, + "learning_rate": 3.988186296444555e-05, + "loss": 4.0772, + "step": 617984 + }, + { + "epoch": 1.0, + "learning_rate": 3.987347701693503e-05, + "loss": 4.0697, + "step": 618496 + }, + { + "epoch": 1.0, + "learning_rate": 3.986509106942451e-05, + "loss": 4.0802, + "step": 619008 + }, + { + "epoch": 1.0, + "learning_rate": 3.985670512191399e-05, + "loss": 4.0731, + "step": 619520 + }, + { + "epoch": 1.0, + "learning_rate": 3.984831917440347e-05, + "loss": 4.0702, + "step": 620032 + }, + { + "epoch": 1.0, + "learning_rate": 3.983993322689295e-05, + "loss": 4.0864, + "step": 620544 + }, + { + "epoch": 1.0, + "learning_rate": 3.983154727938243e-05, + "loss": 4.0903, + "step": 621056 + }, + { + "epoch": 1.0, + "learning_rate": 3.982316133187191e-05, + "loss": 4.0879, + "step": 621568 + }, + { + "epoch": 1.0, + "learning_rate": 3.981477538436139e-05, + "loss": 4.0761, + "step": 622080 + }, + { + "epoch": 1.0, + "learning_rate": 3.980638943685087e-05, + "loss": 4.0784, + "step": 622592 + }, + { + "epoch": 1.0, + "learning_rate": 3.9798019868144084e-05, + "loss": 4.0711, + "step": 623104 + }, + { + "epoch": 1.0, + "learning_rate": 3.9789633920633564e-05, + "loss": 4.0816, + "step": 623616 + }, + { + "epoch": 1.0, + "learning_rate": 3.9781247973123044e-05, + "loss": 4.0745, + "step": 624128 + }, + { + "epoch": 1.0, + "learning_rate": 3.977286202561252e-05, + "loss": 4.0722, + "step": 624640 + }, + { + "epoch": 1.0, + "learning_rate": 3.976449245690573e-05, + "loss": 4.0703, + "step": 625152 + }, + { + "epoch": 1.0, + "learning_rate": 3.975610650939521e-05, + "loss": 4.0731, + "step": 625664 + }, + { + "epoch": 1.01, + "learning_rate": 3.974772056188469e-05, + "loss": 4.069, + "step": 626176 + }, + { + "epoch": 1.01, + "learning_rate": 3.9739334614374166e-05, + "loss": 4.085, + "step": 626688 + }, + { + "epoch": 1.01, + "learning_rate": 3.973096504566738e-05, + "loss": 4.0804, + "step": 627200 + }, + { + "epoch": 1.01, + "learning_rate": 3.972257909815686e-05, + "loss": 4.0733, + "step": 627712 + }, + { + "epoch": 1.01, + "learning_rate": 3.971419315064634e-05, + "loss": 4.0695, + "step": 628224 + }, + { + "epoch": 1.01, + "learning_rate": 3.970582358193956e-05, + "loss": 4.0767, + "step": 628736 + }, + { + "epoch": 1.01, + "learning_rate": 3.969743763442904e-05, + "loss": 4.0763, + "step": 629248 + }, + { + "epoch": 1.01, + "learning_rate": 3.968905168691852e-05, + "loss": 4.072, + "step": 629760 + }, + { + "epoch": 1.01, + "learning_rate": 3.968066573940799e-05, + "loss": 4.0711, + "step": 630272 + }, + { + "epoch": 1.01, + "learning_rate": 3.967229617070121e-05, + "loss": 4.0612, + "step": 630784 + }, + { + "epoch": 1.01, + "learning_rate": 3.966391022319069e-05, + "loss": 4.0656, + "step": 631296 + }, + { + "epoch": 1.01, + "learning_rate": 3.965552427568017e-05, + "loss": 4.0817, + "step": 631808 + }, + { + "epoch": 1.01, + "learning_rate": 3.964713832816964e-05, + "loss": 4.0788, + "step": 632320 + }, + { + "epoch": 1.01, + "learning_rate": 3.963875238065912e-05, + "loss": 4.0639, + "step": 632832 + }, + { + "epoch": 1.01, + "learning_rate": 3.96303664331486e-05, + "loss": 4.0783, + "step": 633344 + }, + { + "epoch": 1.01, + "learning_rate": 3.962198048563808e-05, + "loss": 4.0643, + "step": 633856 + }, + { + "epoch": 1.01, + "learning_rate": 3.961359453812756e-05, + "loss": 4.0771, + "step": 634368 + }, + { + "epoch": 1.01, + "learning_rate": 3.9605224969420776e-05, + "loss": 4.07, + "step": 634880 + }, + { + "epoch": 1.01, + "learning_rate": 3.9596839021910256e-05, + "loss": 4.0451, + "step": 635392 + }, + { + "epoch": 1.01, + "learning_rate": 3.9588469453203465e-05, + "loss": 4.0807, + "step": 635904 + }, + { + "epoch": 1.01, + "learning_rate": 3.9580083505692945e-05, + "loss": 4.0687, + "step": 636416 + }, + { + "epoch": 1.01, + "learning_rate": 3.9571697558182425e-05, + "loss": 4.0743, + "step": 636928 + }, + { + "epoch": 1.01, + "learning_rate": 3.9563311610671905e-05, + "loss": 4.067, + "step": 637440 + }, + { + "epoch": 1.01, + "learning_rate": 3.9554925663161384e-05, + "loss": 4.0655, + "step": 637952 + }, + { + "epoch": 1.01, + "learning_rate": 3.9546539715650864e-05, + "loss": 4.0602, + "step": 638464 + }, + { + "epoch": 1.01, + "learning_rate": 3.9538153768140344e-05, + "loss": 4.0642, + "step": 638976 + }, + { + "epoch": 1.01, + "learning_rate": 3.9529767820629824e-05, + "loss": 4.0649, + "step": 639488 + }, + { + "epoch": 1.01, + "learning_rate": 3.9521381873119304e-05, + "loss": 4.0595, + "step": 640000 + }, + { + "epoch": 1.01, + "learning_rate": 3.9513012304412513e-05, + "loss": 4.077, + "step": 640512 + }, + { + "epoch": 1.01, + "learning_rate": 3.9504626356902e-05, + "loss": 4.0609, + "step": 641024 + }, + { + "epoch": 1.01, + "learning_rate": 3.949624040939148e-05, + "loss": 4.0648, + "step": 641536 + }, + { + "epoch": 1.01, + "learning_rate": 3.948787084068469e-05, + "loss": 4.0785, + "step": 642048 + }, + { + "epoch": 1.01, + "learning_rate": 3.947948489317417e-05, + "loss": 4.0511, + "step": 642560 + }, + { + "epoch": 1.01, + "learning_rate": 3.947109894566365e-05, + "loss": 4.0534, + "step": 643072 + }, + { + "epoch": 1.01, + "learning_rate": 3.946271299815313e-05, + "loss": 4.0705, + "step": 643584 + }, + { + "epoch": 1.01, + "learning_rate": 3.945432705064261e-05, + "loss": 4.0684, + "step": 644096 + }, + { + "epoch": 1.01, + "learning_rate": 3.944594110313209e-05, + "loss": 4.0594, + "step": 644608 + }, + { + "epoch": 1.01, + "learning_rate": 3.94375715344253e-05, + "loss": 4.0611, + "step": 645120 + }, + { + "epoch": 1.01, + "learning_rate": 3.942918558691478e-05, + "loss": 4.054, + "step": 645632 + }, + { + "epoch": 1.01, + "learning_rate": 3.942079963940426e-05, + "loss": 4.0662, + "step": 646144 + }, + { + "epoch": 1.01, + "learning_rate": 3.941241369189374e-05, + "loss": 4.0708, + "step": 646656 + }, + { + "epoch": 1.01, + "learning_rate": 3.940402774438322e-05, + "loss": 4.065, + "step": 647168 + }, + { + "epoch": 1.01, + "learning_rate": 3.93956417968727e-05, + "loss": 4.0692, + "step": 647680 + }, + { + "epoch": 1.01, + "learning_rate": 3.9387255849362185e-05, + "loss": 4.076, + "step": 648192 + }, + { + "epoch": 1.01, + "learning_rate": 3.937886990185166e-05, + "loss": 4.0875, + "step": 648704 + }, + { + "epoch": 1.01, + "learning_rate": 3.9370500333144874e-05, + "loss": 4.0556, + "step": 649216 + }, + { + "epoch": 1.01, + "learning_rate": 3.9362114385634354e-05, + "loss": 4.0664, + "step": 649728 + }, + { + "epoch": 1.01, + "learning_rate": 3.935374481692756e-05, + "loss": 4.0714, + "step": 650240 + }, + { + "epoch": 1.01, + "learning_rate": 3.934535886941704e-05, + "loss": 4.0591, + "step": 650752 + }, + { + "epoch": 1.01, + "learning_rate": 3.933697292190652e-05, + "loss": 4.0603, + "step": 651264 + }, + { + "epoch": 1.01, + "learning_rate": 3.9328586974396e-05, + "loss": 4.0739, + "step": 651776 + }, + { + "epoch": 1.01, + "learning_rate": 3.932021740568921e-05, + "loss": 4.0688, + "step": 652288 + }, + { + "epoch": 1.01, + "learning_rate": 3.931183145817869e-05, + "loss": 4.0743, + "step": 652800 + }, + { + "epoch": 1.01, + "learning_rate": 3.930344551066817e-05, + "loss": 4.0542, + "step": 653312 + }, + { + "epoch": 1.01, + "learning_rate": 3.929505956315765e-05, + "loss": 4.0604, + "step": 653824 + }, + { + "epoch": 1.01, + "learning_rate": 3.928668999445087e-05, + "loss": 4.0616, + "step": 654336 + }, + { + "epoch": 1.01, + "learning_rate": 3.927830404694035e-05, + "loss": 4.0651, + "step": 654848 + }, + { + "epoch": 1.01, + "learning_rate": 3.926991809942983e-05, + "loss": 4.0671, + "step": 655360 + }, + { + "epoch": 1.01, + "learning_rate": 3.92615321519193e-05, + "loss": 4.0606, + "step": 655872 + }, + { + "epoch": 1.02, + "learning_rate": 3.925314620440878e-05, + "loss": 4.056, + "step": 656384 + }, + { + "epoch": 1.02, + "learning_rate": 3.924476025689826e-05, + "loss": 4.0611, + "step": 656896 + }, + { + "epoch": 1.02, + "learning_rate": 3.923637430938774e-05, + "loss": 4.0561, + "step": 657408 + }, + { + "epoch": 1.02, + "learning_rate": 3.922798836187722e-05, + "loss": 4.0638, + "step": 657920 + }, + { + "epoch": 1.02, + "learning_rate": 3.921961879317043e-05, + "loss": 4.0695, + "step": 658432 + }, + { + "epoch": 1.02, + "learning_rate": 3.921123284565991e-05, + "loss": 4.0716, + "step": 658944 + }, + { + "epoch": 1.02, + "learning_rate": 3.9202863276953125e-05, + "loss": 4.0615, + "step": 659456 + }, + { + "epoch": 1.02, + "learning_rate": 3.9194477329442605e-05, + "loss": 4.0553, + "step": 659968 + }, + { + "epoch": 1.02, + "learning_rate": 3.9186091381932085e-05, + "loss": 4.0633, + "step": 660480 + }, + { + "epoch": 1.02, + "learning_rate": 3.9177705434421565e-05, + "loss": 4.0605, + "step": 660992 + }, + { + "epoch": 1.02, + "learning_rate": 3.9169319486911045e-05, + "loss": 4.0675, + "step": 661504 + }, + { + "epoch": 1.02, + "learning_rate": 3.9160933539400525e-05, + "loss": 4.0605, + "step": 662016 + }, + { + "epoch": 1.02, + "learning_rate": 3.9152547591890005e-05, + "loss": 4.054, + "step": 662528 + }, + { + "epoch": 1.02, + "learning_rate": 3.9144161644379485e-05, + "loss": 4.0683, + "step": 663040 + }, + { + "epoch": 1.02, + "learning_rate": 3.9135792075672694e-05, + "loss": 4.0678, + "step": 663552 + }, + { + "epoch": 1.02, + "learning_rate": 3.9127406128162174e-05, + "loss": 4.0431, + "step": 664064 + }, + { + "epoch": 1.02, + "learning_rate": 3.9119020180651654e-05, + "loss": 4.0589, + "step": 664576 + }, + { + "epoch": 1.02, + "learning_rate": 3.911065061194486e-05, + "loss": 4.0502, + "step": 665088 + }, + { + "epoch": 1.02, + "learning_rate": 3.910226466443434e-05, + "loss": 4.0663, + "step": 665600 + }, + { + "epoch": 1.02, + "learning_rate": 3.909387871692383e-05, + "loss": 4.0492, + "step": 666112 + }, + { + "epoch": 1.02, + "learning_rate": 3.908549276941331e-05, + "loss": 4.0657, + "step": 666624 + }, + { + "epoch": 1.02, + "learning_rate": 3.907710682190279e-05, + "loss": 4.0511, + "step": 667136 + }, + { + "epoch": 1.02, + "learning_rate": 3.906872087439227e-05, + "loss": 4.0591, + "step": 667648 + }, + { + "epoch": 1.02, + "learning_rate": 3.906035130568548e-05, + "loss": 4.0613, + "step": 668160 + }, + { + "epoch": 1.02, + "learning_rate": 3.905196535817496e-05, + "loss": 4.0537, + "step": 668672 + }, + { + "epoch": 1.02, + "learning_rate": 3.904357941066444e-05, + "loss": 4.0561, + "step": 669184 + }, + { + "epoch": 1.02, + "learning_rate": 3.903519346315392e-05, + "loss": 4.0739, + "step": 669696 + }, + { + "epoch": 1.02, + "learning_rate": 3.90268075156434e-05, + "loss": 4.0575, + "step": 670208 + }, + { + "epoch": 1.02, + "learning_rate": 3.901843794693661e-05, + "loss": 4.0594, + "step": 670720 + }, + { + "epoch": 1.02, + "learning_rate": 3.901005199942609e-05, + "loss": 4.0614, + "step": 671232 + }, + { + "epoch": 1.02, + "learning_rate": 3.900166605191557e-05, + "loss": 4.0646, + "step": 671744 + }, + { + "epoch": 1.02, + "learning_rate": 3.899328010440505e-05, + "loss": 4.0589, + "step": 672256 + }, + { + "epoch": 1.02, + "learning_rate": 3.898489415689453e-05, + "loss": 4.0591, + "step": 672768 + }, + { + "epoch": 1.02, + "learning_rate": 3.897650820938401e-05, + "loss": 4.046, + "step": 673280 + }, + { + "epoch": 1.02, + "learning_rate": 3.896812226187349e-05, + "loss": 4.0558, + "step": 673792 + }, + { + "epoch": 1.02, + "learning_rate": 3.895973631436297e-05, + "loss": 4.0524, + "step": 674304 + }, + { + "epoch": 1.02, + "learning_rate": 3.895136674565618e-05, + "loss": 4.0552, + "step": 674816 + }, + { + "epoch": 1.02, + "learning_rate": 3.894299717694939e-05, + "loss": 4.0516, + "step": 675328 + }, + { + "epoch": 1.02, + "learning_rate": 3.893461122943887e-05, + "loss": 4.055, + "step": 675840 + }, + { + "epoch": 1.02, + "learning_rate": 3.892622528192835e-05, + "loss": 4.0475, + "step": 676352 + }, + { + "epoch": 1.02, + "learning_rate": 3.891783933441783e-05, + "loss": 4.0706, + "step": 676864 + }, + { + "epoch": 1.02, + "learning_rate": 3.890945338690731e-05, + "loss": 4.0553, + "step": 677376 + }, + { + "epoch": 1.02, + "learning_rate": 3.8901067439396785e-05, + "loss": 4.066, + "step": 677888 + }, + { + "epoch": 1.02, + "learning_rate": 3.889269787069e-05, + "loss": 4.04, + "step": 678400 + }, + { + "epoch": 1.02, + "learning_rate": 3.888431192317948e-05, + "loss": 4.073, + "step": 678912 + }, + { + "epoch": 1.02, + "learning_rate": 3.887592597566896e-05, + "loss": 4.0549, + "step": 679424 + }, + { + "epoch": 1.02, + "learning_rate": 3.886754002815844e-05, + "loss": 4.0606, + "step": 679936 + }, + { + "epoch": 1.02, + "learning_rate": 3.885917045945166e-05, + "loss": 4.0618, + "step": 680448 + }, + { + "epoch": 1.02, + "learning_rate": 3.885078451194114e-05, + "loss": 4.0569, + "step": 680960 + }, + { + "epoch": 1.02, + "learning_rate": 3.884239856443061e-05, + "loss": 4.0564, + "step": 681472 + }, + { + "epoch": 1.02, + "learning_rate": 3.883401261692009e-05, + "loss": 4.0701, + "step": 681984 + }, + { + "epoch": 1.02, + "learning_rate": 3.882562666940957e-05, + "loss": 4.0406, + "step": 682496 + }, + { + "epoch": 1.02, + "learning_rate": 3.881724072189905e-05, + "loss": 4.0658, + "step": 683008 + }, + { + "epoch": 1.02, + "learning_rate": 3.880885477438853e-05, + "loss": 4.0546, + "step": 683520 + }, + { + "epoch": 1.02, + "learning_rate": 3.880046882687801e-05, + "loss": 4.0473, + "step": 684032 + }, + { + "epoch": 1.02, + "learning_rate": 3.879209925817122e-05, + "loss": 4.0533, + "step": 684544 + }, + { + "epoch": 1.02, + "learning_rate": 3.87837133106607e-05, + "loss": 4.0509, + "step": 685056 + }, + { + "epoch": 1.02, + "learning_rate": 3.8775327363150186e-05, + "loss": 4.0649, + "step": 685568 + }, + { + "epoch": 1.02, + "learning_rate": 3.8766941415639666e-05, + "loss": 4.0532, + "step": 686080 + }, + { + "epoch": 1.02, + "learning_rate": 3.8758571846932875e-05, + "loss": 4.0555, + "step": 686592 + }, + { + "epoch": 1.03, + "eval_loss": 4.078179359436035, + "eval_runtime": 303.9441, + "eval_samples_per_second": 1255.464, + "eval_steps_per_second": 39.234, + "step": 686880 + }, + { + "epoch": 0.0, + "learning_rate": 3.8750185899422355e-05, + "loss": 4.0528, + "step": 687104 + }, + { + "epoch": 0.0, + "learning_rate": 3.8741799951911835e-05, + "loss": 4.0507, + "step": 687616 + }, + { + "epoch": 0.0, + "learning_rate": 3.8733414004401314e-05, + "loss": 4.0535, + "step": 688128 + }, + { + "epoch": 0.0, + "learning_rate": 3.8725028056890794e-05, + "loss": 4.0554, + "step": 688640 + }, + { + "epoch": 0.0, + "learning_rate": 3.8716642109380274e-05, + "loss": 4.0647, + "step": 689152 + }, + { + "epoch": 0.0, + "learning_rate": 3.8708256161869754e-05, + "loss": 4.0492, + "step": 689664 + }, + { + "epoch": 0.0, + "learning_rate": 3.8699870214359234e-05, + "loss": 4.0559, + "step": 690176 + }, + { + "epoch": 0.0, + "learning_rate": 3.8691484266848714e-05, + "loss": 4.0506, + "step": 690688 + }, + { + "epoch": 0.0, + "learning_rate": 3.8683098319338194e-05, + "loss": 4.0541, + "step": 691200 + }, + { + "epoch": 0.0, + "learning_rate": 3.867471237182767e-05, + "loss": 4.063, + "step": 691712 + }, + { + "epoch": 0.0, + "learning_rate": 3.8666326424317154e-05, + "loss": 4.054, + "step": 692224 + }, + { + "epoch": 0.0, + "learning_rate": 3.8657940476806634e-05, + "loss": 4.0521, + "step": 692736 + }, + { + "epoch": 0.0, + "learning_rate": 3.864957090809985e-05, + "loss": 4.0624, + "step": 693248 + }, + { + "epoch": 0.0, + "learning_rate": 3.864118496058932e-05, + "loss": 4.0403, + "step": 693760 + }, + { + "epoch": 0.0, + "learning_rate": 3.86327990130788e-05, + "loss": 4.0508, + "step": 694272 + }, + { + "epoch": 0.0, + "learning_rate": 3.862441306556828e-05, + "loss": 4.0423, + "step": 694784 + }, + { + "epoch": 0.0, + "learning_rate": 3.861602711805776e-05, + "loss": 4.0539, + "step": 695296 + }, + { + "epoch": 0.0, + "learning_rate": 3.860764117054724e-05, + "loss": 4.0488, + "step": 695808 + }, + { + "epoch": 0.0, + "learning_rate": 3.859925522303672e-05, + "loss": 4.0468, + "step": 696320 + }, + { + "epoch": 0.0, + "learning_rate": 3.85908692755262e-05, + "loss": 4.0598, + "step": 696832 + }, + { + "epoch": 0.0, + "learning_rate": 3.858248332801568e-05, + "loss": 4.0612, + "step": 697344 + }, + { + "epoch": 0.0, + "learning_rate": 3.857409738050516e-05, + "loss": 4.0605, + "step": 697856 + }, + { + "epoch": 0.0, + "learning_rate": 3.856571143299464e-05, + "loss": 4.0545, + "step": 698368 + }, + { + "epoch": 0.0, + "learning_rate": 3.855732548548412e-05, + "loss": 4.0486, + "step": 698880 + }, + { + "epoch": 0.0, + "learning_rate": 3.85489886743848e-05, + "loss": 4.0449, + "step": 699392 + }, + { + "epoch": 0.0, + "learning_rate": 3.854060272687428e-05, + "loss": 4.055, + "step": 699904 + }, + { + "epoch": 0.0, + "learning_rate": 3.853221677936376e-05, + "loss": 4.0502, + "step": 700416 + }, + { + "epoch": 0.0, + "learning_rate": 3.852383083185324e-05, + "loss": 4.0477, + "step": 700928 + }, + { + "epoch": 0.0, + "learning_rate": 3.851544488434272e-05, + "loss": 4.0428, + "step": 701440 + }, + { + "epoch": 0.0, + "learning_rate": 3.8507058936832197e-05, + "loss": 4.0466, + "step": 701952 + }, + { + "epoch": 0.01, + "learning_rate": 3.8498672989321677e-05, + "loss": 4.0424, + "step": 702464 + }, + { + "epoch": 0.01, + "learning_rate": 3.8490287041811157e-05, + "loss": 4.0585, + "step": 702976 + }, + { + "epoch": 0.01, + "learning_rate": 3.8481901094300636e-05, + "loss": 4.0571, + "step": 703488 + }, + { + "epoch": 0.01, + "learning_rate": 3.8473515146790116e-05, + "loss": 4.0486, + "step": 704000 + }, + { + "epoch": 0.01, + "learning_rate": 3.8465145578083326e-05, + "loss": 4.0477, + "step": 704512 + }, + { + "epoch": 0.01, + "learning_rate": 3.845677600937654e-05, + "loss": 4.0484, + "step": 705024 + }, + { + "epoch": 0.01, + "learning_rate": 3.844839006186602e-05, + "loss": 4.0534, + "step": 705536 + }, + { + "epoch": 0.01, + "learning_rate": 3.84400041143555e-05, + "loss": 4.0452, + "step": 706048 + }, + { + "epoch": 0.01, + "learning_rate": 3.843161816684498e-05, + "loss": 4.0451, + "step": 706560 + }, + { + "epoch": 0.01, + "learning_rate": 3.842323221933446e-05, + "loss": 4.0352, + "step": 707072 + }, + { + "epoch": 0.01, + "learning_rate": 3.841484627182394e-05, + "loss": 4.0437, + "step": 707584 + }, + { + "epoch": 0.01, + "learning_rate": 3.840646032431342e-05, + "loss": 4.0508, + "step": 708096 + }, + { + "epoch": 0.01, + "learning_rate": 3.83980743768029e-05, + "loss": 4.0527, + "step": 708608 + }, + { + "epoch": 0.01, + "learning_rate": 3.838968842929238e-05, + "loss": 4.0452, + "step": 709120 + }, + { + "epoch": 0.01, + "learning_rate": 3.838130248178186e-05, + "loss": 4.0489, + "step": 709632 + }, + { + "epoch": 0.01, + "learning_rate": 3.837293291307507e-05, + "loss": 4.0452, + "step": 710144 + }, + { + "epoch": 0.01, + "learning_rate": 3.836454696556455e-05, + "loss": 4.0483, + "step": 710656 + }, + { + "epoch": 0.01, + "learning_rate": 3.835616101805403e-05, + "loss": 4.0464, + "step": 711168 + }, + { + "epoch": 0.01, + "learning_rate": 3.834777507054351e-05, + "loss": 4.0205, + "step": 711680 + }, + { + "epoch": 0.01, + "learning_rate": 3.833938912303299e-05, + "loss": 4.0526, + "step": 712192 + }, + { + "epoch": 0.01, + "learning_rate": 3.8331019554326206e-05, + "loss": 4.045, + "step": 712704 + }, + { + "epoch": 0.01, + "learning_rate": 3.8322633606815686e-05, + "loss": 4.0506, + "step": 713216 + }, + { + "epoch": 0.01, + "learning_rate": 3.831424765930516e-05, + "loss": 4.0419, + "step": 713728 + }, + { + "epoch": 0.01, + "learning_rate": 3.830586171179464e-05, + "loss": 4.0415, + "step": 714240 + }, + { + "epoch": 0.01, + "learning_rate": 3.829747576428412e-05, + "loss": 4.0359, + "step": 714752 + }, + { + "epoch": 0.01, + "learning_rate": 3.82890898167736e-05, + "loss": 4.0354, + "step": 715264 + }, + { + "epoch": 0.01, + "learning_rate": 3.828070386926308e-05, + "loss": 4.0452, + "step": 715776 + }, + { + "epoch": 0.01, + "learning_rate": 3.827231792175256e-05, + "loss": 4.0286, + "step": 716288 + }, + { + "epoch": 0.01, + "learning_rate": 3.826394835304577e-05, + "loss": 4.0509, + "step": 716800 + }, + { + "epoch": 0.01, + "learning_rate": 3.825557878433898e-05, + "loss": 4.0404, + "step": 717312 + }, + { + "epoch": 0.01, + "learning_rate": 3.8247192836828464e-05, + "loss": 4.0356, + "step": 717824 + }, + { + "epoch": 0.01, + "learning_rate": 3.8238806889317944e-05, + "loss": 4.0579, + "step": 718336 + }, + { + "epoch": 0.01, + "learning_rate": 3.823043732061116e-05, + "loss": 4.0276, + "step": 718848 + }, + { + "epoch": 0.01, + "learning_rate": 3.822205137310063e-05, + "loss": 4.0276, + "step": 719360 + }, + { + "epoch": 0.01, + "learning_rate": 3.821366542559011e-05, + "loss": 4.0466, + "step": 719872 + }, + { + "epoch": 0.01, + "learning_rate": 3.820527947807959e-05, + "loss": 4.0437, + "step": 720384 + }, + { + "epoch": 0.01, + "learning_rate": 3.819689353056907e-05, + "loss": 4.035, + "step": 720896 + }, + { + "epoch": 0.01, + "learning_rate": 3.818850758305855e-05, + "loss": 4.0382, + "step": 721408 + }, + { + "epoch": 0.01, + "learning_rate": 3.818012163554803e-05, + "loss": 4.0234, + "step": 721920 + }, + { + "epoch": 0.01, + "learning_rate": 3.817173568803751e-05, + "loss": 4.0418, + "step": 722432 + }, + { + "epoch": 0.01, + "learning_rate": 3.816334974052699e-05, + "loss": 4.0445, + "step": 722944 + }, + { + "epoch": 0.01, + "learning_rate": 3.815496379301647e-05, + "loss": 4.0477, + "step": 723456 + }, + { + "epoch": 0.01, + "learning_rate": 3.814657784550595e-05, + "loss": 4.0425, + "step": 723968 + }, + { + "epoch": 0.01, + "learning_rate": 3.813819189799543e-05, + "loss": 4.0487, + "step": 724480 + }, + { + "epoch": 0.01, + "learning_rate": 3.812982232928865e-05, + "loss": 4.0627, + "step": 724992 + }, + { + "epoch": 0.01, + "learning_rate": 3.812143638177813e-05, + "loss": 4.0346, + "step": 725504 + }, + { + "epoch": 0.01, + "learning_rate": 3.811306681307134e-05, + "loss": 4.0454, + "step": 726016 + }, + { + "epoch": 0.01, + "learning_rate": 3.810468086556082e-05, + "loss": 4.0411, + "step": 726528 + }, + { + "epoch": 0.01, + "learning_rate": 3.8096311296854026e-05, + "loss": 4.0381, + "step": 727040 + }, + { + "epoch": 0.01, + "learning_rate": 3.8087925349343506e-05, + "loss": 4.0337, + "step": 727552 + }, + { + "epoch": 0.01, + "learning_rate": 3.8079539401832986e-05, + "loss": 4.0513, + "step": 728064 + }, + { + "epoch": 0.01, + "learning_rate": 3.8071153454322466e-05, + "loss": 4.0433, + "step": 728576 + }, + { + "epoch": 0.01, + "learning_rate": 3.8062767506811946e-05, + "loss": 4.0491, + "step": 729088 + }, + { + "epoch": 0.01, + "learning_rate": 3.8054381559301426e-05, + "loss": 4.0304, + "step": 729600 + }, + { + "epoch": 0.01, + "learning_rate": 3.8045995611790906e-05, + "loss": 4.0359, + "step": 730112 + }, + { + "epoch": 0.01, + "learning_rate": 3.8037609664280386e-05, + "loss": 4.0381, + "step": 730624 + }, + { + "epoch": 0.01, + "learning_rate": 3.80292400955736e-05, + "loss": 4.0399, + "step": 731136 + }, + { + "epoch": 0.01, + "learning_rate": 3.802085414806308e-05, + "loss": 4.0431, + "step": 731648 + }, + { + "epoch": 0.01, + "learning_rate": 3.801246820055256e-05, + "loss": 4.0396, + "step": 732160 + }, + { + "epoch": 0.02, + "learning_rate": 3.800408225304204e-05, + "loss": 4.0274, + "step": 732672 + }, + { + "epoch": 0.02, + "learning_rate": 3.799571268433525e-05, + "loss": 4.0409, + "step": 733184 + }, + { + "epoch": 0.02, + "learning_rate": 3.798732673682473e-05, + "loss": 4.0325, + "step": 733696 + }, + { + "epoch": 0.02, + "learning_rate": 3.797894078931421e-05, + "loss": 4.035, + "step": 734208 + }, + { + "epoch": 0.02, + "learning_rate": 3.797055484180369e-05, + "loss": 4.0444, + "step": 734720 + }, + { + "epoch": 0.02, + "learning_rate": 3.7962168894293164e-05, + "loss": 4.0483, + "step": 735232 + }, + { + "epoch": 0.02, + "learning_rate": 3.7953782946782644e-05, + "loss": 4.0367, + "step": 735744 + }, + { + "epoch": 0.02, + "learning_rate": 3.7945396999272124e-05, + "loss": 4.0345, + "step": 736256 + }, + { + "epoch": 0.02, + "learning_rate": 3.793702743056534e-05, + "loss": 4.0348, + "step": 736768 + }, + { + "epoch": 0.02, + "learning_rate": 3.792864148305482e-05, + "loss": 4.037, + "step": 737280 + }, + { + "epoch": 0.02, + "learning_rate": 3.79202555355443e-05, + "loss": 4.0453, + "step": 737792 + }, + { + "epoch": 0.02, + "learning_rate": 3.791186958803378e-05, + "loss": 4.0349, + "step": 738304 + }, + { + "epoch": 0.02, + "learning_rate": 3.790348364052326e-05, + "loss": 4.0335, + "step": 738816 + }, + { + "epoch": 0.02, + "learning_rate": 3.789509769301274e-05, + "loss": 4.042, + "step": 739328 + }, + { + "epoch": 0.02, + "learning_rate": 3.788671174550222e-05, + "loss": 4.0455, + "step": 739840 + }, + { + "epoch": 0.02, + "learning_rate": 3.78783257979917e-05, + "loss": 4.0211, + "step": 740352 + }, + { + "epoch": 0.02, + "learning_rate": 3.786995622928491e-05, + "loss": 4.035, + "step": 740864 + }, + { + "epoch": 0.02, + "learning_rate": 3.786158666057812e-05, + "loss": 4.0268, + "step": 741376 + }, + { + "epoch": 0.02, + "learning_rate": 3.78532007130676e-05, + "loss": 4.0411, + "step": 741888 + }, + { + "epoch": 0.02, + "learning_rate": 3.784481476555708e-05, + "loss": 4.0264, + "step": 742400 + }, + { + "epoch": 0.02, + "learning_rate": 3.783642881804656e-05, + "loss": 4.0416, + "step": 742912 + }, + { + "epoch": 0.02, + "learning_rate": 3.782804287053604e-05, + "loss": 4.0273, + "step": 743424 + }, + { + "epoch": 0.02, + "learning_rate": 3.781965692302552e-05, + "loss": 4.0406, + "step": 743936 + }, + { + "epoch": 0.02, + "learning_rate": 3.7811270975515004e-05, + "loss": 4.0346, + "step": 744448 + }, + { + "epoch": 0.02, + "learning_rate": 3.7802885028004484e-05, + "loss": 4.0284, + "step": 744960 + }, + { + "epoch": 0.02, + "learning_rate": 3.779451545929769e-05, + "loss": 4.0345, + "step": 745472 + }, + { + "epoch": 0.02, + "learning_rate": 3.778612951178717e-05, + "loss": 4.0495, + "step": 745984 + }, + { + "epoch": 0.02, + "learning_rate": 3.777774356427665e-05, + "loss": 4.0342, + "step": 746496 + }, + { + "epoch": 0.02, + "learning_rate": 3.776937399556986e-05, + "loss": 4.0382, + "step": 747008 + }, + { + "epoch": 0.02, + "learning_rate": 3.776098804805934e-05, + "loss": 4.0338, + "step": 747520 + }, + { + "epoch": 0.02, + "learning_rate": 3.775260210054882e-05, + "loss": 4.0388, + "step": 748032 + }, + { + "epoch": 0.02, + "learning_rate": 3.77442161530383e-05, + "loss": 4.0404, + "step": 748544 + }, + { + "epoch": 0.02, + "learning_rate": 3.773584658433151e-05, + "loss": 4.0309, + "step": 749056 + }, + { + "epoch": 0.02, + "learning_rate": 3.772746063682099e-05, + "loss": 4.0251, + "step": 749568 + }, + { + "epoch": 0.02, + "learning_rate": 3.771907468931047e-05, + "loss": 4.0321, + "step": 750080 + }, + { + "epoch": 0.02, + "learning_rate": 3.771068874179996e-05, + "loss": 4.0309, + "step": 750592 + }, + { + "epoch": 0.02, + "learning_rate": 3.770230279428944e-05, + "loss": 4.0323, + "step": 751104 + }, + { + "epoch": 0.02, + "learning_rate": 3.769391684677892e-05, + "loss": 4.0298, + "step": 751616 + }, + { + "epoch": 0.02, + "learning_rate": 3.76855308992684e-05, + "loss": 4.0309, + "step": 752128 + }, + { + "epoch": 0.02, + "learning_rate": 3.7677161330561607e-05, + "loss": 4.0247, + "step": 752640 + }, + { + "epoch": 0.02, + "learning_rate": 3.7668775383051087e-05, + "loss": 4.0457, + "step": 753152 + }, + { + "epoch": 0.02, + "learning_rate": 3.7660389435540566e-05, + "loss": 4.0323, + "step": 753664 + }, + { + "epoch": 0.02, + "learning_rate": 3.7652003488030046e-05, + "loss": 4.0407, + "step": 754176 + }, + { + "epoch": 0.02, + "learning_rate": 3.7643617540519526e-05, + "loss": 4.0197, + "step": 754688 + }, + { + "epoch": 0.02, + "learning_rate": 3.7635231593009e-05, + "loss": 4.0466, + "step": 755200 + }, + { + "epoch": 0.02, + "learning_rate": 3.7626862024302215e-05, + "loss": 4.0381, + "step": 755712 + }, + { + "epoch": 0.02, + "learning_rate": 3.7618476076791695e-05, + "loss": 4.0369, + "step": 756224 + }, + { + "epoch": 0.02, + "learning_rate": 3.7610090129281175e-05, + "loss": 4.035, + "step": 756736 + }, + { + "epoch": 0.02, + "learning_rate": 3.7601704181770655e-05, + "loss": 4.0347, + "step": 757248 + }, + { + "epoch": 0.02, + "learning_rate": 3.7593318234260135e-05, + "loss": 4.0356, + "step": 757760 + }, + { + "epoch": 0.02, + "learning_rate": 3.7584932286749615e-05, + "loss": 4.0474, + "step": 758272 + }, + { + "epoch": 0.02, + "learning_rate": 3.7576546339239095e-05, + "loss": 4.0195, + "step": 758784 + }, + { + "epoch": 0.02, + "learning_rate": 3.7568160391728575e-05, + "loss": 4.0394, + "step": 759296 + }, + { + "epoch": 0.02, + "learning_rate": 3.7559774444218055e-05, + "loss": 4.029, + "step": 759808 + }, + { + "epoch": 0.02, + "learning_rate": 3.7551404875511264e-05, + "loss": 4.0285, + "step": 760320 + }, + { + "epoch": 0.02, + "learning_rate": 3.7543018928000744e-05, + "loss": 4.0325, + "step": 760832 + }, + { + "epoch": 0.02, + "learning_rate": 3.7534632980490224e-05, + "loss": 4.0286, + "step": 761344 + }, + { + "epoch": 0.02, + "learning_rate": 3.7526247032979704e-05, + "loss": 4.0381, + "step": 761856 + }, + { + "epoch": 0.02, + "learning_rate": 3.751787746427291e-05, + "loss": 4.0358, + "step": 762368 + }, + { + "epoch": 0.02, + "learning_rate": 3.750949151676239e-05, + "loss": 4.0303, + "step": 762880 + }, + { + "epoch": 0.03, + "eval_loss": 4.062327861785889, + "eval_runtime": 289.43, + "eval_samples_per_second": 1318.422, + "eval_steps_per_second": 41.202, + "step": 763200 + }, + { + "epoch": 1.0, + "learning_rate": 3.750110556925188e-05, + "loss": 4.0268, + "step": 763392 + }, + { + "epoch": 1.0, + "learning_rate": 3.749271962174136e-05, + "loss": 4.0273, + "step": 763904 + }, + { + "epoch": 1.0, + "learning_rate": 3.748435005303457e-05, + "loss": 4.0293, + "step": 764416 + }, + { + "epoch": 1.0, + "learning_rate": 3.747596410552405e-05, + "loss": 4.0357, + "step": 764928 + }, + { + "epoch": 1.0, + "learning_rate": 3.746757815801353e-05, + "loss": 4.0411, + "step": 765440 + }, + { + "epoch": 1.0, + "learning_rate": 3.745919221050301e-05, + "loss": 4.0255, + "step": 765952 + }, + { + "epoch": 1.0, + "learning_rate": 3.745082264179622e-05, + "loss": 4.0322, + "step": 766464 + }, + { + "epoch": 1.0, + "learning_rate": 3.74424366942857e-05, + "loss": 4.0316, + "step": 766976 + }, + { + "epoch": 1.0, + "learning_rate": 3.743405074677518e-05, + "loss": 4.0298, + "step": 767488 + }, + { + "epoch": 1.0, + "learning_rate": 3.742566479926466e-05, + "loss": 4.0359, + "step": 768000 + }, + { + "epoch": 1.0, + "learning_rate": 3.741727885175414e-05, + "loss": 4.0301, + "step": 768512 + }, + { + "epoch": 1.0, + "learning_rate": 3.740889290424362e-05, + "loss": 4.0337, + "step": 769024 + }, + { + "epoch": 1.0, + "learning_rate": 3.740053971434056e-05, + "loss": 4.0387, + "step": 769536 + }, + { + "epoch": 1.0, + "learning_rate": 3.739215376683004e-05, + "loss": 4.0191, + "step": 770048 + }, + { + "epoch": 1.0, + "learning_rate": 3.738376781931952e-05, + "loss": 4.0268, + "step": 770560 + }, + { + "epoch": 1.0, + "learning_rate": 3.7375381871809e-05, + "loss": 4.0154, + "step": 771072 + }, + { + "epoch": 1.0, + "learning_rate": 3.736699592429848e-05, + "loss": 4.0334, + "step": 771584 + }, + { + "epoch": 1.0, + "learning_rate": 3.735860997678796e-05, + "loss": 4.0255, + "step": 772096 + }, + { + "epoch": 1.0, + "learning_rate": 3.735022402927744e-05, + "loss": 4.0227, + "step": 772608 + }, + { + "epoch": 1.0, + "learning_rate": 3.734183808176692e-05, + "loss": 4.0346, + "step": 773120 + }, + { + "epoch": 1.0, + "learning_rate": 3.73334521342564e-05, + "loss": 4.0377, + "step": 773632 + }, + { + "epoch": 1.0, + "learning_rate": 3.732506618674588e-05, + "loss": 4.0377, + "step": 774144 + }, + { + "epoch": 1.0, + "learning_rate": 3.731668023923536e-05, + "loss": 4.0347, + "step": 774656 + }, + { + "epoch": 1.0, + "learning_rate": 3.7308294291724835e-05, + "loss": 4.0279, + "step": 775168 + }, + { + "epoch": 1.0, + "learning_rate": 3.729992472301805e-05, + "loss": 4.0278, + "step": 775680 + }, + { + "epoch": 1.0, + "learning_rate": 3.729153877550753e-05, + "loss": 4.0271, + "step": 776192 + }, + { + "epoch": 1.0, + "learning_rate": 3.728315282799701e-05, + "loss": 4.0271, + "step": 776704 + }, + { + "epoch": 1.0, + "learning_rate": 3.727476688048649e-05, + "loss": 4.0278, + "step": 777216 + }, + { + "epoch": 1.0, + "learning_rate": 3.726639731177971e-05, + "loss": 4.0247, + "step": 777728 + }, + { + "epoch": 1.0, + "learning_rate": 3.725801136426919e-05, + "loss": 4.022, + "step": 778240 + }, + { + "epoch": 1.01, + "learning_rate": 3.7249641795562396e-05, + "loss": 4.0222, + "step": 778752 + }, + { + "epoch": 1.01, + "learning_rate": 3.7241255848051876e-05, + "loss": 4.029, + "step": 779264 + }, + { + "epoch": 1.01, + "learning_rate": 3.7232869900541356e-05, + "loss": 4.0367, + "step": 779776 + }, + { + "epoch": 1.01, + "learning_rate": 3.7224483953030836e-05, + "loss": 4.0273, + "step": 780288 + }, + { + "epoch": 1.01, + "learning_rate": 3.7216114384324045e-05, + "loss": 4.0254, + "step": 780800 + }, + { + "epoch": 1.01, + "learning_rate": 3.7207728436813525e-05, + "loss": 4.0215, + "step": 781312 + }, + { + "epoch": 1.01, + "learning_rate": 3.7199342489303005e-05, + "loss": 4.0338, + "step": 781824 + }, + { + "epoch": 1.01, + "learning_rate": 3.7190956541792485e-05, + "loss": 4.0243, + "step": 782336 + }, + { + "epoch": 1.01, + "learning_rate": 3.7182570594281965e-05, + "loss": 4.0249, + "step": 782848 + }, + { + "epoch": 1.01, + "learning_rate": 3.717420102557518e-05, + "loss": 4.0117, + "step": 783360 + }, + { + "epoch": 1.01, + "learning_rate": 3.716581507806466e-05, + "loss": 4.0243, + "step": 783872 + }, + { + "epoch": 1.01, + "learning_rate": 3.7157429130554134e-05, + "loss": 4.0235, + "step": 784384 + }, + { + "epoch": 1.01, + "learning_rate": 3.7149043183043614e-05, + "loss": 4.0304, + "step": 784896 + }, + { + "epoch": 1.01, + "learning_rate": 3.7140657235533094e-05, + "loss": 4.0242, + "step": 785408 + }, + { + "epoch": 1.01, + "learning_rate": 3.7132271288022574e-05, + "loss": 4.0271, + "step": 785920 + }, + { + "epoch": 1.01, + "learning_rate": 3.7123885340512054e-05, + "loss": 4.0223, + "step": 786432 + }, + { + "epoch": 1.01, + "learning_rate": 3.7115499393001534e-05, + "loss": 4.0265, + "step": 786944 + }, + { + "epoch": 1.01, + "learning_rate": 3.710712982429474e-05, + "loss": 4.0276, + "step": 787456 + }, + { + "epoch": 1.01, + "learning_rate": 3.709874387678422e-05, + "loss": 3.999, + "step": 787968 + }, + { + "epoch": 1.01, + "learning_rate": 3.70903579292737e-05, + "loss": 4.0297, + "step": 788480 + }, + { + "epoch": 1.01, + "learning_rate": 3.708197198176319e-05, + "loss": 4.0219, + "step": 788992 + }, + { + "epoch": 1.01, + "learning_rate": 3.707358603425267e-05, + "loss": 4.0312, + "step": 789504 + }, + { + "epoch": 1.01, + "learning_rate": 3.706520008674215e-05, + "loss": 4.0201, + "step": 790016 + }, + { + "epoch": 1.01, + "learning_rate": 3.705681413923163e-05, + "loss": 4.0183, + "step": 790528 + }, + { + "epoch": 1.01, + "learning_rate": 3.704844457052484e-05, + "loss": 4.0119, + "step": 791040 + }, + { + "epoch": 1.01, + "learning_rate": 3.704005862301432e-05, + "loss": 4.015, + "step": 791552 + }, + { + "epoch": 1.01, + "learning_rate": 3.70316726755038e-05, + "loss": 4.0282, + "step": 792064 + }, + { + "epoch": 1.01, + "learning_rate": 3.702328672799328e-05, + "loss": 4.004, + "step": 792576 + }, + { + "epoch": 1.01, + "learning_rate": 3.701490078048276e-05, + "loss": 4.0316, + "step": 793088 + }, + { + "epoch": 1.01, + "learning_rate": 3.700651483297224e-05, + "loss": 4.015, + "step": 793600 + }, + { + "epoch": 1.01, + "learning_rate": 3.699814526426545e-05, + "loss": 4.0124, + "step": 794112 + }, + { + "epoch": 1.01, + "learning_rate": 3.698975931675493e-05, + "loss": 4.0366, + "step": 794624 + }, + { + "epoch": 1.01, + "learning_rate": 3.698137336924441e-05, + "loss": 4.0121, + "step": 795136 + }, + { + "epoch": 1.01, + "learning_rate": 3.697298742173389e-05, + "loss": 4.0043, + "step": 795648 + }, + { + "epoch": 1.01, + "learning_rate": 3.6964601474223374e-05, + "loss": 4.0247, + "step": 796160 + }, + { + "epoch": 1.01, + "learning_rate": 3.6956215526712854e-05, + "loss": 4.0216, + "step": 796672 + }, + { + "epoch": 1.01, + "learning_rate": 3.694782957920233e-05, + "loss": 4.0121, + "step": 797184 + }, + { + "epoch": 1.01, + "learning_rate": 3.693944363169181e-05, + "loss": 4.0181, + "step": 797696 + }, + { + "epoch": 1.01, + "learning_rate": 3.693107406298502e-05, + "loss": 4.004, + "step": 798208 + }, + { + "epoch": 1.01, + "learning_rate": 3.692270449427823e-05, + "loss": 4.0184, + "step": 798720 + }, + { + "epoch": 1.01, + "learning_rate": 3.691431854676771e-05, + "loss": 4.0264, + "step": 799232 + }, + { + "epoch": 1.01, + "learning_rate": 3.690593259925719e-05, + "loss": 4.0247, + "step": 799744 + }, + { + "epoch": 1.01, + "learning_rate": 3.689754665174667e-05, + "loss": 4.0205, + "step": 800256 + }, + { + "epoch": 1.01, + "learning_rate": 3.6889160704236145e-05, + "loss": 4.0281, + "step": 800768 + }, + { + "epoch": 1.01, + "learning_rate": 3.6880774756725625e-05, + "loss": 4.0411, + "step": 801280 + }, + { + "epoch": 1.01, + "learning_rate": 3.687238880921511e-05, + "loss": 4.0179, + "step": 801792 + }, + { + "epoch": 1.01, + "learning_rate": 3.686400286170459e-05, + "loss": 4.0206, + "step": 802304 + }, + { + "epoch": 1.01, + "learning_rate": 3.685561691419407e-05, + "loss": 4.0191, + "step": 802816 + }, + { + "epoch": 1.01, + "learning_rate": 3.684724734548728e-05, + "loss": 4.0183, + "step": 803328 + }, + { + "epoch": 1.01, + "learning_rate": 3.6838877776780496e-05, + "loss": 4.011, + "step": 803840 + }, + { + "epoch": 1.01, + "learning_rate": 3.683049182926997e-05, + "loss": 4.0325, + "step": 804352 + }, + { + "epoch": 1.01, + "learning_rate": 3.682210588175945e-05, + "loss": 4.0216, + "step": 804864 + }, + { + "epoch": 1.01, + "learning_rate": 3.681371993424893e-05, + "loss": 4.0296, + "step": 805376 + }, + { + "epoch": 1.01, + "learning_rate": 3.680533398673841e-05, + "loss": 4.0058, + "step": 805888 + }, + { + "epoch": 1.01, + "learning_rate": 3.679696441803162e-05, + "loss": 4.0186, + "step": 806400 + }, + { + "epoch": 1.01, + "learning_rate": 3.67885784705211e-05, + "loss": 4.0183, + "step": 806912 + }, + { + "epoch": 1.01, + "learning_rate": 3.678019252301058e-05, + "loss": 4.0184, + "step": 807424 + }, + { + "epoch": 1.01, + "learning_rate": 3.677180657550006e-05, + "loss": 4.0203, + "step": 807936 + }, + { + "epoch": 1.01, + "learning_rate": 3.6763437006793274e-05, + "loss": 4.0226, + "step": 808448 + }, + { + "epoch": 1.01, + "learning_rate": 3.6755051059282754e-05, + "loss": 4.0062, + "step": 808960 + }, + { + "epoch": 1.02, + "learning_rate": 3.6746665111772234e-05, + "loss": 4.0185, + "step": 809472 + }, + { + "epoch": 1.02, + "learning_rate": 3.6738279164261714e-05, + "loss": 4.0147, + "step": 809984 + }, + { + "epoch": 1.02, + "learning_rate": 3.6729893216751194e-05, + "loss": 4.0143, + "step": 810496 + }, + { + "epoch": 1.02, + "learning_rate": 3.6721507269240674e-05, + "loss": 4.0236, + "step": 811008 + }, + { + "epoch": 1.02, + "learning_rate": 3.671313770053388e-05, + "loss": 4.0298, + "step": 811520 + }, + { + "epoch": 1.02, + "learning_rate": 3.670475175302336e-05, + "loss": 4.0157, + "step": 812032 + }, + { + "epoch": 1.02, + "learning_rate": 3.669636580551284e-05, + "loss": 4.0134, + "step": 812544 + }, + { + "epoch": 1.02, + "learning_rate": 3.668797985800232e-05, + "loss": 4.0159, + "step": 813056 + }, + { + "epoch": 1.02, + "learning_rate": 3.66795939104918e-05, + "loss": 4.0121, + "step": 813568 + }, + { + "epoch": 1.02, + "learning_rate": 3.667120796298128e-05, + "loss": 4.0249, + "step": 814080 + }, + { + "epoch": 1.02, + "learning_rate": 3.666282201547076e-05, + "loss": 4.015, + "step": 814592 + }, + { + "epoch": 1.02, + "learning_rate": 3.665443606796024e-05, + "loss": 4.0165, + "step": 815104 + }, + { + "epoch": 1.02, + "learning_rate": 3.664606649925346e-05, + "loss": 4.0196, + "step": 815616 + }, + { + "epoch": 1.02, + "learning_rate": 3.663768055174294e-05, + "loss": 4.0154, + "step": 816128 + }, + { + "epoch": 1.02, + "learning_rate": 3.662931098303615e-05, + "loss": 4.0114, + "step": 816640 + }, + { + "epoch": 1.02, + "learning_rate": 3.662092503552563e-05, + "loss": 4.0117, + "step": 817152 + }, + { + "epoch": 1.02, + "learning_rate": 3.661253908801511e-05, + "loss": 4.0048, + "step": 817664 + }, + { + "epoch": 1.02, + "learning_rate": 3.660415314050459e-05, + "loss": 4.0201, + "step": 818176 + }, + { + "epoch": 1.02, + "learning_rate": 3.659576719299407e-05, + "loss": 4.0137, + "step": 818688 + }, + { + "epoch": 1.02, + "learning_rate": 3.658738124548355e-05, + "loss": 4.0159, + "step": 819200 + }, + { + "epoch": 1.02, + "learning_rate": 3.657899529797303e-05, + "loss": 4.0023, + "step": 819712 + }, + { + "epoch": 1.02, + "learning_rate": 3.657060935046251e-05, + "loss": 4.0178, + "step": 820224 + }, + { + "epoch": 1.02, + "learning_rate": 3.6562239781755717e-05, + "loss": 4.0191, + "step": 820736 + }, + { + "epoch": 1.02, + "learning_rate": 3.6553853834245197e-05, + "loss": 4.0098, + "step": 821248 + }, + { + "epoch": 1.02, + "learning_rate": 3.654546788673468e-05, + "loss": 4.0172, + "step": 821760 + }, + { + "epoch": 1.02, + "learning_rate": 3.653709831802789e-05, + "loss": 4.0274, + "step": 822272 + }, + { + "epoch": 1.02, + "learning_rate": 3.652871237051737e-05, + "loss": 4.0095, + "step": 822784 + }, + { + "epoch": 1.02, + "learning_rate": 3.652034280181058e-05, + "loss": 4.0202, + "step": 823296 + }, + { + "epoch": 1.02, + "learning_rate": 3.651195685430006e-05, + "loss": 4.0142, + "step": 823808 + }, + { + "epoch": 1.02, + "learning_rate": 3.650357090678954e-05, + "loss": 4.0182, + "step": 824320 + }, + { + "epoch": 1.02, + "learning_rate": 3.649518495927902e-05, + "loss": 4.0178, + "step": 824832 + }, + { + "epoch": 1.02, + "learning_rate": 3.64867990117685e-05, + "loss": 4.0103, + "step": 825344 + }, + { + "epoch": 1.02, + "learning_rate": 3.647841306425798e-05, + "loss": 4.0074, + "step": 825856 + }, + { + "epoch": 1.02, + "learning_rate": 3.6470027116747454e-05, + "loss": 4.0126, + "step": 826368 + }, + { + "epoch": 1.02, + "learning_rate": 3.6461641169236934e-05, + "loss": 4.0141, + "step": 826880 + }, + { + "epoch": 1.02, + "learning_rate": 3.645327160053015e-05, + "loss": 4.0151, + "step": 827392 + }, + { + "epoch": 1.02, + "learning_rate": 3.644488565301963e-05, + "loss": 4.0038, + "step": 827904 + }, + { + "epoch": 1.02, + "learning_rate": 3.643649970550911e-05, + "loss": 4.012, + "step": 828416 + }, + { + "epoch": 1.02, + "learning_rate": 3.642811375799859e-05, + "loss": 4.0015, + "step": 828928 + }, + { + "epoch": 1.02, + "learning_rate": 3.641972781048807e-05, + "loss": 4.026, + "step": 829440 + }, + { + "epoch": 1.02, + "learning_rate": 3.641134186297755e-05, + "loss": 4.0124, + "step": 829952 + }, + { + "epoch": 1.02, + "learning_rate": 3.640295591546703e-05, + "loss": 4.0207, + "step": 830464 + }, + { + "epoch": 1.02, + "learning_rate": 3.639456996795651e-05, + "loss": 4.0021, + "step": 830976 + }, + { + "epoch": 1.02, + "learning_rate": 3.638618402044599e-05, + "loss": 4.0237, + "step": 831488 + }, + { + "epoch": 1.02, + "learning_rate": 3.63778144517392e-05, + "loss": 4.0159, + "step": 832000 + }, + { + "epoch": 1.02, + "learning_rate": 3.636942850422868e-05, + "loss": 4.0155, + "step": 832512 + }, + { + "epoch": 1.02, + "learning_rate": 3.636104255671816e-05, + "loss": 4.0178, + "step": 833024 + }, + { + "epoch": 1.02, + "learning_rate": 3.635265660920764e-05, + "loss": 4.0131, + "step": 833536 + }, + { + "epoch": 1.02, + "learning_rate": 3.6344287040500855e-05, + "loss": 4.0136, + "step": 834048 + }, + { + "epoch": 1.02, + "learning_rate": 3.6335901092990335e-05, + "loss": 4.0278, + "step": 834560 + }, + { + "epoch": 1.02, + "learning_rate": 3.6327515145479815e-05, + "loss": 4.0008, + "step": 835072 + }, + { + "epoch": 1.02, + "learning_rate": 3.6319129197969295e-05, + "loss": 4.0197, + "step": 835584 + }, + { + "epoch": 1.02, + "learning_rate": 3.6310743250458775e-05, + "loss": 4.0079, + "step": 836096 + }, + { + "epoch": 1.02, + "learning_rate": 3.6302373681751984e-05, + "loss": 4.0096, + "step": 836608 + }, + { + "epoch": 1.02, + "learning_rate": 3.6293987734241464e-05, + "loss": 4.0118, + "step": 837120 + }, + { + "epoch": 1.02, + "learning_rate": 3.6285601786730944e-05, + "loss": 4.0082, + "step": 837632 + }, + { + "epoch": 1.02, + "learning_rate": 3.6277215839220423e-05, + "loss": 4.0178, + "step": 838144 + }, + { + "epoch": 1.02, + "learning_rate": 3.626884627051363e-05, + "loss": 4.0187, + "step": 838656 + }, + { + "epoch": 1.02, + "learning_rate": 3.626047670180684e-05, + "loss": 4.0098, + "step": 839168 + }, + { + "epoch": 1.03, + "eval_loss": 4.0497660636901855, + "eval_runtime": 287.7861, + "eval_samples_per_second": 1325.953, + "eval_steps_per_second": 41.437, + "step": 839520 + }, + { + "epoch": 0.0, + "learning_rate": 3.625209075429633e-05, + "loss": 4.0086, + "step": 839680 + }, + { + "epoch": 0.0, + "learning_rate": 3.624370480678581e-05, + "loss": 4.0083, + "step": 840192 + }, + { + "epoch": 0.0, + "learning_rate": 3.623531885927529e-05, + "loss": 4.0108, + "step": 840704 + }, + { + "epoch": 0.0, + "learning_rate": 3.622693291176477e-05, + "loss": 4.0136, + "step": 841216 + }, + { + "epoch": 0.0, + "learning_rate": 3.621854696425425e-05, + "loss": 4.0185, + "step": 841728 + }, + { + "epoch": 0.0, + "learning_rate": 3.621016101674373e-05, + "loss": 4.0076, + "step": 842240 + }, + { + "epoch": 0.0, + "learning_rate": 3.620177506923321e-05, + "loss": 4.0147, + "step": 842752 + }, + { + "epoch": 0.0, + "learning_rate": 3.619338912172269e-05, + "loss": 4.0105, + "step": 843264 + }, + { + "epoch": 0.0, + "learning_rate": 3.618500317421217e-05, + "loss": 4.0082, + "step": 843776 + }, + { + "epoch": 0.0, + "learning_rate": 3.617661722670164e-05, + "loss": 4.0103, + "step": 844288 + }, + { + "epoch": 0.0, + "learning_rate": 3.616823127919112e-05, + "loss": 4.0173, + "step": 844800 + }, + { + "epoch": 0.0, + "learning_rate": 3.61598453316806e-05, + "loss": 4.0088, + "step": 845312 + }, + { + "epoch": 0.0, + "learning_rate": 3.615147576297381e-05, + "loss": 4.0195, + "step": 845824 + }, + { + "epoch": 0.0, + "learning_rate": 3.614308981546329e-05, + "loss": 3.9992, + "step": 846336 + }, + { + "epoch": 0.0, + "learning_rate": 3.613470386795278e-05, + "loss": 4.0082, + "step": 846848 + }, + { + "epoch": 0.0, + "learning_rate": 3.612631792044226e-05, + "loss": 3.9934, + "step": 847360 + }, + { + "epoch": 0.0, + "learning_rate": 3.611793197293174e-05, + "loss": 4.0189, + "step": 847872 + }, + { + "epoch": 0.0, + "learning_rate": 3.610954602542122e-05, + "loss": 4.007, + "step": 848384 + }, + { + "epoch": 0.0, + "learning_rate": 3.61011600779107e-05, + "loss": 4.0017, + "step": 848896 + }, + { + "epoch": 0.0, + "learning_rate": 3.609277413040018e-05, + "loss": 4.0166, + "step": 849408 + }, + { + "epoch": 0.0, + "learning_rate": 3.608438818288966e-05, + "loss": 4.0187, + "step": 849920 + }, + { + "epoch": 0.0, + "learning_rate": 3.607600223537914e-05, + "loss": 4.0148, + "step": 850432 + }, + { + "epoch": 0.0, + "learning_rate": 3.6067616287868617e-05, + "loss": 4.0164, + "step": 850944 + }, + { + "epoch": 0.0, + "learning_rate": 3.6059230340358097e-05, + "loss": 4.0097, + "step": 851456 + }, + { + "epoch": 0.0, + "learning_rate": 3.6050860771651306e-05, + "loss": 4.0104, + "step": 851968 + }, + { + "epoch": 0.0, + "learning_rate": 3.6042474824140786e-05, + "loss": 4.0119, + "step": 852480 + }, + { + "epoch": 0.0, + "learning_rate": 3.6034088876630266e-05, + "loss": 3.9996, + "step": 852992 + }, + { + "epoch": 0.0, + "learning_rate": 3.6025702929119745e-05, + "loss": 4.008, + "step": 853504 + }, + { + "epoch": 0.0, + "learning_rate": 3.6017316981609225e-05, + "loss": 4.0069, + "step": 854016 + }, + { + "epoch": 0.0, + "learning_rate": 3.600894741290244e-05, + "loss": 4.0022, + "step": 854528 + }, + { + "epoch": 0.01, + "learning_rate": 3.600056146539192e-05, + "loss": 4.0033, + "step": 855040 + }, + { + "epoch": 0.01, + "learning_rate": 3.59921755178814e-05, + "loss": 4.0107, + "step": 855552 + }, + { + "epoch": 0.01, + "learning_rate": 3.598378957037088e-05, + "loss": 4.0128, + "step": 856064 + }, + { + "epoch": 0.01, + "learning_rate": 3.597542000166409e-05, + "loss": 4.0164, + "step": 856576 + }, + { + "epoch": 0.01, + "learning_rate": 3.596703405415357e-05, + "loss": 4.0023, + "step": 857088 + }, + { + "epoch": 0.01, + "learning_rate": 3.595866448544678e-05, + "loss": 4.0026, + "step": 857600 + }, + { + "epoch": 0.01, + "learning_rate": 3.595027853793626e-05, + "loss": 4.0154, + "step": 858112 + }, + { + "epoch": 0.01, + "learning_rate": 3.594189259042574e-05, + "loss": 4.0025, + "step": 858624 + }, + { + "epoch": 0.01, + "learning_rate": 3.593350664291522e-05, + "loss": 4.0085, + "step": 859136 + }, + { + "epoch": 0.01, + "learning_rate": 3.592513707420843e-05, + "loss": 3.9966, + "step": 859648 + }, + { + "epoch": 0.01, + "learning_rate": 3.5916751126697915e-05, + "loss": 4.0004, + "step": 860160 + }, + { + "epoch": 0.01, + "learning_rate": 3.5908365179187395e-05, + "loss": 4.0062, + "step": 860672 + }, + { + "epoch": 0.01, + "learning_rate": 3.5899979231676875e-05, + "loss": 4.0129, + "step": 861184 + }, + { + "epoch": 0.01, + "learning_rate": 3.5891593284166355e-05, + "loss": 4.0046, + "step": 861696 + }, + { + "epoch": 0.01, + "learning_rate": 3.588320733665583e-05, + "loss": 4.0043, + "step": 862208 + }, + { + "epoch": 0.01, + "learning_rate": 3.587482138914531e-05, + "loss": 4.0057, + "step": 862720 + }, + { + "epoch": 0.01, + "learning_rate": 3.5866451820438524e-05, + "loss": 4.0066, + "step": 863232 + }, + { + "epoch": 0.01, + "learning_rate": 3.5858065872928004e-05, + "loss": 4.0106, + "step": 863744 + }, + { + "epoch": 0.01, + "learning_rate": 3.584967992541748e-05, + "loss": 3.984, + "step": 864256 + }, + { + "epoch": 0.01, + "learning_rate": 3.584129397790696e-05, + "loss": 4.0074, + "step": 864768 + }, + { + "epoch": 0.01, + "learning_rate": 3.583290803039644e-05, + "loss": 4.0029, + "step": 865280 + }, + { + "epoch": 0.01, + "learning_rate": 3.582452208288592e-05, + "loss": 4.0125, + "step": 865792 + }, + { + "epoch": 0.01, + "learning_rate": 3.58161361353754e-05, + "loss": 4.0028, + "step": 866304 + }, + { + "epoch": 0.01, + "learning_rate": 3.5807750187864884e-05, + "loss": 3.9974, + "step": 866816 + }, + { + "epoch": 0.01, + "learning_rate": 3.579938061915809e-05, + "loss": 3.996, + "step": 867328 + }, + { + "epoch": 0.01, + "learning_rate": 3.579099467164757e-05, + "loss": 3.9949, + "step": 867840 + }, + { + "epoch": 0.01, + "learning_rate": 3.578260872413705e-05, + "loss": 4.0081, + "step": 868352 + }, + { + "epoch": 0.01, + "learning_rate": 3.577422277662653e-05, + "loss": 3.9854, + "step": 868864 + }, + { + "epoch": 0.01, + "learning_rate": 3.576585320791974e-05, + "loss": 4.0152, + "step": 869376 + }, + { + "epoch": 0.01, + "learning_rate": 3.575746726040922e-05, + "loss": 3.9997, + "step": 869888 + }, + { + "epoch": 0.01, + "learning_rate": 3.574909769170243e-05, + "loss": 3.9905, + "step": 870400 + }, + { + "epoch": 0.01, + "learning_rate": 3.574071174419191e-05, + "loss": 4.0163, + "step": 870912 + }, + { + "epoch": 0.01, + "learning_rate": 3.573232579668139e-05, + "loss": 3.9918, + "step": 871424 + }, + { + "epoch": 0.01, + "learning_rate": 3.572393984917087e-05, + "loss": 3.9885, + "step": 871936 + }, + { + "epoch": 0.01, + "learning_rate": 3.571555390166035e-05, + "loss": 4.005, + "step": 872448 + }, + { + "epoch": 0.01, + "learning_rate": 3.570716795414983e-05, + "loss": 4.0052, + "step": 872960 + }, + { + "epoch": 0.01, + "learning_rate": 3.569878200663932e-05, + "loss": 3.9909, + "step": 873472 + }, + { + "epoch": 0.01, + "learning_rate": 3.56903960591288e-05, + "loss": 4.003, + "step": 873984 + }, + { + "epoch": 0.01, + "learning_rate": 3.5682026490422006e-05, + "loss": 3.9849, + "step": 874496 + }, + { + "epoch": 0.01, + "learning_rate": 3.5673640542911486e-05, + "loss": 3.9991, + "step": 875008 + }, + { + "epoch": 0.01, + "learning_rate": 3.5665254595400966e-05, + "loss": 4.0083, + "step": 875520 + }, + { + "epoch": 0.01, + "learning_rate": 3.5656868647890446e-05, + "loss": 4.0045, + "step": 876032 + }, + { + "epoch": 0.01, + "learning_rate": 3.5648482700379926e-05, + "loss": 4.003, + "step": 876544 + }, + { + "epoch": 0.01, + "learning_rate": 3.5640096752869406e-05, + "loss": 4.0061, + "step": 877056 + }, + { + "epoch": 0.01, + "learning_rate": 3.5631710805358886e-05, + "loss": 4.022, + "step": 877568 + }, + { + "epoch": 0.01, + "learning_rate": 3.5623341236652095e-05, + "loss": 4.0004, + "step": 878080 + }, + { + "epoch": 0.01, + "learning_rate": 3.5614955289141575e-05, + "loss": 4.0049, + "step": 878592 + }, + { + "epoch": 0.01, + "learning_rate": 3.5606569341631055e-05, + "loss": 3.9969, + "step": 879104 + }, + { + "epoch": 0.01, + "learning_rate": 3.5598183394120535e-05, + "loss": 3.9993, + "step": 879616 + }, + { + "epoch": 0.01, + "learning_rate": 3.5589797446610015e-05, + "loss": 3.9955, + "step": 880128 + }, + { + "epoch": 0.01, + "learning_rate": 3.558142787790323e-05, + "loss": 4.0113, + "step": 880640 + }, + { + "epoch": 0.01, + "learning_rate": 3.557304193039271e-05, + "loss": 4.0051, + "step": 881152 + }, + { + "epoch": 0.01, + "learning_rate": 3.556465598288219e-05, + "loss": 4.0122, + "step": 881664 + }, + { + "epoch": 0.01, + "learning_rate": 3.5556270035371664e-05, + "loss": 3.9922, + "step": 882176 + }, + { + "epoch": 0.01, + "learning_rate": 3.5547884087861144e-05, + "loss": 3.9985, + "step": 882688 + }, + { + "epoch": 0.01, + "learning_rate": 3.553951451915436e-05, + "loss": 3.9972, + "step": 883200 + }, + { + "epoch": 0.01, + "learning_rate": 3.553112857164383e-05, + "loss": 3.9984, + "step": 883712 + }, + { + "epoch": 0.01, + "learning_rate": 3.552274262413331e-05, + "loss": 4.0002, + "step": 884224 + }, + { + "epoch": 0.01, + "learning_rate": 3.551435667662279e-05, + "loss": 4.0034, + "step": 884736 + }, + { + "epoch": 0.01, + "learning_rate": 3.550597072911227e-05, + "loss": 3.9905, + "step": 885248 + }, + { + "epoch": 0.02, + "learning_rate": 3.549758478160175e-05, + "loss": 3.9993, + "step": 885760 + }, + { + "epoch": 0.02, + "learning_rate": 3.548919883409124e-05, + "loss": 3.9963, + "step": 886272 + }, + { + "epoch": 0.02, + "learning_rate": 3.548081288658072e-05, + "loss": 3.9929, + "step": 886784 + }, + { + "epoch": 0.02, + "learning_rate": 3.54724269390702e-05, + "loss": 4.0076, + "step": 887296 + }, + { + "epoch": 0.02, + "learning_rate": 3.546407374916714e-05, + "loss": 4.0127, + "step": 887808 + }, + { + "epoch": 0.02, + "learning_rate": 3.545568780165662e-05, + "loss": 4.0016, + "step": 888320 + }, + { + "epoch": 0.02, + "learning_rate": 3.54473018541461e-05, + "loss": 3.993, + "step": 888832 + }, + { + "epoch": 0.02, + "learning_rate": 3.543891590663558e-05, + "loss": 3.9992, + "step": 889344 + }, + { + "epoch": 0.02, + "learning_rate": 3.543052995912506e-05, + "loss": 3.9944, + "step": 889856 + }, + { + "epoch": 0.02, + "learning_rate": 3.542214401161454e-05, + "loss": 4.0033, + "step": 890368 + }, + { + "epoch": 0.02, + "learning_rate": 3.541375806410402e-05, + "loss": 4.0026, + "step": 890880 + }, + { + "epoch": 0.02, + "learning_rate": 3.54053721165935e-05, + "loss": 3.9926, + "step": 891392 + }, + { + "epoch": 0.02, + "learning_rate": 3.539698616908298e-05, + "loss": 4.0041, + "step": 891904 + }, + { + "epoch": 0.02, + "learning_rate": 3.538861660037619e-05, + "loss": 3.9983, + "step": 892416 + }, + { + "epoch": 0.02, + "learning_rate": 3.538023065286567e-05, + "loss": 3.995, + "step": 892928 + }, + { + "epoch": 0.02, + "learning_rate": 3.537184470535515e-05, + "loss": 3.9923, + "step": 893440 + }, + { + "epoch": 0.02, + "learning_rate": 3.536347513664836e-05, + "loss": 3.9901, + "step": 893952 + }, + { + "epoch": 0.02, + "learning_rate": 3.535508918913784e-05, + "loss": 3.9986, + "step": 894464 + }, + { + "epoch": 0.02, + "learning_rate": 3.534670324162732e-05, + "loss": 3.9985, + "step": 894976 + }, + { + "epoch": 0.02, + "learning_rate": 3.533833367292053e-05, + "loss": 3.9953, + "step": 895488 + }, + { + "epoch": 0.02, + "learning_rate": 3.532994772541001e-05, + "loss": 3.9859, + "step": 896000 + }, + { + "epoch": 0.02, + "learning_rate": 3.532156177789949e-05, + "loss": 3.9966, + "step": 896512 + }, + { + "epoch": 0.02, + "learning_rate": 3.531317583038897e-05, + "loss": 4.0027, + "step": 897024 + }, + { + "epoch": 0.02, + "learning_rate": 3.530478988287845e-05, + "loss": 3.9913, + "step": 897536 + }, + { + "epoch": 0.02, + "learning_rate": 3.529640393536793e-05, + "loss": 4.002, + "step": 898048 + }, + { + "epoch": 0.02, + "learning_rate": 3.528801798785741e-05, + "loss": 4.0081, + "step": 898560 + }, + { + "epoch": 0.02, + "learning_rate": 3.527963204034689e-05, + "loss": 3.9959, + "step": 899072 + }, + { + "epoch": 0.02, + "learning_rate": 3.527124609283637e-05, + "loss": 3.9994, + "step": 899584 + }, + { + "epoch": 0.02, + "learning_rate": 3.526286014532585e-05, + "loss": 4.0002, + "step": 900096 + }, + { + "epoch": 0.02, + "learning_rate": 3.525447419781533e-05, + "loss": 4.0023, + "step": 900608 + }, + { + "epoch": 0.02, + "learning_rate": 3.524608825030481e-05, + "loss": 4.0015, + "step": 901120 + }, + { + "epoch": 0.02, + "learning_rate": 3.5237718681598027e-05, + "loss": 3.9905, + "step": 901632 + }, + { + "epoch": 0.02, + "learning_rate": 3.52293327340875e-05, + "loss": 3.9897, + "step": 902144 + }, + { + "epoch": 0.02, + "learning_rate": 3.522094678657698e-05, + "loss": 3.9954, + "step": 902656 + }, + { + "epoch": 0.02, + "learning_rate": 3.521256083906646e-05, + "loss": 3.9947, + "step": 903168 + }, + { + "epoch": 0.02, + "learning_rate": 3.520417489155594e-05, + "loss": 3.9939, + "step": 903680 + }, + { + "epoch": 0.02, + "learning_rate": 3.519580532284915e-05, + "loss": 3.9935, + "step": 904192 + }, + { + "epoch": 0.02, + "learning_rate": 3.518741937533863e-05, + "loss": 3.9887, + "step": 904704 + }, + { + "epoch": 0.02, + "learning_rate": 3.5179049806631844e-05, + "loss": 3.9852, + "step": 905216 + }, + { + "epoch": 0.02, + "learning_rate": 3.5170663859121324e-05, + "loss": 4.0091, + "step": 905728 + }, + { + "epoch": 0.02, + "learning_rate": 3.5162277911610804e-05, + "loss": 3.993, + "step": 906240 + }, + { + "epoch": 0.02, + "learning_rate": 3.5153891964100284e-05, + "loss": 4.0069, + "step": 906752 + }, + { + "epoch": 0.02, + "learning_rate": 3.5145506016589764e-05, + "loss": 3.9838, + "step": 907264 + }, + { + "epoch": 0.02, + "learning_rate": 3.5137136447882973e-05, + "loss": 4.0064, + "step": 907776 + }, + { + "epoch": 0.02, + "learning_rate": 3.512875050037245e-05, + "loss": 4.0014, + "step": 908288 + }, + { + "epoch": 0.02, + "learning_rate": 3.512036455286193e-05, + "loss": 3.9981, + "step": 908800 + }, + { + "epoch": 0.02, + "learning_rate": 3.511197860535141e-05, + "loss": 3.995, + "step": 909312 + }, + { + "epoch": 0.02, + "learning_rate": 3.510359265784089e-05, + "loss": 3.9984, + "step": 909824 + }, + { + "epoch": 0.02, + "learning_rate": 3.509520671033037e-05, + "loss": 3.9998, + "step": 910336 + }, + { + "epoch": 0.02, + "learning_rate": 3.508682076281985e-05, + "loss": 4.0056, + "step": 910848 + }, + { + "epoch": 0.02, + "learning_rate": 3.507845119411306e-05, + "loss": 3.9889, + "step": 911360 + }, + { + "epoch": 0.02, + "learning_rate": 3.507006524660255e-05, + "loss": 3.9948, + "step": 911872 + }, + { + "epoch": 0.02, + "learning_rate": 3.506167929909203e-05, + "loss": 3.9946, + "step": 912384 + }, + { + "epoch": 0.02, + "learning_rate": 3.505329335158151e-05, + "loss": 3.9918, + "step": 912896 + }, + { + "epoch": 0.02, + "learning_rate": 3.504490740407099e-05, + "loss": 3.9921, + "step": 913408 + }, + { + "epoch": 0.02, + "learning_rate": 3.50365378353642e-05, + "loss": 3.9949, + "step": 913920 + }, + { + "epoch": 0.02, + "learning_rate": 3.502815188785368e-05, + "loss": 3.9977, + "step": 914432 + }, + { + "epoch": 0.02, + "learning_rate": 3.501976594034316e-05, + "loss": 3.9974, + "step": 914944 + }, + { + "epoch": 0.02, + "learning_rate": 3.501137999283264e-05, + "loss": 3.9926, + "step": 915456 + }, + { + "epoch": 0.03, + "eval_loss": 4.03889274597168, + "eval_runtime": 298.1669, + "eval_samples_per_second": 1279.79, + "eval_steps_per_second": 39.994, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.500299404532212e-05, + "loss": 3.9973, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.49946080978116e-05, + "loss": 3.9877, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.498622215030108e-05, + "loss": 3.996, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.497783620279056e-05, + "loss": 3.9981, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.496945025528003e-05, + "loss": 3.9966, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.496106430776952e-05, + "loss": 3.9952, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.4952678360259e-05, + "loss": 3.997, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.494429241274848e-05, + "loss": 3.9942, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.493590646523796e-05, + "loss": 3.9897, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.492752051772744e-05, + "loss": 3.9951, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.491913457021692e-05, + "loss": 4.0017, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.49107486227064e-05, + "loss": 3.991, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.4902379053999606e-05, + "loss": 4.0094, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.4893993106489086e-05, + "loss": 3.9779, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.4885607158978566e-05, + "loss": 3.9901, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.4877221211468046e-05, + "loss": 3.9794, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.4868835263957526e-05, + "loss": 4.0024, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.4860449316447006e-05, + "loss": 3.9894, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.4852063368936486e-05, + "loss": 3.986, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.4843677421425966e-05, + "loss": 3.9957, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.4835291473915446e-05, + "loss": 4.002, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.482692190520866e-05, + "loss": 3.9997, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.481853595769814e-05, + "loss": 3.9983, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.481015001018762e-05, + "loss": 3.9933, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.48017640626771e-05, + "loss": 3.9974, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.4793378115166575e-05, + "loss": 3.9929, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.4784992167656055e-05, + "loss": 3.9827, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.4776606220145535e-05, + "loss": 3.9893, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.4768220272635015e-05, + "loss": 3.9903, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.4759850703928224e-05, + "loss": 3.9835, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.4751464756417704e-05, + "loss": 3.9919, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.4743078808907184e-05, + "loss": 3.991, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.4734692861396664e-05, + "loss": 3.9968, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.472630691388615e-05, + "loss": 3.9999, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.471793734517936e-05, + "loss": 3.9866, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.4709567776472575e-05, + "loss": 3.9871, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.470118182896205e-05, + "loss": 3.9995, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469279588145153e-05, + "loss": 3.9832, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468440993394101e-05, + "loss": 3.9904, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467602398643049e-05, + "loss": 3.984, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466763803891997e-05, + "loss": 3.9804, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.465925209140945e-05, + "loss": 3.9906, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465086614389893e-05, + "loss": 3.9981, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464249657519214e-05, + "loss": 3.9867, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.463412700648535e-05, + "loss": 3.9894, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.462574105897483e-05, + "loss": 3.9894, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.461735511146431e-05, + "loss": 3.9885, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.460896916395379e-05, + "loss": 3.9947, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.460058321644327e-05, + "loss": 3.9675, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.459219726893275e-05, + "loss": 3.9909, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.458382770022596e-05, + "loss": 3.9835, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.457544175271544e-05, + "loss": 3.9983, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.456705580520492e-05, + "loss": 3.9829, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.45586698576944e-05, + "loss": 3.9842, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.455028391018388e-05, + "loss": 3.98, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.454191434147709e-05, + "loss": 3.9791, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.453352839396657e-05, + "loss": 3.9914, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.452514244645606e-05, + "loss": 3.9669, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.451675649894554e-05, + "loss": 3.9979, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.450838693023875e-05, + "loss": 3.9851, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.450000098272823e-05, + "loss": 3.9741, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449161503521771e-05, + "loss": 4.0025, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.448322908770719e-05, + "loss": 3.9724, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.447484314019667e-05, + "loss": 3.9733, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.446645719268615e-05, + "loss": 3.9844, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.4458071245175627e-05, + "loss": 3.9903, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.4449685297665107e-05, + "loss": 3.9768, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.444129935015458e-05, + "loss": 3.9877, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.443291340264406e-05, + "loss": 3.9648, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.442452745513354e-05, + "loss": 3.9825, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.4416157886426756e-05, + "loss": 3.993, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.4407771938916235e-05, + "loss": 3.9906, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.4399385991405715e-05, + "loss": 3.9866, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.4391000043895195e-05, + "loss": 3.9898, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.4382630475188404e-05, + "loss": 4.0052, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.4374244527677884e-05, + "loss": 3.9847, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.4365858580167364e-05, + "loss": 3.991, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.4357472632656844e-05, + "loss": 3.9764, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.4349086685146324e-05, + "loss": 3.9868, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.4340700737635804e-05, + "loss": 3.9764, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.4332314790125284e-05, + "loss": 3.9943, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.4323928842614764e-05, + "loss": 3.9879, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.4315542895104244e-05, + "loss": 3.9956, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.4307156947593724e-05, + "loss": 3.9796, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.429877100008321e-05, + "loss": 3.9795, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.429038505257269e-05, + "loss": 3.9788, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.42820154838659e-05, + "loss": 3.9885, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.427362953635538e-05, + "loss": 3.9801, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.426524358884486e-05, + "loss": 3.9886, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.425687402013807e-05, + "loss": 3.9773, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.424848807262755e-05, + "loss": 3.981, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.424010212511703e-05, + "loss": 3.9808, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.423171617760651e-05, + "loss": 3.9772, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.422333023009599e-05, + "loss": 3.9869, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.42149606613892e-05, + "loss": 3.9993, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.420657471387868e-05, + "loss": 3.9861, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.419818876636816e-05, + "loss": 3.9775, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.4189802818857644e-05, + "loss": 3.9821, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.4181416871347124e-05, + "loss": 3.9812, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.41730309238366e-05, + "loss": 3.987, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.4164661355129813e-05, + "loss": 3.9858, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.4156275407619293e-05, + "loss": 3.9754, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.4147889460108767e-05, + "loss": 3.9874, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.4139503512598247e-05, + "loss": 3.9848, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.4131117565087726e-05, + "loss": 3.9788, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.4122731617577206e-05, + "loss": 3.9772, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.4114362048870416e-05, + "loss": 3.9768, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.4105976101359895e-05, + "loss": 3.9798, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.409759015384938e-05, + "loss": 3.9818, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.408920420633886e-05, + "loss": 3.9779, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.408081825882834e-05, + "loss": 3.9684, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.407243231131782e-05, + "loss": 3.9792, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.406406274261103e-05, + "loss": 3.9871, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.405567679510051e-05, + "loss": 3.9775, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.404729084758999e-05, + "loss": 3.9834, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.403890490007947e-05, + "loss": 3.9888, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.403051895256895e-05, + "loss": 3.9829, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.402214938386216e-05, + "loss": 3.9842, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.401376343635164e-05, + "loss": 3.9837, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.400537748884112e-05, + "loss": 3.9864, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.39969915413306e-05, + "loss": 3.9906, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398860559382008e-05, + "loss": 3.9715, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.398021964630957e-05, + "loss": 3.9773, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.397183369879905e-05, + "loss": 3.9761, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.3963447751288527e-05, + "loss": 3.9808, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.3955078182581736e-05, + "loss": 3.9802, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.3946692235071216e-05, + "loss": 3.9742, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.3938306287560696e-05, + "loss": 3.9717, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.3929920340050176e-05, + "loss": 3.9725, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.3921534392539655e-05, + "loss": 3.9915, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.391314844502913e-05, + "loss": 3.9811, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.390476249751861e-05, + "loss": 3.9863, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.389637655000809e-05, + "loss": 3.9735, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.3888006981301304e-05, + "loss": 3.9881, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.387963741259452e-05, + "loss": 3.987, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.3871251465084e-05, + "loss": 3.9824, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.386286551757348e-05, + "loss": 3.978, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.3854479570062953e-05, + "loss": 3.9836, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.384609362255243e-05, + "loss": 3.987, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.383770767504191e-05, + "loss": 3.9899, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.382932172753139e-05, + "loss": 3.9766, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.382093578002087e-05, + "loss": 3.9778, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.381256621131408e-05, + "loss": 3.9794, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.380418026380356e-05, + "loss": 3.98, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379579431629304e-05, + "loss": 3.9733, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.378740836878252e-05, + "loss": 3.9829, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.377903880007574e-05, + "loss": 3.976, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.377065285256522e-05, + "loss": 3.9861, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.37622669050547e-05, + "loss": 3.9779, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 4.030065059661865, + "eval_runtime": 295.1251, + "eval_samples_per_second": 1292.981, + "eval_steps_per_second": 40.407, + "step": 992160 + }, + { + "epoch": 0.0, + "learning_rate": 3.375389733634791e-05, + "loss": 3.9909, + "step": 992256 + }, + { + "epoch": 0.0, + "learning_rate": 3.374551138883739e-05, + "loss": 3.9715, + "step": 992768 + }, + { + "epoch": 0.0, + "learning_rate": 3.373712544132687e-05, + "loss": 3.9767, + "step": 993280 + }, + { + "epoch": 0.0, + "learning_rate": 3.372873949381635e-05, + "loss": 3.9853, + "step": 993792 + }, + { + "epoch": 0.0, + "learning_rate": 3.372035354630583e-05, + "loss": 3.9813, + "step": 994304 + }, + { + "epoch": 0.0, + "learning_rate": 3.371196759879531e-05, + "loss": 3.9806, + "step": 994816 + }, + { + "epoch": 0.0, + "learning_rate": 3.370358165128479e-05, + "loss": 3.9802, + "step": 995328 + }, + { + "epoch": 0.0, + "learning_rate": 3.369519570377427e-05, + "loss": 3.9772, + "step": 995840 + }, + { + "epoch": 0.0, + "learning_rate": 3.368680975626375e-05, + "loss": 3.9744, + "step": 996352 + }, + { + "epoch": 0.0, + "learning_rate": 3.367842380875323e-05, + "loss": 3.9862, + "step": 996864 + }, + { + "epoch": 0.0, + "learning_rate": 3.367003786124271e-05, + "loss": 3.9783, + "step": 997376 + }, + { + "epoch": 0.0, + "learning_rate": 3.3661651913732187e-05, + "loss": 3.9815, + "step": 997888 + }, + { + "epoch": 0.0, + "learning_rate": 3.36532823450254e-05, + "loss": 3.9916, + "step": 998400 + }, + { + "epoch": 0.0, + "learning_rate": 3.364489639751488e-05, + "loss": 3.9645, + "step": 998912 + }, + { + "epoch": 0.0, + "learning_rate": 3.363651045000436e-05, + "loss": 3.9746, + "step": 999424 + }, + { + "epoch": 0.0, + "learning_rate": 3.362812450249384e-05, + "loss": 3.9627, + "step": 999936 + }, + { + "epoch": 0.0, + "learning_rate": 3.3619738554983316e-05, + "loss": 3.9879, + "step": 1000448 + }, + { + "epoch": 0.0, + "learning_rate": 3.3611352607472795e-05, + "loss": 3.9743, + "step": 1000960 + }, + { + "epoch": 0.0, + "learning_rate": 3.3602966659962275e-05, + "loss": 3.9735, + "step": 1001472 + }, + { + "epoch": 0.0, + "learning_rate": 3.3594580712451755e-05, + "loss": 3.9763, + "step": 1001984 + }, + { + "epoch": 0.0, + "learning_rate": 3.3586194764941235e-05, + "loss": 3.9914, + "step": 1002496 + }, + { + "epoch": 0.0, + "learning_rate": 3.3577808817430715e-05, + "loss": 3.9813, + "step": 1003008 + }, + { + "epoch": 0.0, + "learning_rate": 3.3569422869920195e-05, + "loss": 3.9866, + "step": 1003520 + }, + { + "epoch": 0.0, + "learning_rate": 3.3561036922409675e-05, + "loss": 3.978, + "step": 1004032 + }, + { + "epoch": 0.0, + "learning_rate": 3.355266735370289e-05, + "loss": 3.984, + "step": 1004544 + }, + { + "epoch": 0.0, + "learning_rate": 3.354428140619237e-05, + "loss": 3.974, + "step": 1005056 + }, + { + "epoch": 0.0, + "learning_rate": 3.353589545868185e-05, + "loss": 3.9721, + "step": 1005568 + }, + { + "epoch": 0.0, + "learning_rate": 3.352750951117133e-05, + "loss": 3.9729, + "step": 1006080 + }, + { + "epoch": 0.0, + "learning_rate": 3.351912356366081e-05, + "loss": 3.9757, + "step": 1006592 + }, + { + "epoch": 0.0, + "learning_rate": 3.351075399495402e-05, + "loss": 3.9693, + "step": 1007104 + }, + { + "epoch": 0.01, + "learning_rate": 3.350238442624723e-05, + "loss": 3.9751, + "step": 1007616 + }, + { + "epoch": 0.01, + "learning_rate": 3.349399847873671e-05, + "loss": 3.9769, + "step": 1008128 + }, + { + "epoch": 0.01, + "learning_rate": 3.348561253122619e-05, + "loss": 3.9841, + "step": 1008640 + }, + { + "epoch": 0.01, + "learning_rate": 3.347722658371567e-05, + "loss": 3.9833, + "step": 1009152 + }, + { + "epoch": 0.01, + "learning_rate": 3.346884063620515e-05, + "loss": 3.9706, + "step": 1009664 + }, + { + "epoch": 0.01, + "learning_rate": 3.346047106749836e-05, + "loss": 3.9712, + "step": 1010176 + }, + { + "epoch": 0.01, + "learning_rate": 3.3452085119987845e-05, + "loss": 3.9901, + "step": 1010688 + }, + { + "epoch": 0.01, + "learning_rate": 3.3443699172477325e-05, + "loss": 3.9603, + "step": 1011200 + }, + { + "epoch": 0.01, + "learning_rate": 3.3435313224966805e-05, + "loss": 3.9797, + "step": 1011712 + }, + { + "epoch": 0.01, + "learning_rate": 3.3426927277456285e-05, + "loss": 3.9711, + "step": 1012224 + }, + { + "epoch": 0.01, + "learning_rate": 3.3418557708749494e-05, + "loss": 3.9628, + "step": 1012736 + }, + { + "epoch": 0.01, + "learning_rate": 3.3410171761238974e-05, + "loss": 3.9772, + "step": 1013248 + }, + { + "epoch": 0.01, + "learning_rate": 3.3401785813728454e-05, + "loss": 3.9827, + "step": 1013760 + }, + { + "epoch": 0.01, + "learning_rate": 3.3393399866217934e-05, + "loss": 3.9716, + "step": 1014272 + }, + { + "epoch": 0.01, + "learning_rate": 3.3385013918707414e-05, + "loss": 3.976, + "step": 1014784 + }, + { + "epoch": 0.01, + "learning_rate": 3.3376627971196893e-05, + "loss": 3.9726, + "step": 1015296 + }, + { + "epoch": 0.01, + "learning_rate": 3.3368242023686373e-05, + "loss": 3.9722, + "step": 1015808 + }, + { + "epoch": 0.01, + "learning_rate": 3.3359856076175853e-05, + "loss": 3.9826, + "step": 1016320 + }, + { + "epoch": 0.01, + "learning_rate": 3.3351470128665327e-05, + "loss": 3.9545, + "step": 1016832 + }, + { + "epoch": 0.01, + "learning_rate": 3.334310055995854e-05, + "loss": 3.9718, + "step": 1017344 + }, + { + "epoch": 0.01, + "learning_rate": 3.333471461244803e-05, + "loss": 3.973, + "step": 1017856 + }, + { + "epoch": 0.01, + "learning_rate": 3.332634504374124e-05, + "loss": 3.9844, + "step": 1018368 + }, + { + "epoch": 0.01, + "learning_rate": 3.331797547503445e-05, + "loss": 3.9656, + "step": 1018880 + }, + { + "epoch": 0.01, + "learning_rate": 3.330958952752393e-05, + "loss": 3.9722, + "step": 1019392 + }, + { + "epoch": 0.01, + "learning_rate": 3.330120358001341e-05, + "loss": 3.9568, + "step": 1019904 + }, + { + "epoch": 0.01, + "learning_rate": 3.329281763250289e-05, + "loss": 3.9665, + "step": 1020416 + }, + { + "epoch": 0.01, + "learning_rate": 3.328443168499237e-05, + "loss": 3.9802, + "step": 1020928 + }, + { + "epoch": 0.01, + "learning_rate": 3.327604573748185e-05, + "loss": 3.9521, + "step": 1021440 + }, + { + "epoch": 0.01, + "learning_rate": 3.326765978997133e-05, + "loss": 3.983, + "step": 1021952 + }, + { + "epoch": 0.01, + "learning_rate": 3.32592738424608e-05, + "loss": 3.9732, + "step": 1022464 + }, + { + "epoch": 0.01, + "learning_rate": 3.3250904273754016e-05, + "loss": 3.9625, + "step": 1022976 + }, + { + "epoch": 0.01, + "learning_rate": 3.3242518326243496e-05, + "loss": 3.9831, + "step": 1023488 + }, + { + "epoch": 0.01, + "learning_rate": 3.3234132378732976e-05, + "loss": 3.9587, + "step": 1024000 + }, + { + "epoch": 0.01, + "learning_rate": 3.3225746431222456e-05, + "loss": 3.9587, + "step": 1024512 + }, + { + "epoch": 0.01, + "learning_rate": 3.3217360483711936e-05, + "loss": 3.9687, + "step": 1025024 + }, + { + "epoch": 0.01, + "learning_rate": 3.3208974536201416e-05, + "loss": 3.9809, + "step": 1025536 + }, + { + "epoch": 0.01, + "learning_rate": 3.3200588588690896e-05, + "loss": 3.9625, + "step": 1026048 + }, + { + "epoch": 0.01, + "learning_rate": 3.3192202641180376e-05, + "loss": 3.9714, + "step": 1026560 + }, + { + "epoch": 0.01, + "learning_rate": 3.3183833072473585e-05, + "loss": 3.9519, + "step": 1027072 + }, + { + "epoch": 0.01, + "learning_rate": 3.31754635037668e-05, + "loss": 3.9681, + "step": 1027584 + }, + { + "epoch": 0.01, + "learning_rate": 3.3167077556256274e-05, + "loss": 3.976, + "step": 1028096 + }, + { + "epoch": 0.01, + "learning_rate": 3.3158691608745754e-05, + "loss": 3.9804, + "step": 1028608 + }, + { + "epoch": 0.01, + "learning_rate": 3.3150305661235234e-05, + "loss": 3.9696, + "step": 1029120 + }, + { + "epoch": 0.01, + "learning_rate": 3.314191971372472e-05, + "loss": 3.9773, + "step": 1029632 + }, + { + "epoch": 0.01, + "learning_rate": 3.31335337662142e-05, + "loss": 3.9869, + "step": 1030144 + }, + { + "epoch": 0.01, + "learning_rate": 3.312514781870368e-05, + "loss": 3.9722, + "step": 1030656 + }, + { + "epoch": 0.01, + "learning_rate": 3.311676187119316e-05, + "loss": 3.9714, + "step": 1031168 + }, + { + "epoch": 0.01, + "learning_rate": 3.310839230248637e-05, + "loss": 3.9683, + "step": 1031680 + }, + { + "epoch": 0.01, + "learning_rate": 3.310002273377958e-05, + "loss": 3.9723, + "step": 1032192 + }, + { + "epoch": 0.01, + "learning_rate": 3.309163678626906e-05, + "loss": 3.9644, + "step": 1032704 + }, + { + "epoch": 0.01, + "learning_rate": 3.308325083875854e-05, + "loss": 3.9764, + "step": 1033216 + }, + { + "epoch": 0.01, + "learning_rate": 3.307486489124802e-05, + "loss": 3.9714, + "step": 1033728 + }, + { + "epoch": 0.01, + "learning_rate": 3.30664789437375e-05, + "loss": 3.9842, + "step": 1034240 + }, + { + "epoch": 0.01, + "learning_rate": 3.305809299622698e-05, + "loss": 3.9696, + "step": 1034752 + }, + { + "epoch": 0.01, + "learning_rate": 3.304972342752019e-05, + "loss": 3.9611, + "step": 1035264 + }, + { + "epoch": 0.01, + "learning_rate": 3.304133748000967e-05, + "loss": 3.9639, + "step": 1035776 + }, + { + "epoch": 0.01, + "learning_rate": 3.3032951532499154e-05, + "loss": 3.9757, + "step": 1036288 + }, + { + "epoch": 0.01, + "learning_rate": 3.302458196379236e-05, + "loss": 3.9625, + "step": 1036800 + }, + { + "epoch": 0.01, + "learning_rate": 3.301619601628184e-05, + "loss": 3.9762, + "step": 1037312 + }, + { + "epoch": 0.01, + "learning_rate": 3.300781006877132e-05, + "loss": 3.9671, + "step": 1037824 + }, + { + "epoch": 0.02, + "learning_rate": 3.29994241212608e-05, + "loss": 3.9647, + "step": 1038336 + }, + { + "epoch": 0.02, + "learning_rate": 3.299103817375028e-05, + "loss": 3.9666, + "step": 1038848 + }, + { + "epoch": 0.02, + "learning_rate": 3.298265222623976e-05, + "loss": 3.9656, + "step": 1039360 + }, + { + "epoch": 0.02, + "learning_rate": 3.297426627872924e-05, + "loss": 3.9727, + "step": 1039872 + }, + { + "epoch": 0.02, + "learning_rate": 3.296588033121872e-05, + "loss": 3.9802, + "step": 1040384 + }, + { + "epoch": 0.02, + "learning_rate": 3.29574943837082e-05, + "loss": 3.9761, + "step": 1040896 + }, + { + "epoch": 0.02, + "learning_rate": 3.294910843619768e-05, + "loss": 3.9606, + "step": 1041408 + }, + { + "epoch": 0.02, + "learning_rate": 3.294073886749089e-05, + "loss": 3.9701, + "step": 1041920 + }, + { + "epoch": 0.02, + "learning_rate": 3.293235291998037e-05, + "loss": 3.9645, + "step": 1042432 + }, + { + "epoch": 0.02, + "learning_rate": 3.292396697246985e-05, + "loss": 3.9737, + "step": 1042944 + }, + { + "epoch": 0.02, + "learning_rate": 3.291558102495934e-05, + "loss": 3.9752, + "step": 1043456 + }, + { + "epoch": 0.02, + "learning_rate": 3.290719507744881e-05, + "loss": 3.9597, + "step": 1043968 + }, + { + "epoch": 0.02, + "learning_rate": 3.289880912993829e-05, + "loss": 3.9749, + "step": 1044480 + }, + { + "epoch": 0.02, + "learning_rate": 3.289042318242777e-05, + "loss": 3.9687, + "step": 1044992 + }, + { + "epoch": 0.02, + "learning_rate": 3.288203723491725e-05, + "loss": 3.9661, + "step": 1045504 + }, + { + "epoch": 0.02, + "learning_rate": 3.287365128740673e-05, + "loss": 3.9651, + "step": 1046016 + }, + { + "epoch": 0.02, + "learning_rate": 3.286528171869994e-05, + "loss": 3.9624, + "step": 1046528 + }, + { + "epoch": 0.02, + "learning_rate": 3.285689577118942e-05, + "loss": 3.9661, + "step": 1047040 + }, + { + "epoch": 0.02, + "learning_rate": 3.28485098236789e-05, + "loss": 3.9695, + "step": 1047552 + }, + { + "epoch": 0.02, + "learning_rate": 3.284012387616838e-05, + "loss": 3.9644, + "step": 1048064 + }, + { + "epoch": 0.02, + "learning_rate": 3.283175430746159e-05, + "loss": 3.9567, + "step": 1048576 + }, + { + "epoch": 0.02, + "learning_rate": 3.2823368359951076e-05, + "loss": 3.9639, + "step": 1049088 + }, + { + "epoch": 0.02, + "learning_rate": 3.2814982412440556e-05, + "loss": 3.9761, + "step": 1049600 + }, + { + "epoch": 0.02, + "learning_rate": 3.2806596464930036e-05, + "loss": 3.963, + "step": 1050112 + }, + { + "epoch": 0.02, + "learning_rate": 3.2798226896223246e-05, + "loss": 3.9684, + "step": 1050624 + }, + { + "epoch": 0.02, + "learning_rate": 3.2789840948712725e-05, + "loss": 3.9699, + "step": 1051136 + }, + { + "epoch": 0.02, + "learning_rate": 3.2781455001202205e-05, + "loss": 3.9748, + "step": 1051648 + }, + { + "epoch": 0.02, + "learning_rate": 3.2773069053691685e-05, + "loss": 3.9703, + "step": 1052160 + }, + { + "epoch": 0.02, + "learning_rate": 3.2764683106181165e-05, + "loss": 3.9684, + "step": 1052672 + }, + { + "epoch": 0.02, + "learning_rate": 3.2756297158670645e-05, + "loss": 3.9744, + "step": 1053184 + }, + { + "epoch": 0.02, + "learning_rate": 3.2747911211160125e-05, + "loss": 3.9735, + "step": 1053696 + }, + { + "epoch": 0.02, + "learning_rate": 3.2739525263649605e-05, + "loss": 3.9608, + "step": 1054208 + }, + { + "epoch": 0.02, + "learning_rate": 3.2731155694942814e-05, + "loss": 3.9652, + "step": 1054720 + }, + { + "epoch": 0.02, + "learning_rate": 3.2722769747432294e-05, + "loss": 3.9571, + "step": 1055232 + }, + { + "epoch": 0.02, + "learning_rate": 3.2714383799921774e-05, + "loss": 3.9697, + "step": 1055744 + }, + { + "epoch": 0.02, + "learning_rate": 3.270599785241126e-05, + "loss": 3.965, + "step": 1056256 + }, + { + "epoch": 0.02, + "learning_rate": 3.269762828370447e-05, + "loss": 3.9592, + "step": 1056768 + }, + { + "epoch": 0.02, + "learning_rate": 3.268925871499768e-05, + "loss": 3.9568, + "step": 1057280 + }, + { + "epoch": 0.02, + "learning_rate": 3.268087276748716e-05, + "loss": 3.9627, + "step": 1057792 + }, + { + "epoch": 0.02, + "learning_rate": 3.267248681997664e-05, + "loss": 3.976, + "step": 1058304 + }, + { + "epoch": 0.02, + "learning_rate": 3.266410087246612e-05, + "loss": 3.9708, + "step": 1058816 + }, + { + "epoch": 0.02, + "learning_rate": 3.26557149249556e-05, + "loss": 3.9702, + "step": 1059328 + }, + { + "epoch": 0.02, + "learning_rate": 3.264732897744508e-05, + "loss": 3.9606, + "step": 1059840 + }, + { + "epoch": 0.02, + "learning_rate": 3.263894302993456e-05, + "loss": 3.9749, + "step": 1060352 + }, + { + "epoch": 0.02, + "learning_rate": 3.263055708242404e-05, + "loss": 3.974, + "step": 1060864 + }, + { + "epoch": 0.02, + "learning_rate": 3.262218751371725e-05, + "loss": 3.9711, + "step": 1061376 + }, + { + "epoch": 0.02, + "learning_rate": 3.261380156620673e-05, + "loss": 3.964, + "step": 1061888 + }, + { + "epoch": 0.02, + "learning_rate": 3.260541561869621e-05, + "loss": 3.9686, + "step": 1062400 + }, + { + "epoch": 0.02, + "learning_rate": 3.2597029671185695e-05, + "loss": 3.9728, + "step": 1062912 + }, + { + "epoch": 0.02, + "learning_rate": 3.2588643723675175e-05, + "loss": 3.9762, + "step": 1063424 + }, + { + "epoch": 0.02, + "learning_rate": 3.2580274154968384e-05, + "loss": 3.9621, + "step": 1063936 + }, + { + "epoch": 0.02, + "learning_rate": 3.2571888207457864e-05, + "loss": 3.9597, + "step": 1064448 + }, + { + "epoch": 0.02, + "learning_rate": 3.2563502259947344e-05, + "loss": 3.9715, + "step": 1064960 + }, + { + "epoch": 0.02, + "learning_rate": 3.2555116312436823e-05, + "loss": 3.9656, + "step": 1065472 + }, + { + "epoch": 0.02, + "learning_rate": 3.254674674373003e-05, + "loss": 3.9582, + "step": 1065984 + }, + { + "epoch": 0.02, + "learning_rate": 3.253836079621951e-05, + "loss": 3.9729, + "step": 1066496 + }, + { + "epoch": 0.02, + "learning_rate": 3.252997484870899e-05, + "loss": 3.9615, + "step": 1067008 + }, + { + "epoch": 0.02, + "learning_rate": 3.2521588901198466e-05, + "loss": 3.9774, + "step": 1067520 + }, + { + "epoch": 0.02, + "learning_rate": 3.251321933249168e-05, + "loss": 3.9569, + "step": 1068032 + }, + { + "epoch": 0.03, + "eval_loss": 4.0224127769470215, + "eval_runtime": 299.2038, + "eval_samples_per_second": 1275.355, + "eval_steps_per_second": 39.856, + "step": 1068480 + }, + { + "epoch": 1.0, + "learning_rate": 3.250483338498116e-05, + "loss": 3.9689, + "step": 1068544 + }, + { + "epoch": 1.0, + "learning_rate": 3.249644743747065e-05, + "loss": 3.9594, + "step": 1069056 + }, + { + "epoch": 1.0, + "learning_rate": 3.248806148996012e-05, + "loss": 3.9661, + "step": 1069568 + }, + { + "epoch": 1.0, + "learning_rate": 3.247969192125334e-05, + "loss": 3.9703, + "step": 1070080 + }, + { + "epoch": 1.0, + "learning_rate": 3.247130597374282e-05, + "loss": 3.9677, + "step": 1070592 + }, + { + "epoch": 1.0, + "learning_rate": 3.24629200262323e-05, + "loss": 3.9672, + "step": 1071104 + }, + { + "epoch": 1.0, + "learning_rate": 3.245453407872177e-05, + "loss": 3.9632, + "step": 1071616 + }, + { + "epoch": 1.0, + "learning_rate": 3.2446164510014986e-05, + "loss": 3.9655, + "step": 1072128 + }, + { + "epoch": 1.0, + "learning_rate": 3.2437778562504466e-05, + "loss": 3.9624, + "step": 1072640 + }, + { + "epoch": 1.0, + "learning_rate": 3.242939261499394e-05, + "loss": 3.9688, + "step": 1073152 + }, + { + "epoch": 1.0, + "learning_rate": 3.242100666748342e-05, + "loss": 3.9698, + "step": 1073664 + }, + { + "epoch": 1.0, + "learning_rate": 3.2412637098776635e-05, + "loss": 3.9702, + "step": 1074176 + }, + { + "epoch": 1.0, + "learning_rate": 3.240426753006985e-05, + "loss": 3.9765, + "step": 1074688 + }, + { + "epoch": 1.0, + "learning_rate": 3.239588158255933e-05, + "loss": 3.9527, + "step": 1075200 + }, + { + "epoch": 1.0, + "learning_rate": 3.238749563504881e-05, + "loss": 3.9594, + "step": 1075712 + }, + { + "epoch": 1.0, + "learning_rate": 3.237910968753829e-05, + "loss": 3.9489, + "step": 1076224 + }, + { + "epoch": 1.0, + "learning_rate": 3.237072374002777e-05, + "loss": 3.9751, + "step": 1076736 + }, + { + "epoch": 1.0, + "learning_rate": 3.2362337792517244e-05, + "loss": 3.9603, + "step": 1077248 + }, + { + "epoch": 1.0, + "learning_rate": 3.2353951845006724e-05, + "loss": 3.9594, + "step": 1077760 + }, + { + "epoch": 1.0, + "learning_rate": 3.2345565897496204e-05, + "loss": 3.967, + "step": 1078272 + }, + { + "epoch": 1.0, + "learning_rate": 3.2337179949985684e-05, + "loss": 3.9742, + "step": 1078784 + }, + { + "epoch": 1.0, + "learning_rate": 3.2328794002475164e-05, + "loss": 3.9686, + "step": 1079296 + }, + { + "epoch": 1.0, + "learning_rate": 3.2320408054964644e-05, + "loss": 3.9682, + "step": 1079808 + }, + { + "epoch": 1.0, + "learning_rate": 3.2312022107454124e-05, + "loss": 3.967, + "step": 1080320 + }, + { + "epoch": 1.0, + "learning_rate": 3.2303636159943604e-05, + "loss": 3.9714, + "step": 1080832 + }, + { + "epoch": 1.0, + "learning_rate": 3.2295250212433084e-05, + "loss": 3.9586, + "step": 1081344 + }, + { + "epoch": 1.0, + "learning_rate": 3.22868806437263e-05, + "loss": 3.9591, + "step": 1081856 + }, + { + "epoch": 1.0, + "learning_rate": 3.227849469621578e-05, + "loss": 3.9632, + "step": 1082368 + }, + { + "epoch": 1.0, + "learning_rate": 3.227010874870526e-05, + "loss": 3.9598, + "step": 1082880 + }, + { + "epoch": 1.0, + "learning_rate": 3.226172280119474e-05, + "loss": 3.9547, + "step": 1083392 + }, + { + "epoch": 1.01, + "learning_rate": 3.225333685368422e-05, + "loss": 3.9623, + "step": 1083904 + }, + { + "epoch": 1.01, + "learning_rate": 3.224496728497743e-05, + "loss": 3.9593, + "step": 1084416 + }, + { + "epoch": 1.01, + "learning_rate": 3.223658133746691e-05, + "loss": 3.9734, + "step": 1084928 + }, + { + "epoch": 1.01, + "learning_rate": 3.222819538995639e-05, + "loss": 3.9699, + "step": 1085440 + }, + { + "epoch": 1.01, + "learning_rate": 3.221980944244587e-05, + "loss": 3.9559, + "step": 1085952 + }, + { + "epoch": 1.01, + "learning_rate": 3.221143987373908e-05, + "loss": 3.9623, + "step": 1086464 + }, + { + "epoch": 1.01, + "learning_rate": 3.220305392622856e-05, + "loss": 3.9732, + "step": 1086976 + }, + { + "epoch": 1.01, + "learning_rate": 3.219466797871804e-05, + "loss": 3.9479, + "step": 1087488 + }, + { + "epoch": 1.01, + "learning_rate": 3.2186282031207524e-05, + "loss": 3.9683, + "step": 1088000 + }, + { + "epoch": 1.01, + "learning_rate": 3.2177896083697004e-05, + "loss": 3.9506, + "step": 1088512 + }, + { + "epoch": 1.01, + "learning_rate": 3.2169510136186484e-05, + "loss": 3.9516, + "step": 1089024 + }, + { + "epoch": 1.01, + "learning_rate": 3.216112418867596e-05, + "loss": 3.9624, + "step": 1089536 + }, + { + "epoch": 1.01, + "learning_rate": 3.215273824116544e-05, + "loss": 3.9753, + "step": 1090048 + }, + { + "epoch": 1.01, + "learning_rate": 3.214435229365492e-05, + "loss": 3.9525, + "step": 1090560 + }, + { + "epoch": 1.01, + "learning_rate": 3.21359663461444e-05, + "loss": 3.9608, + "step": 1091072 + }, + { + "epoch": 1.01, + "learning_rate": 3.2127596777437606e-05, + "loss": 3.962, + "step": 1091584 + }, + { + "epoch": 1.01, + "learning_rate": 3.2119210829927086e-05, + "loss": 3.9594, + "step": 1092096 + }, + { + "epoch": 1.01, + "learning_rate": 3.2110824882416566e-05, + "loss": 3.9645, + "step": 1092608 + }, + { + "epoch": 1.01, + "learning_rate": 3.2102438934906046e-05, + "loss": 3.9446, + "step": 1093120 + }, + { + "epoch": 1.01, + "learning_rate": 3.2094052987395526e-05, + "loss": 3.9631, + "step": 1093632 + }, + { + "epoch": 1.01, + "learning_rate": 3.2085667039885006e-05, + "loss": 3.9636, + "step": 1094144 + }, + { + "epoch": 1.01, + "learning_rate": 3.207729747117822e-05, + "loss": 3.9699, + "step": 1094656 + }, + { + "epoch": 1.01, + "learning_rate": 3.20689115236677e-05, + "loss": 3.9509, + "step": 1095168 + }, + { + "epoch": 1.01, + "learning_rate": 3.206052557615718e-05, + "loss": 3.9535, + "step": 1095680 + }, + { + "epoch": 1.01, + "learning_rate": 3.205213962864666e-05, + "loss": 3.9526, + "step": 1096192 + }, + { + "epoch": 1.01, + "learning_rate": 3.204377005993987e-05, + "loss": 3.9466, + "step": 1096704 + }, + { + "epoch": 1.01, + "learning_rate": 3.203538411242935e-05, + "loss": 3.9696, + "step": 1097216 + }, + { + "epoch": 1.01, + "learning_rate": 3.202699816491883e-05, + "loss": 3.9374, + "step": 1097728 + }, + { + "epoch": 1.01, + "learning_rate": 3.201861221740831e-05, + "loss": 3.9656, + "step": 1098240 + }, + { + "epoch": 1.01, + "learning_rate": 3.201022626989779e-05, + "loss": 3.9608, + "step": 1098752 + }, + { + "epoch": 1.01, + "learning_rate": 3.200184032238727e-05, + "loss": 3.9542, + "step": 1099264 + }, + { + "epoch": 1.01, + "learning_rate": 3.199345437487675e-05, + "loss": 3.9706, + "step": 1099776 + }, + { + "epoch": 1.01, + "learning_rate": 3.198506842736623e-05, + "loss": 3.9471, + "step": 1100288 + }, + { + "epoch": 1.01, + "learning_rate": 3.197669885865944e-05, + "loss": 3.9465, + "step": 1100800 + }, + { + "epoch": 1.01, + "learning_rate": 3.1968312911148926e-05, + "loss": 3.9487, + "step": 1101312 + }, + { + "epoch": 1.01, + "learning_rate": 3.1959926963638406e-05, + "loss": 3.972, + "step": 1101824 + }, + { + "epoch": 1.01, + "learning_rate": 3.1951541016127886e-05, + "loss": 3.9505, + "step": 1102336 + }, + { + "epoch": 1.01, + "learning_rate": 3.1943155068617366e-05, + "loss": 3.9505, + "step": 1102848 + }, + { + "epoch": 1.01, + "learning_rate": 3.1934801878714304e-05, + "loss": 3.9431, + "step": 1103360 + }, + { + "epoch": 1.01, + "learning_rate": 3.1926415931203784e-05, + "loss": 3.9513, + "step": 1103872 + }, + { + "epoch": 1.01, + "learning_rate": 3.1918029983693264e-05, + "loss": 3.9642, + "step": 1104384 + }, + { + "epoch": 1.01, + "learning_rate": 3.1909644036182744e-05, + "loss": 3.9676, + "step": 1104896 + }, + { + "epoch": 1.01, + "learning_rate": 3.1901258088672224e-05, + "loss": 3.9541, + "step": 1105408 + }, + { + "epoch": 1.01, + "learning_rate": 3.1892872141161704e-05, + "loss": 3.967, + "step": 1105920 + }, + { + "epoch": 1.01, + "learning_rate": 3.1884486193651184e-05, + "loss": 3.9737, + "step": 1106432 + }, + { + "epoch": 1.01, + "learning_rate": 3.1876100246140664e-05, + "loss": 3.959, + "step": 1106944 + }, + { + "epoch": 1.01, + "learning_rate": 3.186773067743388e-05, + "loss": 3.9603, + "step": 1107456 + }, + { + "epoch": 1.01, + "learning_rate": 3.185934472992336e-05, + "loss": 3.955, + "step": 1107968 + }, + { + "epoch": 1.01, + "learning_rate": 3.185095878241284e-05, + "loss": 3.961, + "step": 1108480 + }, + { + "epoch": 1.01, + "learning_rate": 3.184257283490232e-05, + "loss": 3.9522, + "step": 1108992 + }, + { + "epoch": 1.01, + "learning_rate": 3.183420326619553e-05, + "loss": 3.9601, + "step": 1109504 + }, + { + "epoch": 1.01, + "learning_rate": 3.182581731868501e-05, + "loss": 3.962, + "step": 1110016 + }, + { + "epoch": 1.01, + "learning_rate": 3.181743137117449e-05, + "loss": 3.9693, + "step": 1110528 + }, + { + "epoch": 1.01, + "learning_rate": 3.180904542366396e-05, + "loss": 3.9598, + "step": 1111040 + }, + { + "epoch": 1.01, + "learning_rate": 3.180067585495718e-05, + "loss": 3.9454, + "step": 1111552 + }, + { + "epoch": 1.01, + "learning_rate": 3.179228990744666e-05, + "loss": 3.9499, + "step": 1112064 + }, + { + "epoch": 1.01, + "learning_rate": 3.178390395993614e-05, + "loss": 3.9625, + "step": 1112576 + }, + { + "epoch": 1.01, + "learning_rate": 3.177551801242562e-05, + "loss": 3.95, + "step": 1113088 + }, + { + "epoch": 1.01, + "learning_rate": 3.1767148443718834e-05, + "loss": 3.9619, + "step": 1113600 + }, + { + "epoch": 1.01, + "learning_rate": 3.1758762496208314e-05, + "loss": 3.9565, + "step": 1114112 + }, + { + "epoch": 1.02, + "learning_rate": 3.1750376548697794e-05, + "loss": 3.9532, + "step": 1114624 + }, + { + "epoch": 1.02, + "learning_rate": 3.174199060118727e-05, + "loss": 3.9501, + "step": 1115136 + }, + { + "epoch": 1.02, + "learning_rate": 3.173360465367675e-05, + "loss": 3.9561, + "step": 1115648 + }, + { + "epoch": 1.02, + "learning_rate": 3.172521870616623e-05, + "loss": 3.9626, + "step": 1116160 + }, + { + "epoch": 1.02, + "learning_rate": 3.1716832758655707e-05, + "loss": 3.9666, + "step": 1116672 + }, + { + "epoch": 1.02, + "learning_rate": 3.1708446811145187e-05, + "loss": 3.9606, + "step": 1117184 + }, + { + "epoch": 1.02, + "learning_rate": 3.1700077242438396e-05, + "loss": 3.9488, + "step": 1117696 + }, + { + "epoch": 1.02, + "learning_rate": 3.1691691294927876e-05, + "loss": 3.9564, + "step": 1118208 + }, + { + "epoch": 1.02, + "learning_rate": 3.1683305347417356e-05, + "loss": 3.9571, + "step": 1118720 + }, + { + "epoch": 1.02, + "learning_rate": 3.1674919399906836e-05, + "loss": 3.9565, + "step": 1119232 + }, + { + "epoch": 1.02, + "learning_rate": 3.166654983120005e-05, + "loss": 3.963, + "step": 1119744 + }, + { + "epoch": 1.02, + "learning_rate": 3.165816388368953e-05, + "loss": 3.9472, + "step": 1120256 + }, + { + "epoch": 1.02, + "learning_rate": 3.164977793617901e-05, + "loss": 3.9613, + "step": 1120768 + }, + { + "epoch": 1.02, + "learning_rate": 3.164139198866849e-05, + "loss": 3.956, + "step": 1121280 + }, + { + "epoch": 1.02, + "learning_rate": 3.163300604115797e-05, + "loss": 3.9524, + "step": 1121792 + }, + { + "epoch": 1.02, + "learning_rate": 3.162462009364745e-05, + "loss": 3.9502, + "step": 1122304 + }, + { + "epoch": 1.02, + "learning_rate": 3.161625052494066e-05, + "loss": 3.9505, + "step": 1122816 + }, + { + "epoch": 1.02, + "learning_rate": 3.160786457743014e-05, + "loss": 3.955, + "step": 1123328 + }, + { + "epoch": 1.02, + "learning_rate": 3.159947862991962e-05, + "loss": 3.9568, + "step": 1123840 + }, + { + "epoch": 1.02, + "learning_rate": 3.15910926824091e-05, + "loss": 3.9518, + "step": 1124352 + }, + { + "epoch": 1.02, + "learning_rate": 3.158270673489858e-05, + "loss": 3.9435, + "step": 1124864 + }, + { + "epoch": 1.02, + "learning_rate": 3.157433716619179e-05, + "loss": 3.948, + "step": 1125376 + }, + { + "epoch": 1.02, + "learning_rate": 3.156595121868127e-05, + "loss": 3.9658, + "step": 1125888 + }, + { + "epoch": 1.02, + "learning_rate": 3.1557565271170756e-05, + "loss": 3.9527, + "step": 1126400 + }, + { + "epoch": 1.02, + "learning_rate": 3.1549179323660236e-05, + "loss": 3.9523, + "step": 1126912 + }, + { + "epoch": 1.02, + "learning_rate": 3.1540793376149716e-05, + "loss": 3.9617, + "step": 1127424 + }, + { + "epoch": 1.02, + "learning_rate": 3.1532407428639196e-05, + "loss": 3.962, + "step": 1127936 + }, + { + "epoch": 1.02, + "learning_rate": 3.1524037859932405e-05, + "loss": 3.955, + "step": 1128448 + }, + { + "epoch": 1.02, + "learning_rate": 3.1515651912421885e-05, + "loss": 3.9577, + "step": 1128960 + }, + { + "epoch": 1.02, + "learning_rate": 3.1507265964911365e-05, + "loss": 3.9631, + "step": 1129472 + }, + { + "epoch": 1.02, + "learning_rate": 3.1498880017400845e-05, + "loss": 3.9608, + "step": 1129984 + }, + { + "epoch": 1.02, + "learning_rate": 3.1490494069890325e-05, + "loss": 3.9463, + "step": 1130496 + }, + { + "epoch": 1.02, + "learning_rate": 3.14821081223798e-05, + "loss": 3.9541, + "step": 1131008 + }, + { + "epoch": 1.02, + "learning_rate": 3.147372217486928e-05, + "loss": 3.9507, + "step": 1131520 + }, + { + "epoch": 1.02, + "learning_rate": 3.146533622735876e-05, + "loss": 3.9523, + "step": 1132032 + }, + { + "epoch": 1.02, + "learning_rate": 3.1456966658651974e-05, + "loss": 3.9512, + "step": 1132544 + }, + { + "epoch": 1.02, + "learning_rate": 3.1448580711141454e-05, + "loss": 3.9475, + "step": 1133056 + }, + { + "epoch": 1.02, + "learning_rate": 3.144021114243467e-05, + "loss": 3.9488, + "step": 1133568 + }, + { + "epoch": 1.02, + "learning_rate": 3.143182519492415e-05, + "loss": 3.9538, + "step": 1134080 + }, + { + "epoch": 1.02, + "learning_rate": 3.142343924741362e-05, + "loss": 3.9541, + "step": 1134592 + }, + { + "epoch": 1.02, + "learning_rate": 3.14150532999031e-05, + "loss": 3.9639, + "step": 1135104 + }, + { + "epoch": 1.02, + "learning_rate": 3.140666735239258e-05, + "loss": 3.9616, + "step": 1135616 + }, + { + "epoch": 1.02, + "learning_rate": 3.139828140488206e-05, + "loss": 3.9464, + "step": 1136128 + }, + { + "epoch": 1.02, + "learning_rate": 3.138991183617527e-05, + "loss": 3.962, + "step": 1136640 + }, + { + "epoch": 1.02, + "learning_rate": 3.138152588866475e-05, + "loss": 3.9607, + "step": 1137152 + }, + { + "epoch": 1.02, + "learning_rate": 3.137313994115423e-05, + "loss": 3.9616, + "step": 1137664 + }, + { + "epoch": 1.02, + "learning_rate": 3.136475399364371e-05, + "loss": 3.9522, + "step": 1138176 + }, + { + "epoch": 1.02, + "learning_rate": 3.135636804613319e-05, + "loss": 3.9588, + "step": 1138688 + }, + { + "epoch": 1.02, + "learning_rate": 3.134798209862267e-05, + "loss": 3.9621, + "step": 1139200 + }, + { + "epoch": 1.02, + "learning_rate": 3.133959615111216e-05, + "loss": 3.9602, + "step": 1139712 + }, + { + "epoch": 1.02, + "learning_rate": 3.133121020360164e-05, + "loss": 3.9506, + "step": 1140224 + }, + { + "epoch": 1.02, + "learning_rate": 3.132284063489485e-05, + "loss": 3.9503, + "step": 1140736 + }, + { + "epoch": 1.02, + "learning_rate": 3.131445468738433e-05, + "loss": 3.956, + "step": 1141248 + }, + { + "epoch": 1.02, + "learning_rate": 3.130606873987381e-05, + "loss": 3.9509, + "step": 1141760 + }, + { + "epoch": 1.02, + "learning_rate": 3.129768279236329e-05, + "loss": 3.9462, + "step": 1142272 + }, + { + "epoch": 1.02, + "learning_rate": 3.1289313223656496e-05, + "loss": 3.961, + "step": 1142784 + }, + { + "epoch": 1.02, + "learning_rate": 3.1280943654949705e-05, + "loss": 3.9503, + "step": 1143296 + }, + { + "epoch": 1.02, + "learning_rate": 3.1272557707439185e-05, + "loss": 3.9665, + "step": 1143808 + }, + { + "epoch": 1.02, + "learning_rate": 3.1264171759928665e-05, + "loss": 3.9473, + "step": 1144320 + }, + { + "epoch": 1.03, + "eval_loss": 4.015634536743164, + "eval_runtime": 299.7876, + "eval_samples_per_second": 1272.871, + "eval_steps_per_second": 39.778, + "step": 1144800 + }, + { + "epoch": 0.0, + "learning_rate": 3.1255785812418145e-05, + "loss": 3.9354, + "step": 1144832 + }, + { + "epoch": 0.0, + "learning_rate": 3.1247399864907625e-05, + "loss": 3.9511, + "step": 1145344 + }, + { + "epoch": 0.0, + "learning_rate": 3.123901391739711e-05, + "loss": 3.9503, + "step": 1145856 + }, + { + "epoch": 0.0, + "learning_rate": 3.123062796988659e-05, + "loss": 3.9601, + "step": 1146368 + }, + { + "epoch": 0.0, + "learning_rate": 3.122224202237607e-05, + "loss": 3.9542, + "step": 1146880 + }, + { + "epoch": 0.0, + "learning_rate": 3.121385607486555e-05, + "loss": 3.9585, + "step": 1147392 + }, + { + "epoch": 0.0, + "learning_rate": 3.120547012735503e-05, + "loss": 3.9505, + "step": 1147904 + }, + { + "epoch": 0.0, + "learning_rate": 3.119708417984451e-05, + "loss": 3.9519, + "step": 1148416 + }, + { + "epoch": 0.0, + "learning_rate": 3.1188698232333985e-05, + "loss": 3.952, + "step": 1148928 + }, + { + "epoch": 0.0, + "learning_rate": 3.1180312284823465e-05, + "loss": 3.9575, + "step": 1149440 + }, + { + "epoch": 0.0, + "learning_rate": 3.1171926337312945e-05, + "loss": 3.9528, + "step": 1149952 + }, + { + "epoch": 0.0, + "learning_rate": 3.1163540389802425e-05, + "loss": 3.9626, + "step": 1150464 + }, + { + "epoch": 0.0, + "learning_rate": 3.1155170821095634e-05, + "loss": 3.9642, + "step": 1150976 + }, + { + "epoch": 0.0, + "learning_rate": 3.1146784873585114e-05, + "loss": 3.9414, + "step": 1151488 + }, + { + "epoch": 0.0, + "learning_rate": 3.1138398926074594e-05, + "loss": 3.9469, + "step": 1152000 + }, + { + "epoch": 0.0, + "learning_rate": 3.113001297856408e-05, + "loss": 3.939, + "step": 1152512 + }, + { + "epoch": 0.0, + "learning_rate": 3.112162703105356e-05, + "loss": 3.9598, + "step": 1153024 + }, + { + "epoch": 0.0, + "learning_rate": 3.111324108354304e-05, + "loss": 3.9525, + "step": 1153536 + }, + { + "epoch": 0.0, + "learning_rate": 3.110485513603252e-05, + "loss": 3.9461, + "step": 1154048 + }, + { + "epoch": 0.0, + "learning_rate": 3.109648556732573e-05, + "loss": 3.953, + "step": 1154560 + }, + { + "epoch": 0.0, + "learning_rate": 3.108809961981521e-05, + "loss": 3.9651, + "step": 1155072 + }, + { + "epoch": 0.0, + "learning_rate": 3.107971367230469e-05, + "loss": 3.9589, + "step": 1155584 + }, + { + "epoch": 0.0, + "learning_rate": 3.107132772479417e-05, + "loss": 3.9557, + "step": 1156096 + }, + { + "epoch": 0.0, + "learning_rate": 3.106294177728365e-05, + "loss": 3.9546, + "step": 1156608 + }, + { + "epoch": 0.0, + "learning_rate": 3.105455582977313e-05, + "loss": 3.9646, + "step": 1157120 + }, + { + "epoch": 0.0, + "learning_rate": 3.104616988226261e-05, + "loss": 3.9457, + "step": 1157632 + }, + { + "epoch": 0.0, + "learning_rate": 3.103778393475209e-05, + "loss": 3.9503, + "step": 1158144 + }, + { + "epoch": 0.0, + "learning_rate": 3.102939798724157e-05, + "loss": 3.9531, + "step": 1158656 + }, + { + "epoch": 0.0, + "learning_rate": 3.102101203973105e-05, + "loss": 3.9442, + "step": 1159168 + }, + { + "epoch": 0.0, + "learning_rate": 3.101262609222053e-05, + "loss": 3.9466, + "step": 1159680 + }, + { + "epoch": 0.01, + "learning_rate": 3.100424014471001e-05, + "loss": 3.9484, + "step": 1160192 + }, + { + "epoch": 0.01, + "learning_rate": 3.0995870576003225e-05, + "loss": 3.9503, + "step": 1160704 + }, + { + "epoch": 0.01, + "learning_rate": 3.09874846284927e-05, + "loss": 3.9617, + "step": 1161216 + }, + { + "epoch": 0.01, + "learning_rate": 3.0979115059785914e-05, + "loss": 3.9536, + "step": 1161728 + }, + { + "epoch": 0.01, + "learning_rate": 3.0970729112275394e-05, + "loss": 3.9488, + "step": 1162240 + }, + { + "epoch": 0.01, + "learning_rate": 3.09623595435686e-05, + "loss": 3.9489, + "step": 1162752 + }, + { + "epoch": 0.01, + "learning_rate": 3.095397359605808e-05, + "loss": 3.9596, + "step": 1163264 + }, + { + "epoch": 0.01, + "learning_rate": 3.094558764854756e-05, + "loss": 3.9389, + "step": 1163776 + }, + { + "epoch": 0.01, + "learning_rate": 3.093720170103704e-05, + "loss": 3.9543, + "step": 1164288 + }, + { + "epoch": 0.01, + "learning_rate": 3.092881575352652e-05, + "loss": 3.9425, + "step": 1164800 + }, + { + "epoch": 0.01, + "learning_rate": 3.0920429806016e-05, + "loss": 3.9429, + "step": 1165312 + }, + { + "epoch": 0.01, + "learning_rate": 3.091204385850548e-05, + "loss": 3.9493, + "step": 1165824 + }, + { + "epoch": 0.01, + "learning_rate": 3.090365791099496e-05, + "loss": 3.965, + "step": 1166336 + }, + { + "epoch": 0.01, + "learning_rate": 3.089527196348444e-05, + "loss": 3.9371, + "step": 1166848 + }, + { + "epoch": 0.01, + "learning_rate": 3.088688601597392e-05, + "loss": 3.9544, + "step": 1167360 + }, + { + "epoch": 0.01, + "learning_rate": 3.08785000684634e-05, + "loss": 3.9512, + "step": 1167872 + }, + { + "epoch": 0.01, + "learning_rate": 3.087011412095288e-05, + "loss": 3.9483, + "step": 1168384 + }, + { + "epoch": 0.01, + "learning_rate": 3.086174455224609e-05, + "loss": 3.9538, + "step": 1168896 + }, + { + "epoch": 0.01, + "learning_rate": 3.085335860473557e-05, + "loss": 3.9306, + "step": 1169408 + }, + { + "epoch": 0.01, + "learning_rate": 3.084497265722505e-05, + "loss": 3.9472, + "step": 1169920 + }, + { + "epoch": 0.01, + "learning_rate": 3.083658670971453e-05, + "loss": 3.9546, + "step": 1170432 + }, + { + "epoch": 0.01, + "learning_rate": 3.082821714100774e-05, + "loss": 3.9548, + "step": 1170944 + }, + { + "epoch": 0.01, + "learning_rate": 3.081984757230095e-05, + "loss": 3.9415, + "step": 1171456 + }, + { + "epoch": 0.01, + "learning_rate": 3.0811461624790436e-05, + "loss": 3.9392, + "step": 1171968 + }, + { + "epoch": 0.01, + "learning_rate": 3.0803075677279916e-05, + "loss": 3.944, + "step": 1172480 + }, + { + "epoch": 0.01, + "learning_rate": 3.0794689729769396e-05, + "loss": 3.9353, + "step": 1172992 + }, + { + "epoch": 0.01, + "learning_rate": 3.0786303782258876e-05, + "loss": 3.9607, + "step": 1173504 + }, + { + "epoch": 0.01, + "learning_rate": 3.0777917834748356e-05, + "loss": 3.926, + "step": 1174016 + }, + { + "epoch": 0.01, + "learning_rate": 3.0769531887237836e-05, + "loss": 3.951, + "step": 1174528 + }, + { + "epoch": 0.01, + "learning_rate": 3.0761145939727316e-05, + "loss": 3.949, + "step": 1175040 + }, + { + "epoch": 0.01, + "learning_rate": 3.0752776371020525e-05, + "loss": 3.9415, + "step": 1175552 + }, + { + "epoch": 0.01, + "learning_rate": 3.0744406802313734e-05, + "loss": 3.956, + "step": 1176064 + }, + { + "epoch": 0.01, + "learning_rate": 3.0736020854803214e-05, + "loss": 3.9394, + "step": 1176576 + }, + { + "epoch": 0.01, + "learning_rate": 3.0727634907292694e-05, + "loss": 3.9354, + "step": 1177088 + }, + { + "epoch": 0.01, + "learning_rate": 3.0719248959782174e-05, + "loss": 3.9367, + "step": 1177600 + }, + { + "epoch": 0.01, + "learning_rate": 3.0710863012271654e-05, + "loss": 3.9631, + "step": 1178112 + }, + { + "epoch": 0.01, + "learning_rate": 3.070249344356487e-05, + "loss": 3.9388, + "step": 1178624 + }, + { + "epoch": 0.01, + "learning_rate": 3.069410749605435e-05, + "loss": 3.9378, + "step": 1179136 + }, + { + "epoch": 0.01, + "learning_rate": 3.068572154854383e-05, + "loss": 3.9313, + "step": 1179648 + }, + { + "epoch": 0.01, + "learning_rate": 3.067733560103331e-05, + "loss": 3.941, + "step": 1180160 + }, + { + "epoch": 0.01, + "learning_rate": 3.066894965352279e-05, + "loss": 3.9537, + "step": 1180672 + }, + { + "epoch": 0.01, + "learning_rate": 3.066056370601227e-05, + "loss": 3.9555, + "step": 1181184 + }, + { + "epoch": 0.01, + "learning_rate": 3.065217775850175e-05, + "loss": 3.9411, + "step": 1181696 + }, + { + "epoch": 0.01, + "learning_rate": 3.064379181099123e-05, + "loss": 3.9565, + "step": 1182208 + }, + { + "epoch": 0.01, + "learning_rate": 3.063542224228444e-05, + "loss": 3.9615, + "step": 1182720 + }, + { + "epoch": 0.01, + "learning_rate": 3.062703629477392e-05, + "loss": 3.9522, + "step": 1183232 + }, + { + "epoch": 0.01, + "learning_rate": 3.06186503472634e-05, + "loss": 3.9442, + "step": 1183744 + }, + { + "epoch": 0.01, + "learning_rate": 3.061028077855661e-05, + "loss": 3.9463, + "step": 1184256 + }, + { + "epoch": 0.01, + "learning_rate": 3.060189483104609e-05, + "loss": 3.9501, + "step": 1184768 + }, + { + "epoch": 0.01, + "learning_rate": 3.0593508883535574e-05, + "loss": 3.9441, + "step": 1185280 + }, + { + "epoch": 0.01, + "learning_rate": 3.058513931482878e-05, + "loss": 3.9442, + "step": 1185792 + }, + { + "epoch": 0.01, + "learning_rate": 3.057675336731826e-05, + "loss": 3.9542, + "step": 1186304 + }, + { + "epoch": 0.01, + "learning_rate": 3.056836741980774e-05, + "loss": 3.9564, + "step": 1186816 + }, + { + "epoch": 0.01, + "learning_rate": 3.055998147229722e-05, + "loss": 3.9523, + "step": 1187328 + }, + { + "epoch": 0.01, + "learning_rate": 3.05515955247867e-05, + "loss": 3.933, + "step": 1187840 + }, + { + "epoch": 0.01, + "learning_rate": 3.054320957727618e-05, + "loss": 3.9387, + "step": 1188352 + }, + { + "epoch": 0.01, + "learning_rate": 3.0534823629765656e-05, + "loss": 3.9508, + "step": 1188864 + }, + { + "epoch": 0.01, + "learning_rate": 3.0526437682255136e-05, + "loss": 3.9391, + "step": 1189376 + }, + { + "epoch": 0.01, + "learning_rate": 3.0518051734744616e-05, + "loss": 3.9509, + "step": 1189888 + }, + { + "epoch": 0.01, + "learning_rate": 3.05096657872341e-05, + "loss": 3.9424, + "step": 1190400 + }, + { + "epoch": 0.02, + "learning_rate": 3.050127983972358e-05, + "loss": 3.942, + "step": 1190912 + }, + { + "epoch": 0.02, + "learning_rate": 3.049289389221306e-05, + "loss": 3.9382, + "step": 1191424 + }, + { + "epoch": 0.02, + "learning_rate": 3.048452432350627e-05, + "loss": 3.947, + "step": 1191936 + }, + { + "epoch": 0.02, + "learning_rate": 3.047613837599575e-05, + "loss": 3.9478, + "step": 1192448 + }, + { + "epoch": 0.02, + "learning_rate": 3.046775242848523e-05, + "loss": 3.9532, + "step": 1192960 + }, + { + "epoch": 0.02, + "learning_rate": 3.045938285977844e-05, + "loss": 3.9521, + "step": 1193472 + }, + { + "epoch": 0.02, + "learning_rate": 3.045099691226792e-05, + "loss": 3.9334, + "step": 1193984 + }, + { + "epoch": 0.02, + "learning_rate": 3.04426109647574e-05, + "loss": 3.9477, + "step": 1194496 + }, + { + "epoch": 0.02, + "learning_rate": 3.043422501724688e-05, + "loss": 3.9435, + "step": 1195008 + }, + { + "epoch": 0.02, + "learning_rate": 3.042583906973636e-05, + "loss": 3.9487, + "step": 1195520 + }, + { + "epoch": 0.02, + "learning_rate": 3.041745312222584e-05, + "loss": 3.9518, + "step": 1196032 + }, + { + "epoch": 0.02, + "learning_rate": 3.040906717471532e-05, + "loss": 3.9355, + "step": 1196544 + }, + { + "epoch": 0.02, + "learning_rate": 3.0400697606008533e-05, + "loss": 3.9457, + "step": 1197056 + }, + { + "epoch": 0.02, + "learning_rate": 3.0392311658498013e-05, + "loss": 3.9469, + "step": 1197568 + }, + { + "epoch": 0.02, + "learning_rate": 3.0383925710987493e-05, + "loss": 3.9457, + "step": 1198080 + }, + { + "epoch": 0.02, + "learning_rate": 3.0375539763476973e-05, + "loss": 3.9377, + "step": 1198592 + }, + { + "epoch": 0.02, + "learning_rate": 3.0367170194770182e-05, + "loss": 3.9409, + "step": 1199104 + }, + { + "epoch": 0.02, + "learning_rate": 3.0358784247259665e-05, + "loss": 3.9447, + "step": 1199616 + }, + { + "epoch": 0.02, + "learning_rate": 3.0350398299749145e-05, + "loss": 3.9467, + "step": 1200128 + }, + { + "epoch": 0.02, + "learning_rate": 3.0342012352238625e-05, + "loss": 3.9384, + "step": 1200640 + }, + { + "epoch": 0.02, + "learning_rate": 3.0333626404728105e-05, + "loss": 3.9383, + "step": 1201152 + }, + { + "epoch": 0.02, + "learning_rate": 3.0325240457217585e-05, + "loss": 3.9346, + "step": 1201664 + }, + { + "epoch": 0.02, + "learning_rate": 3.0316854509707065e-05, + "loss": 3.9527, + "step": 1202176 + }, + { + "epoch": 0.02, + "learning_rate": 3.0308468562196545e-05, + "loss": 3.941, + "step": 1202688 + }, + { + "epoch": 0.02, + "learning_rate": 3.0300098993489758e-05, + "loss": 3.9418, + "step": 1203200 + }, + { + "epoch": 0.02, + "learning_rate": 3.0291713045979238e-05, + "loss": 3.9512, + "step": 1203712 + }, + { + "epoch": 0.02, + "learning_rate": 3.0283327098468718e-05, + "loss": 3.9527, + "step": 1204224 + }, + { + "epoch": 0.02, + "learning_rate": 3.027494115095819e-05, + "loss": 3.9417, + "step": 1204736 + }, + { + "epoch": 0.02, + "learning_rate": 3.0266571582251407e-05, + "loss": 3.9448, + "step": 1205248 + }, + { + "epoch": 0.02, + "learning_rate": 3.0258185634740887e-05, + "loss": 3.9526, + "step": 1205760 + }, + { + "epoch": 0.02, + "learning_rate": 3.02498160660341e-05, + "loss": 3.9463, + "step": 1206272 + }, + { + "epoch": 0.02, + "learning_rate": 3.024143011852358e-05, + "loss": 3.938, + "step": 1206784 + }, + { + "epoch": 0.02, + "learning_rate": 3.023304417101306e-05, + "loss": 3.945, + "step": 1207296 + }, + { + "epoch": 0.02, + "learning_rate": 3.022465822350254e-05, + "loss": 3.9352, + "step": 1207808 + }, + { + "epoch": 0.02, + "learning_rate": 3.021627227599202e-05, + "loss": 3.9427, + "step": 1208320 + }, + { + "epoch": 0.02, + "learning_rate": 3.0207886328481495e-05, + "loss": 3.9381, + "step": 1208832 + }, + { + "epoch": 0.02, + "learning_rate": 3.019951675977471e-05, + "loss": 3.9424, + "step": 1209344 + }, + { + "epoch": 0.02, + "learning_rate": 3.019113081226419e-05, + "loss": 3.9387, + "step": 1209856 + }, + { + "epoch": 0.02, + "learning_rate": 3.0182744864753664e-05, + "loss": 3.9398, + "step": 1210368 + }, + { + "epoch": 0.02, + "learning_rate": 3.0174358917243144e-05, + "loss": 3.9417, + "step": 1210880 + }, + { + "epoch": 0.02, + "learning_rate": 3.0165972969732624e-05, + "loss": 3.9529, + "step": 1211392 + }, + { + "epoch": 0.02, + "learning_rate": 3.0157587022222104e-05, + "loss": 3.9519, + "step": 1211904 + }, + { + "epoch": 0.02, + "learning_rate": 3.0149217453515317e-05, + "loss": 3.9411, + "step": 1212416 + }, + { + "epoch": 0.02, + "learning_rate": 3.0140831506004797e-05, + "loss": 3.9439, + "step": 1212928 + }, + { + "epoch": 0.02, + "learning_rate": 3.0132445558494277e-05, + "loss": 3.9465, + "step": 1213440 + }, + { + "epoch": 0.02, + "learning_rate": 3.0124059610983757e-05, + "loss": 3.9494, + "step": 1213952 + }, + { + "epoch": 0.02, + "learning_rate": 3.0115690042276966e-05, + "loss": 3.9454, + "step": 1214464 + }, + { + "epoch": 0.02, + "learning_rate": 3.010730409476645e-05, + "loss": 3.9465, + "step": 1214976 + }, + { + "epoch": 0.02, + "learning_rate": 3.009891814725593e-05, + "loss": 3.9499, + "step": 1215488 + }, + { + "epoch": 0.02, + "learning_rate": 3.009053219974541e-05, + "loss": 3.9465, + "step": 1216000 + }, + { + "epoch": 0.02, + "learning_rate": 3.008214625223489e-05, + "loss": 3.9424, + "step": 1216512 + }, + { + "epoch": 0.02, + "learning_rate": 3.0073776683528098e-05, + "loss": 3.9392, + "step": 1217024 + }, + { + "epoch": 0.02, + "learning_rate": 3.0065390736017578e-05, + "loss": 3.9445, + "step": 1217536 + }, + { + "epoch": 0.02, + "learning_rate": 3.0057004788507058e-05, + "loss": 3.9412, + "step": 1218048 + }, + { + "epoch": 0.02, + "learning_rate": 3.004861884099654e-05, + "loss": 3.9349, + "step": 1218560 + }, + { + "epoch": 0.02, + "learning_rate": 3.004024927228975e-05, + "loss": 3.9495, + "step": 1219072 + }, + { + "epoch": 0.02, + "learning_rate": 3.003186332477923e-05, + "loss": 3.9427, + "step": 1219584 + }, + { + "epoch": 0.02, + "learning_rate": 3.002347737726871e-05, + "loss": 3.9494, + "step": 1220096 + }, + { + "epoch": 0.02, + "learning_rate": 3.001509142975819e-05, + "loss": 3.9385, + "step": 1220608 + }, + { + "epoch": 0.03, + "learning_rate": 3.000670548224767e-05, + "loss": 3.9428, + "step": 1221120 + }, + { + "epoch": 0.03, + "eval_loss": 4.0101094245910645, + "eval_runtime": 297.1044, + "eval_samples_per_second": 1284.367, + "eval_steps_per_second": 40.137, + "step": 1221120 + }, + { + "epoch": 1.0, + "learning_rate": 2.999831953473715e-05, + "loss": 3.9429, + "step": 1221632 + }, + { + "epoch": 1.0, + "learning_rate": 2.998993358722663e-05, + "loss": 3.9363, + "step": 1222144 + }, + { + "epoch": 1.0, + "learning_rate": 2.9981547639716114e-05, + "loss": 3.95, + "step": 1222656 + }, + { + "epoch": 1.0, + "learning_rate": 2.9973161692205593e-05, + "loss": 3.9447, + "step": 1223168 + }, + { + "epoch": 1.0, + "learning_rate": 2.9964775744695073e-05, + "loss": 3.9467, + "step": 1223680 + }, + { + "epoch": 1.0, + "learning_rate": 2.9956389797184553e-05, + "loss": 3.9398, + "step": 1224192 + }, + { + "epoch": 1.0, + "learning_rate": 2.9948003849674027e-05, + "loss": 3.9437, + "step": 1224704 + }, + { + "epoch": 1.0, + "learning_rate": 2.9939634280967242e-05, + "loss": 3.9375, + "step": 1225216 + }, + { + "epoch": 1.0, + "learning_rate": 2.9931248333456722e-05, + "loss": 3.9484, + "step": 1225728 + }, + { + "epoch": 1.0, + "learning_rate": 2.9922878764749935e-05, + "loss": 3.9424, + "step": 1226240 + }, + { + "epoch": 1.0, + "learning_rate": 2.9914492817239415e-05, + "loss": 3.9509, + "step": 1226752 + }, + { + "epoch": 1.0, + "learning_rate": 2.9906106869728895e-05, + "loss": 3.9508, + "step": 1227264 + }, + { + "epoch": 1.0, + "learning_rate": 2.9897737301022104e-05, + "loss": 3.9387, + "step": 1227776 + }, + { + "epoch": 1.0, + "learning_rate": 2.9889351353511584e-05, + "loss": 3.9358, + "step": 1228288 + }, + { + "epoch": 1.0, + "learning_rate": 2.9880965406001067e-05, + "loss": 3.9269, + "step": 1228800 + }, + { + "epoch": 1.0, + "learning_rate": 2.9872579458490547e-05, + "loss": 3.9444, + "step": 1229312 + }, + { + "epoch": 1.0, + "learning_rate": 2.9864193510980027e-05, + "loss": 3.9404, + "step": 1229824 + }, + { + "epoch": 1.0, + "learning_rate": 2.98558075634695e-05, + "loss": 3.9393, + "step": 1230336 + }, + { + "epoch": 1.0, + "learning_rate": 2.9847437994762716e-05, + "loss": 3.9391, + "step": 1230848 + }, + { + "epoch": 1.0, + "learning_rate": 2.9839052047252196e-05, + "loss": 3.956, + "step": 1231360 + }, + { + "epoch": 1.0, + "learning_rate": 2.9830666099741676e-05, + "loss": 3.9433, + "step": 1231872 + }, + { + "epoch": 1.0, + "learning_rate": 2.9822280152231153e-05, + "loss": 3.946, + "step": 1232384 + }, + { + "epoch": 1.0, + "learning_rate": 2.9813894204720633e-05, + "loss": 3.9465, + "step": 1232896 + }, + { + "epoch": 1.0, + "learning_rate": 2.9805508257210113e-05, + "loss": 3.9512, + "step": 1233408 + }, + { + "epoch": 1.0, + "learning_rate": 2.9797122309699593e-05, + "loss": 3.9345, + "step": 1233920 + }, + { + "epoch": 1.0, + "learning_rate": 2.9788736362189072e-05, + "loss": 3.9398, + "step": 1234432 + }, + { + "epoch": 1.0, + "learning_rate": 2.9780350414678552e-05, + "loss": 3.9376, + "step": 1234944 + }, + { + "epoch": 1.0, + "learning_rate": 2.9771964467168036e-05, + "loss": 3.9355, + "step": 1235456 + }, + { + "epoch": 1.0, + "learning_rate": 2.9763578519657516e-05, + "loss": 3.9361, + "step": 1235968 + }, + { + "epoch": 1.01, + "learning_rate": 2.9755192572146996e-05, + "loss": 3.9375, + "step": 1236480 + }, + { + "epoch": 1.01, + "learning_rate": 2.9746823003440205e-05, + "loss": 3.9393, + "step": 1236992 + }, + { + "epoch": 1.01, + "learning_rate": 2.9738437055929685e-05, + "loss": 3.9495, + "step": 1237504 + }, + { + "epoch": 1.01, + "learning_rate": 2.9730051108419165e-05, + "loss": 3.9445, + "step": 1238016 + }, + { + "epoch": 1.01, + "learning_rate": 2.9721665160908645e-05, + "loss": 3.9374, + "step": 1238528 + }, + { + "epoch": 1.01, + "learning_rate": 2.9713295592201857e-05, + "loss": 3.9402, + "step": 1239040 + }, + { + "epoch": 1.01, + "learning_rate": 2.9704909644691337e-05, + "loss": 3.946, + "step": 1239552 + }, + { + "epoch": 1.01, + "learning_rate": 2.9696540075984546e-05, + "loss": 3.9328, + "step": 1240064 + }, + { + "epoch": 1.01, + "learning_rate": 2.9688154128474026e-05, + "loss": 3.9449, + "step": 1240576 + }, + { + "epoch": 1.01, + "learning_rate": 2.9679768180963506e-05, + "loss": 3.9287, + "step": 1241088 + }, + { + "epoch": 1.01, + "learning_rate": 2.967138223345299e-05, + "loss": 3.9347, + "step": 1241600 + }, + { + "epoch": 1.01, + "learning_rate": 2.966299628594247e-05, + "loss": 3.9401, + "step": 1242112 + }, + { + "epoch": 1.01, + "learning_rate": 2.965461033843195e-05, + "loss": 3.9505, + "step": 1242624 + }, + { + "epoch": 1.01, + "learning_rate": 2.964624076972516e-05, + "loss": 3.9304, + "step": 1243136 + }, + { + "epoch": 1.01, + "learning_rate": 2.963785482221464e-05, + "loss": 3.9397, + "step": 1243648 + }, + { + "epoch": 1.01, + "learning_rate": 2.962946887470412e-05, + "loss": 3.9397, + "step": 1244160 + }, + { + "epoch": 1.01, + "learning_rate": 2.96210829271936e-05, + "loss": 3.9356, + "step": 1244672 + }, + { + "epoch": 1.01, + "learning_rate": 2.961269697968308e-05, + "loss": 3.9475, + "step": 1245184 + }, + { + "epoch": 1.01, + "learning_rate": 2.960431103217256e-05, + "loss": 3.9166, + "step": 1245696 + }, + { + "epoch": 1.01, + "learning_rate": 2.959594146346577e-05, + "loss": 3.9359, + "step": 1246208 + }, + { + "epoch": 1.01, + "learning_rate": 2.958755551595525e-05, + "loss": 3.944, + "step": 1246720 + }, + { + "epoch": 1.01, + "learning_rate": 2.957916956844473e-05, + "loss": 3.9467, + "step": 1247232 + }, + { + "epoch": 1.01, + "learning_rate": 2.957078362093421e-05, + "loss": 3.9328, + "step": 1247744 + }, + { + "epoch": 1.01, + "learning_rate": 2.9562397673423687e-05, + "loss": 3.9253, + "step": 1248256 + }, + { + "epoch": 1.01, + "learning_rate": 2.9554011725913167e-05, + "loss": 3.9356, + "step": 1248768 + }, + { + "epoch": 1.01, + "learning_rate": 2.9545642157206383e-05, + "loss": 3.9224, + "step": 1249280 + }, + { + "epoch": 1.01, + "learning_rate": 2.9537256209695863e-05, + "loss": 3.9527, + "step": 1249792 + }, + { + "epoch": 1.01, + "learning_rate": 2.9528870262185336e-05, + "loss": 3.917, + "step": 1250304 + }, + { + "epoch": 1.01, + "learning_rate": 2.952048431467482e-05, + "loss": 3.9432, + "step": 1250816 + }, + { + "epoch": 1.01, + "learning_rate": 2.95120983671643e-05, + "loss": 3.9373, + "step": 1251328 + }, + { + "epoch": 1.01, + "learning_rate": 2.950371241965378e-05, + "loss": 3.9326, + "step": 1251840 + }, + { + "epoch": 1.01, + "learning_rate": 2.949532647214326e-05, + "loss": 3.9419, + "step": 1252352 + }, + { + "epoch": 1.01, + "learning_rate": 2.948694052463274e-05, + "loss": 3.9295, + "step": 1252864 + }, + { + "epoch": 1.01, + "learning_rate": 2.947857095592595e-05, + "loss": 3.9221, + "step": 1253376 + }, + { + "epoch": 1.01, + "learning_rate": 2.947018500841543e-05, + "loss": 3.9264, + "step": 1253888 + }, + { + "epoch": 1.01, + "learning_rate": 2.9461799060904908e-05, + "loss": 3.9491, + "step": 1254400 + }, + { + "epoch": 1.01, + "learning_rate": 2.945342949219812e-05, + "loss": 3.9329, + "step": 1254912 + }, + { + "epoch": 1.01, + "learning_rate": 2.94450435446876e-05, + "loss": 3.9326, + "step": 1255424 + }, + { + "epoch": 1.01, + "learning_rate": 2.943665759717708e-05, + "loss": 3.9192, + "step": 1255936 + }, + { + "epoch": 1.01, + "learning_rate": 2.942827164966656e-05, + "loss": 3.9271, + "step": 1256448 + }, + { + "epoch": 1.01, + "learning_rate": 2.941990208095977e-05, + "loss": 3.9443, + "step": 1256960 + }, + { + "epoch": 1.01, + "learning_rate": 2.9411516133449253e-05, + "loss": 3.9476, + "step": 1257472 + }, + { + "epoch": 1.01, + "learning_rate": 2.9403130185938733e-05, + "loss": 3.9311, + "step": 1257984 + }, + { + "epoch": 1.01, + "learning_rate": 2.9394744238428213e-05, + "loss": 3.9433, + "step": 1258496 + }, + { + "epoch": 1.01, + "learning_rate": 2.9386358290917693e-05, + "loss": 3.9524, + "step": 1259008 + }, + { + "epoch": 1.01, + "learning_rate": 2.9377972343407173e-05, + "loss": 3.9417, + "step": 1259520 + }, + { + "epoch": 1.01, + "learning_rate": 2.9369586395896653e-05, + "loss": 3.931, + "step": 1260032 + }, + { + "epoch": 1.01, + "learning_rate": 2.9361233205993594e-05, + "loss": 3.9374, + "step": 1260544 + }, + { + "epoch": 1.01, + "learning_rate": 2.9352847258483074e-05, + "loss": 3.9387, + "step": 1261056 + }, + { + "epoch": 1.01, + "learning_rate": 2.9344461310972554e-05, + "loss": 3.9335, + "step": 1261568 + }, + { + "epoch": 1.01, + "learning_rate": 2.9336075363462034e-05, + "loss": 3.9348, + "step": 1262080 + }, + { + "epoch": 1.01, + "learning_rate": 2.9327689415951514e-05, + "loss": 3.9392, + "step": 1262592 + }, + { + "epoch": 1.01, + "learning_rate": 2.9319303468440994e-05, + "loss": 3.946, + "step": 1263104 + }, + { + "epoch": 1.01, + "learning_rate": 2.9310917520930474e-05, + "loss": 3.9422, + "step": 1263616 + }, + { + "epoch": 1.01, + "learning_rate": 2.9302531573419954e-05, + "loss": 3.9237, + "step": 1264128 + }, + { + "epoch": 1.01, + "learning_rate": 2.9294145625909438e-05, + "loss": 3.9325, + "step": 1264640 + }, + { + "epoch": 1.01, + "learning_rate": 2.9285759678398917e-05, + "loss": 3.9364, + "step": 1265152 + }, + { + "epoch": 1.01, + "learning_rate": 2.9277373730888397e-05, + "loss": 3.9357, + "step": 1265664 + }, + { + "epoch": 1.01, + "learning_rate": 2.9269004162181607e-05, + "loss": 3.9373, + "step": 1266176 + }, + { + "epoch": 1.01, + "learning_rate": 2.9260618214671086e-05, + "loss": 3.9359, + "step": 1266688 + }, + { + "epoch": 1.02, + "learning_rate": 2.9252232267160566e-05, + "loss": 3.9336, + "step": 1267200 + }, + { + "epoch": 1.02, + "learning_rate": 2.9243846319650046e-05, + "loss": 3.9236, + "step": 1267712 + }, + { + "epoch": 1.02, + "learning_rate": 2.9235460372139523e-05, + "loss": 3.9362, + "step": 1268224 + }, + { + "epoch": 1.02, + "learning_rate": 2.9227074424629003e-05, + "loss": 3.9364, + "step": 1268736 + }, + { + "epoch": 1.02, + "learning_rate": 2.921870485592222e-05, + "loss": 3.9405, + "step": 1269248 + }, + { + "epoch": 1.02, + "learning_rate": 2.92103189084117e-05, + "loss": 3.9425, + "step": 1269760 + }, + { + "epoch": 1.02, + "learning_rate": 2.9201949339704908e-05, + "loss": 3.927, + "step": 1270272 + }, + { + "epoch": 1.02, + "learning_rate": 2.919356339219439e-05, + "loss": 3.9363, + "step": 1270784 + }, + { + "epoch": 1.02, + "learning_rate": 2.918517744468387e-05, + "loss": 3.9365, + "step": 1271296 + }, + { + "epoch": 1.02, + "learning_rate": 2.9176791497173344e-05, + "loss": 3.9351, + "step": 1271808 + }, + { + "epoch": 1.02, + "learning_rate": 2.9168405549662824e-05, + "loss": 3.9421, + "step": 1272320 + }, + { + "epoch": 1.02, + "learning_rate": 2.916003598095604e-05, + "loss": 3.9273, + "step": 1272832 + }, + { + "epoch": 1.02, + "learning_rate": 2.915165003344552e-05, + "loss": 3.9347, + "step": 1273344 + }, + { + "epoch": 1.02, + "learning_rate": 2.9143264085934997e-05, + "loss": 3.9366, + "step": 1273856 + }, + { + "epoch": 1.02, + "learning_rate": 2.9134878138424477e-05, + "loss": 3.9342, + "step": 1274368 + }, + { + "epoch": 1.02, + "learning_rate": 2.9126492190913957e-05, + "loss": 3.9273, + "step": 1274880 + }, + { + "epoch": 1.02, + "learning_rate": 2.9118106243403437e-05, + "loss": 3.9307, + "step": 1275392 + }, + { + "epoch": 1.02, + "learning_rate": 2.9109720295892916e-05, + "loss": 3.9379, + "step": 1275904 + }, + { + "epoch": 1.02, + "learning_rate": 2.9101334348382396e-05, + "loss": 3.9317, + "step": 1276416 + }, + { + "epoch": 1.02, + "learning_rate": 2.9092948400871876e-05, + "loss": 3.9306, + "step": 1276928 + }, + { + "epoch": 1.02, + "learning_rate": 2.908456245336136e-05, + "loss": 3.928, + "step": 1277440 + }, + { + "epoch": 1.02, + "learning_rate": 2.907617650585084e-05, + "loss": 3.9254, + "step": 1277952 + }, + { + "epoch": 1.02, + "learning_rate": 2.906779055834032e-05, + "loss": 3.9465, + "step": 1278464 + }, + { + "epoch": 1.02, + "learning_rate": 2.905942098963353e-05, + "loss": 3.9286, + "step": 1278976 + }, + { + "epoch": 1.02, + "learning_rate": 2.9051051420926738e-05, + "loss": 3.9376, + "step": 1279488 + }, + { + "epoch": 1.02, + "learning_rate": 2.904266547341622e-05, + "loss": 3.9377, + "step": 1280000 + }, + { + "epoch": 1.02, + "learning_rate": 2.90342795259057e-05, + "loss": 3.9431, + "step": 1280512 + }, + { + "epoch": 1.02, + "learning_rate": 2.902589357839518e-05, + "loss": 3.9314, + "step": 1281024 + }, + { + "epoch": 1.02, + "learning_rate": 2.901750763088466e-05, + "loss": 3.9323, + "step": 1281536 + }, + { + "epoch": 1.02, + "learning_rate": 2.900912168337414e-05, + "loss": 3.9471, + "step": 1282048 + }, + { + "epoch": 1.02, + "learning_rate": 2.900073573586362e-05, + "loss": 3.9362, + "step": 1282560 + }, + { + "epoch": 1.02, + "learning_rate": 2.89923497883531e-05, + "loss": 3.926, + "step": 1283072 + }, + { + "epoch": 1.02, + "learning_rate": 2.898396384084258e-05, + "loss": 3.9335, + "step": 1283584 + }, + { + "epoch": 1.02, + "learning_rate": 2.8975594272135793e-05, + "loss": 3.9263, + "step": 1284096 + }, + { + "epoch": 1.02, + "learning_rate": 2.8967224703429002e-05, + "loss": 3.9313, + "step": 1284608 + }, + { + "epoch": 1.02, + "learning_rate": 2.8958838755918482e-05, + "loss": 3.9282, + "step": 1285120 + }, + { + "epoch": 1.02, + "learning_rate": 2.8950452808407962e-05, + "loss": 3.9341, + "step": 1285632 + }, + { + "epoch": 1.02, + "learning_rate": 2.8942066860897442e-05, + "loss": 3.9257, + "step": 1286144 + }, + { + "epoch": 1.02, + "learning_rate": 2.8933697292190655e-05, + "loss": 3.9288, + "step": 1286656 + }, + { + "epoch": 1.02, + "learning_rate": 2.8925311344680135e-05, + "loss": 3.9267, + "step": 1287168 + }, + { + "epoch": 1.02, + "learning_rate": 2.8916925397169615e-05, + "loss": 3.9481, + "step": 1287680 + }, + { + "epoch": 1.02, + "learning_rate": 2.8908539449659095e-05, + "loss": 3.9445, + "step": 1288192 + }, + { + "epoch": 1.02, + "learning_rate": 2.8900153502148575e-05, + "loss": 3.9305, + "step": 1288704 + }, + { + "epoch": 1.02, + "learning_rate": 2.8891767554638055e-05, + "loss": 3.9332, + "step": 1289216 + }, + { + "epoch": 1.02, + "learning_rate": 2.8883381607127535e-05, + "loss": 3.9351, + "step": 1289728 + }, + { + "epoch": 1.02, + "learning_rate": 2.887499565961701e-05, + "loss": 3.9433, + "step": 1290240 + }, + { + "epoch": 1.02, + "learning_rate": 2.886660971210649e-05, + "loss": 3.9367, + "step": 1290752 + }, + { + "epoch": 1.02, + "learning_rate": 2.8858256522203436e-05, + "loss": 3.9336, + "step": 1291264 + }, + { + "epoch": 1.02, + "learning_rate": 2.8849870574692916e-05, + "loss": 3.9424, + "step": 1291776 + }, + { + "epoch": 1.02, + "learning_rate": 2.8841484627182396e-05, + "loss": 3.9356, + "step": 1292288 + }, + { + "epoch": 1.02, + "learning_rate": 2.8833098679671876e-05, + "loss": 3.9331, + "step": 1292800 + }, + { + "epoch": 1.02, + "learning_rate": 2.8824712732161356e-05, + "loss": 3.9301, + "step": 1293312 + }, + { + "epoch": 1.02, + "learning_rate": 2.8816326784650832e-05, + "loss": 3.9388, + "step": 1293824 + }, + { + "epoch": 1.02, + "learning_rate": 2.8807940837140312e-05, + "loss": 3.9303, + "step": 1294336 + }, + { + "epoch": 1.02, + "learning_rate": 2.8799554889629792e-05, + "loss": 3.9226, + "step": 1294848 + }, + { + "epoch": 1.02, + "learning_rate": 2.8791185320923008e-05, + "loss": 3.9396, + "step": 1295360 + }, + { + "epoch": 1.02, + "learning_rate": 2.8782799373412485e-05, + "loss": 3.935, + "step": 1295872 + }, + { + "epoch": 1.02, + "learning_rate": 2.8774413425901965e-05, + "loss": 3.9399, + "step": 1296384 + }, + { + "epoch": 1.02, + "learning_rate": 2.8766027478391445e-05, + "loss": 3.9294, + "step": 1296896 + }, + { + "epoch": 1.02, + "learning_rate": 2.8757657909684654e-05, + "loss": 3.9302, + "step": 1297408 + }, + { + "epoch": 1.03, + "eval_loss": 4.005356788635254, + "eval_runtime": 296.9299, + "eval_samples_per_second": 1285.122, + "eval_steps_per_second": 40.161, + "step": 1297440 + }, + { + "epoch": 0.0, + "learning_rate": 2.8749271962174134e-05, + "loss": 3.9301, + "step": 1297920 + }, + { + "epoch": 0.0, + "learning_rate": 2.8740886014663614e-05, + "loss": 3.9279, + "step": 1298432 + }, + { + "epoch": 0.0, + "learning_rate": 2.8732500067153094e-05, + "loss": 3.9419, + "step": 1298944 + }, + { + "epoch": 0.0, + "learning_rate": 2.8724114119642577e-05, + "loss": 3.9315, + "step": 1299456 + }, + { + "epoch": 0.0, + "learning_rate": 2.8715728172132057e-05, + "loss": 3.9396, + "step": 1299968 + }, + { + "epoch": 0.0, + "learning_rate": 2.8707342224621537e-05, + "loss": 3.9281, + "step": 1300480 + }, + { + "epoch": 0.0, + "learning_rate": 2.8698956277111017e-05, + "loss": 3.9359, + "step": 1300992 + }, + { + "epoch": 0.0, + "learning_rate": 2.8690570329600497e-05, + "loss": 3.9266, + "step": 1301504 + }, + { + "epoch": 0.0, + "learning_rate": 2.8682184382089977e-05, + "loss": 3.936, + "step": 1302016 + }, + { + "epoch": 0.0, + "learning_rate": 2.8673798434579457e-05, + "loss": 3.9339, + "step": 1302528 + }, + { + "epoch": 0.0, + "learning_rate": 2.8665412487068937e-05, + "loss": 3.9424, + "step": 1303040 + }, + { + "epoch": 0.0, + "learning_rate": 2.8657026539558417e-05, + "loss": 3.9386, + "step": 1303552 + }, + { + "epoch": 0.0, + "learning_rate": 2.864865697085163e-05, + "loss": 3.926, + "step": 1304064 + }, + { + "epoch": 0.0, + "learning_rate": 2.864027102334111e-05, + "loss": 3.9264, + "step": 1304576 + }, + { + "epoch": 0.0, + "learning_rate": 2.863188507583059e-05, + "loss": 3.9262, + "step": 1305088 + }, + { + "epoch": 0.0, + "learning_rate": 2.862349912832007e-05, + "loss": 3.9266, + "step": 1305600 + }, + { + "epoch": 0.0, + "learning_rate": 2.8615113180809546e-05, + "loss": 3.9322, + "step": 1306112 + }, + { + "epoch": 0.0, + "learning_rate": 2.8606727233299026e-05, + "loss": 3.929, + "step": 1306624 + }, + { + "epoch": 0.0, + "learning_rate": 2.8598341285788506e-05, + "loss": 3.9296, + "step": 1307136 + }, + { + "epoch": 0.0, + "learning_rate": 2.8589955338277985e-05, + "loss": 3.9486, + "step": 1307648 + }, + { + "epoch": 0.0, + "learning_rate": 2.8581569390767465e-05, + "loss": 3.9336, + "step": 1308160 + }, + { + "epoch": 0.0, + "learning_rate": 2.8573183443256945e-05, + "loss": 3.9365, + "step": 1308672 + }, + { + "epoch": 0.0, + "learning_rate": 2.8564797495746425e-05, + "loss": 3.9345, + "step": 1309184 + }, + { + "epoch": 0.0, + "learning_rate": 2.8556427927039638e-05, + "loss": 3.946, + "step": 1309696 + }, + { + "epoch": 0.0, + "learning_rate": 2.8548041979529118e-05, + "loss": 3.9183, + "step": 1310208 + }, + { + "epoch": 0.0, + "learning_rate": 2.8539656032018598e-05, + "loss": 3.9362, + "step": 1310720 + }, + { + "epoch": 0.0, + "learning_rate": 2.8531270084508078e-05, + "loss": 3.9232, + "step": 1311232 + }, + { + "epoch": 0.0, + "learning_rate": 2.8522900515801287e-05, + "loss": 3.9305, + "step": 1311744 + }, + { + "epoch": 0.0, + "learning_rate": 2.8514514568290767e-05, + "loss": 3.9254, + "step": 1312256 + }, + { + "epoch": 0.01, + "learning_rate": 2.8506128620780247e-05, + "loss": 3.9239, + "step": 1312768 + }, + { + "epoch": 0.01, + "learning_rate": 2.849774267326973e-05, + "loss": 3.9306, + "step": 1313280 + }, + { + "epoch": 0.01, + "learning_rate": 2.848937310456294e-05, + "loss": 3.9421, + "step": 1313792 + }, + { + "epoch": 0.01, + "learning_rate": 2.848098715705242e-05, + "loss": 3.9296, + "step": 1314304 + }, + { + "epoch": 0.01, + "learning_rate": 2.84726012095419e-05, + "loss": 3.9331, + "step": 1314816 + }, + { + "epoch": 0.01, + "learning_rate": 2.8464231640835108e-05, + "loss": 3.9272, + "step": 1315328 + }, + { + "epoch": 0.01, + "learning_rate": 2.845584569332459e-05, + "loss": 3.9336, + "step": 1315840 + }, + { + "epoch": 0.01, + "learning_rate": 2.844745974581407e-05, + "loss": 3.9239, + "step": 1316352 + }, + { + "epoch": 0.01, + "learning_rate": 2.843907379830355e-05, + "loss": 3.9353, + "step": 1316864 + }, + { + "epoch": 0.01, + "learning_rate": 2.843068785079303e-05, + "loss": 3.9207, + "step": 1317376 + }, + { + "epoch": 0.01, + "learning_rate": 2.842230190328251e-05, + "loss": 3.9252, + "step": 1317888 + }, + { + "epoch": 0.01, + "learning_rate": 2.841391595577199e-05, + "loss": 3.9278, + "step": 1318400 + }, + { + "epoch": 0.01, + "learning_rate": 2.840553000826147e-05, + "loss": 3.9412, + "step": 1318912 + }, + { + "epoch": 0.01, + "learning_rate": 2.839714406075095e-05, + "loss": 3.9208, + "step": 1319424 + }, + { + "epoch": 0.01, + "learning_rate": 2.838875811324043e-05, + "loss": 3.9335, + "step": 1319936 + }, + { + "epoch": 0.01, + "learning_rate": 2.8380372165729908e-05, + "loss": 3.9337, + "step": 1320448 + }, + { + "epoch": 0.01, + "learning_rate": 2.8371986218219388e-05, + "loss": 3.926, + "step": 1320960 + }, + { + "epoch": 0.01, + "learning_rate": 2.8363616649512604e-05, + "loss": 3.9369, + "step": 1321472 + }, + { + "epoch": 0.01, + "learning_rate": 2.8355230702002083e-05, + "loss": 3.9131, + "step": 1321984 + }, + { + "epoch": 0.01, + "learning_rate": 2.8346844754491557e-05, + "loss": 3.9222, + "step": 1322496 + }, + { + "epoch": 0.01, + "learning_rate": 2.8338475185784773e-05, + "loss": 3.9385, + "step": 1323008 + }, + { + "epoch": 0.01, + "learning_rate": 2.8330105617077985e-05, + "loss": 3.9296, + "step": 1323520 + }, + { + "epoch": 0.01, + "learning_rate": 2.8321719669567465e-05, + "loss": 3.9214, + "step": 1324032 + }, + { + "epoch": 0.01, + "learning_rate": 2.8313333722056945e-05, + "loss": 3.9214, + "step": 1324544 + }, + { + "epoch": 0.01, + "learning_rate": 2.8304947774546425e-05, + "loss": 3.9256, + "step": 1325056 + }, + { + "epoch": 0.01, + "learning_rate": 2.8296561827035905e-05, + "loss": 3.9155, + "step": 1325568 + }, + { + "epoch": 0.01, + "learning_rate": 2.828817587952538e-05, + "loss": 3.9363, + "step": 1326080 + }, + { + "epoch": 0.01, + "learning_rate": 2.827978993201486e-05, + "loss": 3.9124, + "step": 1326592 + }, + { + "epoch": 0.01, + "learning_rate": 2.827140398450434e-05, + "loss": 3.9274, + "step": 1327104 + }, + { + "epoch": 0.01, + "learning_rate": 2.826301803699382e-05, + "loss": 3.9271, + "step": 1327616 + }, + { + "epoch": 0.01, + "learning_rate": 2.82546320894833e-05, + "loss": 3.924, + "step": 1328128 + }, + { + "epoch": 0.01, + "learning_rate": 2.824624614197278e-05, + "loss": 3.9305, + "step": 1328640 + }, + { + "epoch": 0.01, + "learning_rate": 2.823786019446226e-05, + "loss": 3.9243, + "step": 1329152 + }, + { + "epoch": 0.01, + "learning_rate": 2.8229490625755474e-05, + "loss": 3.9111, + "step": 1329664 + }, + { + "epoch": 0.01, + "learning_rate": 2.8221121057048683e-05, + "loss": 3.9138, + "step": 1330176 + }, + { + "epoch": 0.01, + "learning_rate": 2.8212735109538163e-05, + "loss": 3.9414, + "step": 1330688 + }, + { + "epoch": 0.01, + "learning_rate": 2.8204349162027643e-05, + "loss": 3.9218, + "step": 1331200 + }, + { + "epoch": 0.01, + "learning_rate": 2.8195963214517123e-05, + "loss": 3.9205, + "step": 1331712 + }, + { + "epoch": 0.01, + "learning_rate": 2.8187577267006603e-05, + "loss": 3.9123, + "step": 1332224 + }, + { + "epoch": 0.01, + "learning_rate": 2.8179191319496086e-05, + "loss": 3.9202, + "step": 1332736 + }, + { + "epoch": 0.01, + "learning_rate": 2.8170821750789295e-05, + "loss": 3.9311, + "step": 1333248 + }, + { + "epoch": 0.01, + "learning_rate": 2.8162435803278775e-05, + "loss": 3.9356, + "step": 1333760 + }, + { + "epoch": 0.01, + "learning_rate": 2.8154049855768255e-05, + "loss": 3.9256, + "step": 1334272 + }, + { + "epoch": 0.01, + "learning_rate": 2.8145663908257735e-05, + "loss": 3.9349, + "step": 1334784 + }, + { + "epoch": 0.01, + "learning_rate": 2.8137277960747215e-05, + "loss": 3.9377, + "step": 1335296 + }, + { + "epoch": 0.01, + "learning_rate": 2.8128908392040427e-05, + "loss": 3.9382, + "step": 1335808 + }, + { + "epoch": 0.01, + "learning_rate": 2.8120522444529907e-05, + "loss": 3.9182, + "step": 1336320 + }, + { + "epoch": 0.01, + "learning_rate": 2.8112136497019387e-05, + "loss": 3.9307, + "step": 1336832 + }, + { + "epoch": 0.01, + "learning_rate": 2.8103750549508867e-05, + "loss": 3.9284, + "step": 1337344 + }, + { + "epoch": 0.01, + "learning_rate": 2.8095364601998347e-05, + "loss": 3.9282, + "step": 1337856 + }, + { + "epoch": 0.01, + "learning_rate": 2.8086978654487827e-05, + "loss": 3.923, + "step": 1338368 + }, + { + "epoch": 0.01, + "learning_rate": 2.807860908578104e-05, + "loss": 3.9281, + "step": 1338880 + }, + { + "epoch": 0.01, + "learning_rate": 2.807022313827052e-05, + "loss": 3.9379, + "step": 1339392 + }, + { + "epoch": 0.01, + "learning_rate": 2.806183719076e-05, + "loss": 3.9316, + "step": 1339904 + }, + { + "epoch": 0.01, + "learning_rate": 2.805345124324948e-05, + "loss": 3.9142, + "step": 1340416 + }, + { + "epoch": 0.01, + "learning_rate": 2.804506529573896e-05, + "loss": 3.9216, + "step": 1340928 + }, + { + "epoch": 0.01, + "learning_rate": 2.803667934822844e-05, + "loss": 3.9245, + "step": 1341440 + }, + { + "epoch": 0.01, + "learning_rate": 2.8028293400717916e-05, + "loss": 3.9273, + "step": 1341952 + }, + { + "epoch": 0.01, + "learning_rate": 2.8019907453207396e-05, + "loss": 3.9303, + "step": 1342464 + }, + { + "epoch": 0.01, + "learning_rate": 2.8011537884500612e-05, + "loss": 3.923, + "step": 1342976 + }, + { + "epoch": 0.02, + "learning_rate": 2.800315193699009e-05, + "loss": 3.9293, + "step": 1343488 + }, + { + "epoch": 0.02, + "learning_rate": 2.7994765989479565e-05, + "loss": 3.9118, + "step": 1344000 + }, + { + "epoch": 0.02, + "learning_rate": 2.7986380041969045e-05, + "loss": 3.9251, + "step": 1344512 + }, + { + "epoch": 0.02, + "learning_rate": 2.7978026852065993e-05, + "loss": 3.9305, + "step": 1345024 + }, + { + "epoch": 0.02, + "learning_rate": 2.7969640904555473e-05, + "loss": 3.9274, + "step": 1345536 + }, + { + "epoch": 0.02, + "learning_rate": 2.7961254957044953e-05, + "loss": 3.9346, + "step": 1346048 + }, + { + "epoch": 0.02, + "learning_rate": 2.7952869009534433e-05, + "loss": 3.9219, + "step": 1346560 + }, + { + "epoch": 0.02, + "learning_rate": 2.7944483062023913e-05, + "loss": 3.9229, + "step": 1347072 + }, + { + "epoch": 0.02, + "learning_rate": 2.7936097114513386e-05, + "loss": 3.9293, + "step": 1347584 + }, + { + "epoch": 0.02, + "learning_rate": 2.792771116700287e-05, + "loss": 3.9296, + "step": 1348096 + }, + { + "epoch": 0.02, + "learning_rate": 2.791932521949235e-05, + "loss": 3.9272, + "step": 1348608 + }, + { + "epoch": 0.02, + "learning_rate": 2.7910955650785565e-05, + "loss": 3.9193, + "step": 1349120 + }, + { + "epoch": 0.02, + "learning_rate": 2.790256970327504e-05, + "loss": 3.9234, + "step": 1349632 + }, + { + "epoch": 0.02, + "learning_rate": 2.7894200134568254e-05, + "loss": 3.9292, + "step": 1350144 + }, + { + "epoch": 0.02, + "learning_rate": 2.7885814187057734e-05, + "loss": 3.9299, + "step": 1350656 + }, + { + "epoch": 0.02, + "learning_rate": 2.7877428239547214e-05, + "loss": 3.9114, + "step": 1351168 + }, + { + "epoch": 0.02, + "learning_rate": 2.786904229203669e-05, + "loss": 3.9234, + "step": 1351680 + }, + { + "epoch": 0.02, + "learning_rate": 2.786065634452617e-05, + "loss": 3.9304, + "step": 1352192 + }, + { + "epoch": 0.02, + "learning_rate": 2.785227039701565e-05, + "loss": 3.9218, + "step": 1352704 + }, + { + "epoch": 0.02, + "learning_rate": 2.784388444950513e-05, + "loss": 3.9184, + "step": 1353216 + }, + { + "epoch": 0.02, + "learning_rate": 2.783549850199461e-05, + "loss": 3.9203, + "step": 1353728 + }, + { + "epoch": 0.02, + "learning_rate": 2.782711255448409e-05, + "loss": 3.915, + "step": 1354240 + }, + { + "epoch": 0.02, + "learning_rate": 2.7818742985777303e-05, + "loss": 3.936, + "step": 1354752 + }, + { + "epoch": 0.02, + "learning_rate": 2.7810373417070512e-05, + "loss": 3.9201, + "step": 1355264 + }, + { + "epoch": 0.02, + "learning_rate": 2.7801987469559992e-05, + "loss": 3.9266, + "step": 1355776 + }, + { + "epoch": 0.02, + "learning_rate": 2.7793601522049472e-05, + "loss": 3.9241, + "step": 1356288 + }, + { + "epoch": 0.02, + "learning_rate": 2.7785215574538952e-05, + "loss": 3.9366, + "step": 1356800 + }, + { + "epoch": 0.02, + "learning_rate": 2.7776829627028432e-05, + "loss": 3.9207, + "step": 1357312 + }, + { + "epoch": 0.02, + "learning_rate": 2.7768460058321645e-05, + "loss": 3.9278, + "step": 1357824 + }, + { + "epoch": 0.02, + "learning_rate": 2.7760074110811125e-05, + "loss": 3.935, + "step": 1358336 + }, + { + "epoch": 0.02, + "learning_rate": 2.7751688163300605e-05, + "loss": 3.9263, + "step": 1358848 + }, + { + "epoch": 0.02, + "learning_rate": 2.7743302215790084e-05, + "loss": 3.9196, + "step": 1359360 + }, + { + "epoch": 0.02, + "learning_rate": 2.7734916268279564e-05, + "loss": 3.9239, + "step": 1359872 + }, + { + "epoch": 0.02, + "learning_rate": 2.7726546699572774e-05, + "loss": 3.9177, + "step": 1360384 + }, + { + "epoch": 0.02, + "learning_rate": 2.7718160752062257e-05, + "loss": 3.9195, + "step": 1360896 + }, + { + "epoch": 0.02, + "learning_rate": 2.7709774804551737e-05, + "loss": 3.9241, + "step": 1361408 + }, + { + "epoch": 0.02, + "learning_rate": 2.7701388857041217e-05, + "loss": 3.9217, + "step": 1361920 + }, + { + "epoch": 0.02, + "learning_rate": 2.7693019288334426e-05, + "loss": 3.917, + "step": 1362432 + }, + { + "epoch": 0.02, + "learning_rate": 2.7684633340823906e-05, + "loss": 3.9196, + "step": 1362944 + }, + { + "epoch": 0.02, + "learning_rate": 2.7676247393313386e-05, + "loss": 3.9187, + "step": 1363456 + }, + { + "epoch": 0.02, + "learning_rate": 2.7667861445802866e-05, + "loss": 3.9371, + "step": 1363968 + }, + { + "epoch": 0.02, + "learning_rate": 2.765947549829235e-05, + "loss": 3.9362, + "step": 1364480 + }, + { + "epoch": 0.02, + "learning_rate": 2.765108955078183e-05, + "loss": 3.9265, + "step": 1364992 + }, + { + "epoch": 0.02, + "learning_rate": 2.7642719982075038e-05, + "loss": 3.9181, + "step": 1365504 + }, + { + "epoch": 0.02, + "learning_rate": 2.7634334034564518e-05, + "loss": 3.9284, + "step": 1366016 + }, + { + "epoch": 0.02, + "learning_rate": 2.7625948087053998e-05, + "loss": 3.931, + "step": 1366528 + }, + { + "epoch": 0.02, + "learning_rate": 2.7617562139543478e-05, + "loss": 3.9305, + "step": 1367040 + }, + { + "epoch": 0.02, + "learning_rate": 2.7609176192032958e-05, + "loss": 3.9241, + "step": 1367552 + }, + { + "epoch": 0.02, + "learning_rate": 2.760079024452244e-05, + "loss": 3.931, + "step": 1368064 + }, + { + "epoch": 0.02, + "learning_rate": 2.759242067581565e-05, + "loss": 3.9239, + "step": 1368576 + }, + { + "epoch": 0.02, + "learning_rate": 2.758403472830513e-05, + "loss": 3.9251, + "step": 1369088 + }, + { + "epoch": 0.02, + "learning_rate": 2.757564878079461e-05, + "loss": 3.9231, + "step": 1369600 + }, + { + "epoch": 0.02, + "learning_rate": 2.756726283328409e-05, + "loss": 3.9253, + "step": 1370112 + }, + { + "epoch": 0.02, + "learning_rate": 2.7558893264577303e-05, + "loss": 3.9207, + "step": 1370624 + }, + { + "epoch": 0.02, + "learning_rate": 2.7550507317066783e-05, + "loss": 3.9164, + "step": 1371136 + }, + { + "epoch": 0.02, + "learning_rate": 2.7542121369556263e-05, + "loss": 3.9274, + "step": 1371648 + }, + { + "epoch": 0.02, + "learning_rate": 2.7533735422045743e-05, + "loss": 3.9275, + "step": 1372160 + }, + { + "epoch": 0.02, + "learning_rate": 2.7525349474535223e-05, + "loss": 3.9293, + "step": 1372672 + }, + { + "epoch": 0.02, + "learning_rate": 2.7516963527024696e-05, + "loss": 3.9184, + "step": 1373184 + }, + { + "epoch": 0.02, + "learning_rate": 2.750857757951418e-05, + "loss": 3.9204, + "step": 1373696 + }, + { + "epoch": 0.03, + "eval_loss": 4.0012125968933105, + "eval_runtime": 295.0519, + "eval_samples_per_second": 1293.301, + "eval_steps_per_second": 40.417, + "step": 1373760 + }, + { + "epoch": 1.0, + "learning_rate": 2.750019163200366e-05, + "loss": 3.9245, + "step": 1374208 + }, + { + "epoch": 1.0, + "learning_rate": 2.7491822063296875e-05, + "loss": 3.9183, + "step": 1374720 + }, + { + "epoch": 1.0, + "learning_rate": 2.7483436115786348e-05, + "loss": 3.9308, + "step": 1375232 + }, + { + "epoch": 1.0, + "learning_rate": 2.7475050168275828e-05, + "loss": 3.9229, + "step": 1375744 + }, + { + "epoch": 1.0, + "learning_rate": 2.7466664220765308e-05, + "loss": 3.9332, + "step": 1376256 + }, + { + "epoch": 1.0, + "learning_rate": 2.7458278273254788e-05, + "loss": 3.9176, + "step": 1376768 + }, + { + "epoch": 1.0, + "learning_rate": 2.744989232574427e-05, + "loss": 3.9258, + "step": 1377280 + }, + { + "epoch": 1.0, + "learning_rate": 2.744150637823375e-05, + "loss": 3.9183, + "step": 1377792 + }, + { + "epoch": 1.0, + "learning_rate": 2.743312043072323e-05, + "loss": 3.9281, + "step": 1378304 + }, + { + "epoch": 1.0, + "learning_rate": 2.742473448321271e-05, + "loss": 3.9232, + "step": 1378816 + }, + { + "epoch": 1.0, + "learning_rate": 2.741636491450592e-05, + "loss": 3.9317, + "step": 1379328 + }, + { + "epoch": 1.0, + "learning_rate": 2.74079789669954e-05, + "loss": 3.9288, + "step": 1379840 + }, + { + "epoch": 1.0, + "learning_rate": 2.739962577709235e-05, + "loss": 3.9189, + "step": 1380352 + }, + { + "epoch": 1.0, + "learning_rate": 2.7391239829581822e-05, + "loss": 3.9216, + "step": 1380864 + }, + { + "epoch": 1.0, + "learning_rate": 2.7382853882071302e-05, + "loss": 3.9175, + "step": 1381376 + }, + { + "epoch": 1.0, + "learning_rate": 2.7374467934560782e-05, + "loss": 3.9181, + "step": 1381888 + }, + { + "epoch": 1.0, + "learning_rate": 2.736608198705026e-05, + "loss": 3.9225, + "step": 1382400 + }, + { + "epoch": 1.0, + "learning_rate": 2.735769603953974e-05, + "loss": 3.9168, + "step": 1382912 + }, + { + "epoch": 1.0, + "learning_rate": 2.7349310092029225e-05, + "loss": 3.9211, + "step": 1383424 + }, + { + "epoch": 1.0, + "learning_rate": 2.7340924144518705e-05, + "loss": 3.9407, + "step": 1383936 + }, + { + "epoch": 1.0, + "learning_rate": 2.7332554575811914e-05, + "loss": 3.9265, + "step": 1384448 + }, + { + "epoch": 1.0, + "learning_rate": 2.7324168628301394e-05, + "loss": 3.9268, + "step": 1384960 + }, + { + "epoch": 1.0, + "learning_rate": 2.7315782680790874e-05, + "loss": 3.9281, + "step": 1385472 + }, + { + "epoch": 1.0, + "learning_rate": 2.7307396733280354e-05, + "loss": 3.9317, + "step": 1385984 + }, + { + "epoch": 1.0, + "learning_rate": 2.7299010785769834e-05, + "loss": 3.9097, + "step": 1386496 + }, + { + "epoch": 1.0, + "learning_rate": 2.7290624838259314e-05, + "loss": 3.9235, + "step": 1387008 + }, + { + "epoch": 1.0, + "learning_rate": 2.7282238890748797e-05, + "loss": 3.92, + "step": 1387520 + }, + { + "epoch": 1.0, + "learning_rate": 2.7273852943238277e-05, + "loss": 3.9186, + "step": 1388032 + }, + { + "epoch": 1.0, + "learning_rate": 2.7265466995727757e-05, + "loss": 3.9149, + "step": 1388544 + }, + { + "epoch": 1.01, + "learning_rate": 2.7257097427020966e-05, + "loss": 3.9144, + "step": 1389056 + }, + { + "epoch": 1.01, + "learning_rate": 2.7248711479510446e-05, + "loss": 3.9221, + "step": 1389568 + }, + { + "epoch": 1.01, + "learning_rate": 2.7240325531999926e-05, + "loss": 3.9321, + "step": 1390080 + }, + { + "epoch": 1.01, + "learning_rate": 2.7231939584489406e-05, + "loss": 3.9223, + "step": 1390592 + }, + { + "epoch": 1.01, + "learning_rate": 2.722357001578262e-05, + "loss": 3.926, + "step": 1391104 + }, + { + "epoch": 1.01, + "learning_rate": 2.7215200447075828e-05, + "loss": 3.9191, + "step": 1391616 + }, + { + "epoch": 1.01, + "learning_rate": 2.7206814499565308e-05, + "loss": 3.9224, + "step": 1392128 + }, + { + "epoch": 1.01, + "learning_rate": 2.7198428552054788e-05, + "loss": 3.9132, + "step": 1392640 + }, + { + "epoch": 1.01, + "learning_rate": 2.7190042604544267e-05, + "loss": 3.9315, + "step": 1393152 + }, + { + "epoch": 1.01, + "learning_rate": 2.718165665703375e-05, + "loss": 3.9082, + "step": 1393664 + }, + { + "epoch": 1.01, + "learning_rate": 2.717327070952323e-05, + "loss": 3.9193, + "step": 1394176 + }, + { + "epoch": 1.01, + "learning_rate": 2.716488476201271e-05, + "loss": 3.9171, + "step": 1394688 + }, + { + "epoch": 1.01, + "learning_rate": 2.7156498814502184e-05, + "loss": 3.9321, + "step": 1395200 + }, + { + "epoch": 1.01, + "learning_rate": 2.71481292457954e-05, + "loss": 3.9138, + "step": 1395712 + }, + { + "epoch": 1.01, + "learning_rate": 2.7139759677088612e-05, + "loss": 3.92, + "step": 1396224 + }, + { + "epoch": 1.01, + "learning_rate": 2.7131373729578092e-05, + "loss": 3.926, + "step": 1396736 + }, + { + "epoch": 1.01, + "learning_rate": 2.7122987782067572e-05, + "loss": 3.9159, + "step": 1397248 + }, + { + "epoch": 1.01, + "learning_rate": 2.7114601834557052e-05, + "loss": 3.9251, + "step": 1397760 + }, + { + "epoch": 1.01, + "learning_rate": 2.7106215887046532e-05, + "loss": 3.9072, + "step": 1398272 + }, + { + "epoch": 1.01, + "learning_rate": 2.709784631833974e-05, + "loss": 3.9147, + "step": 1398784 + }, + { + "epoch": 1.01, + "learning_rate": 2.708946037082922e-05, + "loss": 3.9286, + "step": 1399296 + }, + { + "epoch": 1.01, + "learning_rate": 2.7081090802122434e-05, + "loss": 3.9191, + "step": 1399808 + }, + { + "epoch": 1.01, + "learning_rate": 2.7072704854611914e-05, + "loss": 3.9161, + "step": 1400320 + }, + { + "epoch": 1.01, + "learning_rate": 2.7064318907101394e-05, + "loss": 3.9144, + "step": 1400832 + }, + { + "epoch": 1.01, + "learning_rate": 2.7055932959590873e-05, + "loss": 3.9198, + "step": 1401344 + }, + { + "epoch": 1.01, + "learning_rate": 2.7047547012080353e-05, + "loss": 3.904, + "step": 1401856 + }, + { + "epoch": 1.01, + "learning_rate": 2.703916106456983e-05, + "loss": 3.9233, + "step": 1402368 + }, + { + "epoch": 1.01, + "learning_rate": 2.703077511705931e-05, + "loss": 3.9024, + "step": 1402880 + }, + { + "epoch": 1.01, + "learning_rate": 2.702238916954879e-05, + "loss": 3.9197, + "step": 1403392 + }, + { + "epoch": 1.01, + "learning_rate": 2.701400322203827e-05, + "loss": 3.9232, + "step": 1403904 + }, + { + "epoch": 1.01, + "learning_rate": 2.700561727452775e-05, + "loss": 3.9138, + "step": 1404416 + }, + { + "epoch": 1.01, + "learning_rate": 2.699723132701723e-05, + "loss": 3.9188, + "step": 1404928 + }, + { + "epoch": 1.01, + "learning_rate": 2.698884537950671e-05, + "loss": 3.921, + "step": 1405440 + }, + { + "epoch": 1.01, + "learning_rate": 2.6980475810799922e-05, + "loss": 3.9006, + "step": 1405952 + }, + { + "epoch": 1.01, + "learning_rate": 2.697210624209313e-05, + "loss": 3.9098, + "step": 1406464 + }, + { + "epoch": 1.01, + "learning_rate": 2.696372029458261e-05, + "loss": 3.9252, + "step": 1406976 + }, + { + "epoch": 1.01, + "learning_rate": 2.695533434707209e-05, + "loss": 3.9187, + "step": 1407488 + }, + { + "epoch": 1.01, + "learning_rate": 2.694694839956157e-05, + "loss": 3.9145, + "step": 1408000 + }, + { + "epoch": 1.01, + "learning_rate": 2.693856245205105e-05, + "loss": 3.9007, + "step": 1408512 + }, + { + "epoch": 1.01, + "learning_rate": 2.6930176504540534e-05, + "loss": 3.911, + "step": 1409024 + }, + { + "epoch": 1.01, + "learning_rate": 2.6921790557030014e-05, + "loss": 3.9258, + "step": 1409536 + }, + { + "epoch": 1.01, + "learning_rate": 2.6913404609519494e-05, + "loss": 3.9276, + "step": 1410048 + }, + { + "epoch": 1.01, + "learning_rate": 2.6905035040812704e-05, + "loss": 3.9139, + "step": 1410560 + }, + { + "epoch": 1.01, + "learning_rate": 2.6896649093302183e-05, + "loss": 3.9264, + "step": 1411072 + }, + { + "epoch": 1.01, + "learning_rate": 2.6888263145791663e-05, + "loss": 3.9284, + "step": 1411584 + }, + { + "epoch": 1.01, + "learning_rate": 2.6879893577084876e-05, + "loss": 3.9331, + "step": 1412096 + }, + { + "epoch": 1.01, + "learning_rate": 2.6871507629574356e-05, + "loss": 3.9039, + "step": 1412608 + }, + { + "epoch": 1.01, + "learning_rate": 2.6863121682063836e-05, + "loss": 3.9235, + "step": 1413120 + }, + { + "epoch": 1.01, + "learning_rate": 2.6854735734553316e-05, + "loss": 3.9198, + "step": 1413632 + }, + { + "epoch": 1.01, + "learning_rate": 2.6846349787042796e-05, + "loss": 3.9148, + "step": 1414144 + }, + { + "epoch": 1.01, + "learning_rate": 2.6837980218336005e-05, + "loss": 3.9188, + "step": 1414656 + }, + { + "epoch": 1.01, + "learning_rate": 2.6829594270825488e-05, + "loss": 3.9199, + "step": 1415168 + }, + { + "epoch": 1.01, + "learning_rate": 2.6821208323314968e-05, + "loss": 3.9257, + "step": 1415680 + }, + { + "epoch": 1.01, + "learning_rate": 2.6812822375804448e-05, + "loss": 3.9275, + "step": 1416192 + }, + { + "epoch": 1.01, + "learning_rate": 2.6804436428293928e-05, + "loss": 3.9024, + "step": 1416704 + }, + { + "epoch": 1.01, + "learning_rate": 2.6796050480783408e-05, + "loss": 3.9137, + "step": 1417216 + }, + { + "epoch": 1.01, + "learning_rate": 2.6787664533272888e-05, + "loss": 3.915, + "step": 1417728 + }, + { + "epoch": 1.01, + "learning_rate": 2.6779278585762368e-05, + "loss": 3.9176, + "step": 1418240 + }, + { + "epoch": 1.01, + "learning_rate": 2.6770892638251844e-05, + "loss": 3.9223, + "step": 1418752 + }, + { + "epoch": 1.01, + "learning_rate": 2.676252306954506e-05, + "loss": 3.9111, + "step": 1419264 + }, + { + "epoch": 1.02, + "learning_rate": 2.675413712203454e-05, + "loss": 3.9202, + "step": 1419776 + }, + { + "epoch": 1.02, + "learning_rate": 2.6745751174524013e-05, + "loss": 3.9052, + "step": 1420288 + }, + { + "epoch": 1.02, + "learning_rate": 2.6737365227013493e-05, + "loss": 3.9159, + "step": 1420800 + }, + { + "epoch": 1.02, + "learning_rate": 2.672899565830671e-05, + "loss": 3.919, + "step": 1421312 + }, + { + "epoch": 1.02, + "learning_rate": 2.672060971079619e-05, + "loss": 3.9167, + "step": 1421824 + }, + { + "epoch": 1.02, + "learning_rate": 2.6712223763285666e-05, + "loss": 3.9249, + "step": 1422336 + }, + { + "epoch": 1.02, + "learning_rate": 2.6703837815775146e-05, + "loss": 3.919, + "step": 1422848 + }, + { + "epoch": 1.02, + "learning_rate": 2.669546824706836e-05, + "loss": 3.911, + "step": 1423360 + }, + { + "epoch": 1.02, + "learning_rate": 2.668708229955784e-05, + "loss": 3.9199, + "step": 1423872 + }, + { + "epoch": 1.02, + "learning_rate": 2.6678696352047318e-05, + "loss": 3.9207, + "step": 1424384 + }, + { + "epoch": 1.02, + "learning_rate": 2.6670310404536798e-05, + "loss": 3.9211, + "step": 1424896 + }, + { + "epoch": 1.02, + "learning_rate": 2.6661924457026278e-05, + "loss": 3.9079, + "step": 1425408 + }, + { + "epoch": 1.02, + "learning_rate": 2.6653571267123223e-05, + "loss": 3.9174, + "step": 1425920 + }, + { + "epoch": 1.02, + "learning_rate": 2.6645185319612703e-05, + "loss": 3.9184, + "step": 1426432 + }, + { + "epoch": 1.02, + "learning_rate": 2.6636799372102183e-05, + "loss": 3.9206, + "step": 1426944 + }, + { + "epoch": 1.02, + "learning_rate": 2.6628413424591663e-05, + "loss": 3.9004, + "step": 1427456 + }, + { + "epoch": 1.02, + "learning_rate": 2.6620043855884875e-05, + "loss": 3.9146, + "step": 1427968 + }, + { + "epoch": 1.02, + "learning_rate": 2.6611657908374355e-05, + "loss": 3.9233, + "step": 1428480 + }, + { + "epoch": 1.02, + "learning_rate": 2.6603271960863835e-05, + "loss": 3.9133, + "step": 1428992 + }, + { + "epoch": 1.02, + "learning_rate": 2.6594886013353315e-05, + "loss": 3.9097, + "step": 1429504 + }, + { + "epoch": 1.02, + "learning_rate": 2.658650006584279e-05, + "loss": 3.9149, + "step": 1430016 + }, + { + "epoch": 1.02, + "learning_rate": 2.6578114118332272e-05, + "loss": 3.9067, + "step": 1430528 + }, + { + "epoch": 1.02, + "learning_rate": 2.6569744549625484e-05, + "loss": 3.9252, + "step": 1431040 + }, + { + "epoch": 1.02, + "learning_rate": 2.656135860211496e-05, + "loss": 3.9098, + "step": 1431552 + }, + { + "epoch": 1.02, + "learning_rate": 2.655297265460444e-05, + "loss": 3.9203, + "step": 1432064 + }, + { + "epoch": 1.02, + "learning_rate": 2.654458670709392e-05, + "loss": 3.9176, + "step": 1432576 + }, + { + "epoch": 1.02, + "learning_rate": 2.65362007595834e-05, + "loss": 3.9253, + "step": 1433088 + }, + { + "epoch": 1.02, + "learning_rate": 2.652781481207288e-05, + "loss": 3.9114, + "step": 1433600 + }, + { + "epoch": 1.02, + "learning_rate": 2.651942886456236e-05, + "loss": 3.9201, + "step": 1434112 + }, + { + "epoch": 1.02, + "learning_rate": 2.6511042917051844e-05, + "loss": 3.9264, + "step": 1434624 + }, + { + "epoch": 1.02, + "learning_rate": 2.6502673348345053e-05, + "loss": 3.9176, + "step": 1435136 + }, + { + "epoch": 1.02, + "learning_rate": 2.6494287400834533e-05, + "loss": 3.9093, + "step": 1435648 + }, + { + "epoch": 1.02, + "learning_rate": 2.6485901453324013e-05, + "loss": 3.9148, + "step": 1436160 + }, + { + "epoch": 1.02, + "learning_rate": 2.6477515505813493e-05, + "loss": 3.9104, + "step": 1436672 + }, + { + "epoch": 1.02, + "learning_rate": 2.6469145937106705e-05, + "loss": 3.9142, + "step": 1437184 + }, + { + "epoch": 1.02, + "learning_rate": 2.6460759989596185e-05, + "loss": 3.9139, + "step": 1437696 + }, + { + "epoch": 1.02, + "learning_rate": 2.6452390420889395e-05, + "loss": 3.9143, + "step": 1438208 + }, + { + "epoch": 1.02, + "learning_rate": 2.6444004473378874e-05, + "loss": 3.9052, + "step": 1438720 + }, + { + "epoch": 1.02, + "learning_rate": 2.6435618525868354e-05, + "loss": 3.91, + "step": 1439232 + }, + { + "epoch": 1.02, + "learning_rate": 2.6427232578357834e-05, + "loss": 3.9084, + "step": 1439744 + }, + { + "epoch": 1.02, + "learning_rate": 2.6418846630847314e-05, + "loss": 3.9283, + "step": 1440256 + }, + { + "epoch": 1.02, + "learning_rate": 2.6410477062140527e-05, + "loss": 3.9263, + "step": 1440768 + }, + { + "epoch": 1.02, + "learning_rate": 2.6402091114630007e-05, + "loss": 3.921, + "step": 1441280 + }, + { + "epoch": 1.02, + "learning_rate": 2.6393705167119487e-05, + "loss": 3.9087, + "step": 1441792 + }, + { + "epoch": 1.02, + "learning_rate": 2.6385319219608967e-05, + "loss": 3.9184, + "step": 1442304 + }, + { + "epoch": 1.02, + "learning_rate": 2.6376933272098447e-05, + "loss": 3.925, + "step": 1442816 + }, + { + "epoch": 1.02, + "learning_rate": 2.6368547324587927e-05, + "loss": 3.9169, + "step": 1443328 + }, + { + "epoch": 1.02, + "learning_rate": 2.6360161377077407e-05, + "loss": 3.9148, + "step": 1443840 + }, + { + "epoch": 1.02, + "learning_rate": 2.635177542956689e-05, + "loss": 3.9238, + "step": 1444352 + }, + { + "epoch": 1.02, + "learning_rate": 2.634338948205637e-05, + "loss": 3.9163, + "step": 1444864 + }, + { + "epoch": 1.02, + "learning_rate": 2.633501991334958e-05, + "loss": 3.9223, + "step": 1445376 + }, + { + "epoch": 1.02, + "learning_rate": 2.632663396583906e-05, + "loss": 3.9098, + "step": 1445888 + }, + { + "epoch": 1.02, + "learning_rate": 2.631824801832854e-05, + "loss": 3.9199, + "step": 1446400 + }, + { + "epoch": 1.02, + "learning_rate": 2.630986207081802e-05, + "loss": 3.9125, + "step": 1446912 + }, + { + "epoch": 1.02, + "learning_rate": 2.630149250211123e-05, + "loss": 3.906, + "step": 1447424 + }, + { + "epoch": 1.02, + "learning_rate": 2.629310655460071e-05, + "loss": 3.9179, + "step": 1447936 + }, + { + "epoch": 1.02, + "learning_rate": 2.628472060709019e-05, + "loss": 3.9204, + "step": 1448448 + }, + { + "epoch": 1.02, + "learning_rate": 2.627633465957967e-05, + "loss": 3.9162, + "step": 1448960 + }, + { + "epoch": 1.02, + "learning_rate": 2.626796509087288e-05, + "loss": 3.9134, + "step": 1449472 + }, + { + "epoch": 1.02, + "learning_rate": 2.625957914336236e-05, + "loss": 3.9088, + "step": 1449984 + }, + { + "epoch": 1.03, + "eval_loss": 3.9971611499786377, + "eval_runtime": 296.462, + "eval_samples_per_second": 1287.15, + "eval_steps_per_second": 40.224, + "step": 1450080 + }, + { + "epoch": 0.0, + "learning_rate": 2.6251193195851844e-05, + "loss": 3.9181, + "step": 1450496 + }, + { + "epoch": 0.0, + "learning_rate": 2.6242807248341324e-05, + "loss": 3.9109, + "step": 1451008 + }, + { + "epoch": 0.0, + "learning_rate": 2.6234421300830797e-05, + "loss": 3.9204, + "step": 1451520 + }, + { + "epoch": 0.0, + "learning_rate": 2.6226035353320277e-05, + "loss": 3.9125, + "step": 1452032 + }, + { + "epoch": 0.0, + "learning_rate": 2.6217649405809757e-05, + "loss": 3.9304, + "step": 1452544 + }, + { + "epoch": 0.0, + "learning_rate": 2.6209263458299237e-05, + "loss": 3.9038, + "step": 1453056 + }, + { + "epoch": 0.0, + "learning_rate": 2.620087751078872e-05, + "loss": 3.9219, + "step": 1453568 + }, + { + "epoch": 0.0, + "learning_rate": 2.61924915632782e-05, + "loss": 3.9082, + "step": 1454080 + }, + { + "epoch": 0.0, + "learning_rate": 2.618410561576768e-05, + "loss": 3.9202, + "step": 1454592 + }, + { + "epoch": 0.0, + "learning_rate": 2.617571966825716e-05, + "loss": 3.9184, + "step": 1455104 + }, + { + "epoch": 0.0, + "learning_rate": 2.616733372074664e-05, + "loss": 3.9177, + "step": 1455616 + }, + { + "epoch": 0.0, + "learning_rate": 2.615894777323612e-05, + "loss": 3.9245, + "step": 1456128 + }, + { + "epoch": 0.0, + "learning_rate": 2.615057820452933e-05, + "loss": 3.9062, + "step": 1456640 + }, + { + "epoch": 0.0, + "learning_rate": 2.6142192257018812e-05, + "loss": 3.9123, + "step": 1457152 + }, + { + "epoch": 0.0, + "learning_rate": 2.6133806309508292e-05, + "loss": 3.912, + "step": 1457664 + }, + { + "epoch": 0.0, + "learning_rate": 2.6125420361997772e-05, + "loss": 3.9108, + "step": 1458176 + }, + { + "epoch": 0.0, + "learning_rate": 2.6117034414487252e-05, + "loss": 3.9125, + "step": 1458688 + }, + { + "epoch": 0.0, + "learning_rate": 2.6108648466976732e-05, + "loss": 3.9092, + "step": 1459200 + }, + { + "epoch": 0.0, + "learning_rate": 2.6100262519466212e-05, + "loss": 3.9128, + "step": 1459712 + }, + { + "epoch": 0.0, + "learning_rate": 2.609187657195569e-05, + "loss": 3.932, + "step": 1460224 + }, + { + "epoch": 0.0, + "learning_rate": 2.60835070032489e-05, + "loss": 3.9165, + "step": 1460736 + }, + { + "epoch": 0.0, + "learning_rate": 2.6075121055738384e-05, + "loss": 3.9159, + "step": 1461248 + }, + { + "epoch": 0.0, + "learning_rate": 2.6066735108227864e-05, + "loss": 3.9208, + "step": 1461760 + }, + { + "epoch": 0.0, + "learning_rate": 2.6058349160717337e-05, + "loss": 3.92, + "step": 1462272 + }, + { + "epoch": 0.0, + "learning_rate": 2.6049963213206817e-05, + "loss": 3.9039, + "step": 1462784 + }, + { + "epoch": 0.0, + "learning_rate": 2.6041577265696297e-05, + "loss": 3.9211, + "step": 1463296 + }, + { + "epoch": 0.0, + "learning_rate": 2.6033191318185777e-05, + "loss": 3.9078, + "step": 1463808 + }, + { + "epoch": 0.0, + "learning_rate": 2.602480537067526e-05, + "loss": 3.9095, + "step": 1464320 + }, + { + "epoch": 0.0, + "learning_rate": 2.601641942316474e-05, + "loss": 3.9051, + "step": 1464832 + }, + { + "epoch": 0.01, + "learning_rate": 2.600804985445795e-05, + "loss": 3.9124, + "step": 1465344 + }, + { + "epoch": 0.01, + "learning_rate": 2.599968028575116e-05, + "loss": 3.9109, + "step": 1465856 + }, + { + "epoch": 0.01, + "learning_rate": 2.599129433824064e-05, + "loss": 3.9258, + "step": 1466368 + }, + { + "epoch": 0.01, + "learning_rate": 2.5982908390730122e-05, + "loss": 3.9173, + "step": 1466880 + }, + { + "epoch": 0.01, + "learning_rate": 2.5974522443219602e-05, + "loss": 3.918, + "step": 1467392 + }, + { + "epoch": 0.01, + "learning_rate": 2.596615287451281e-05, + "loss": 3.9072, + "step": 1467904 + }, + { + "epoch": 0.01, + "learning_rate": 2.595776692700229e-05, + "loss": 3.9176, + "step": 1468416 + }, + { + "epoch": 0.01, + "learning_rate": 2.594938097949177e-05, + "loss": 3.9023, + "step": 1468928 + }, + { + "epoch": 0.01, + "learning_rate": 2.594099503198125e-05, + "loss": 3.9252, + "step": 1469440 + }, + { + "epoch": 0.01, + "learning_rate": 2.593260908447073e-05, + "loss": 3.8992, + "step": 1469952 + }, + { + "epoch": 0.01, + "learning_rate": 2.5924223136960214e-05, + "loss": 3.9073, + "step": 1470464 + }, + { + "epoch": 0.01, + "learning_rate": 2.5915837189449694e-05, + "loss": 3.9087, + "step": 1470976 + }, + { + "epoch": 0.01, + "learning_rate": 2.5907451241939174e-05, + "loss": 3.9232, + "step": 1471488 + }, + { + "epoch": 0.01, + "learning_rate": 2.5899065294428654e-05, + "loss": 3.9088, + "step": 1472000 + }, + { + "epoch": 0.01, + "learning_rate": 2.5890679346918134e-05, + "loss": 3.911, + "step": 1472512 + }, + { + "epoch": 0.01, + "learning_rate": 2.5882309778211343e-05, + "loss": 3.9135, + "step": 1473024 + }, + { + "epoch": 0.01, + "learning_rate": 2.5873923830700823e-05, + "loss": 3.9124, + "step": 1473536 + }, + { + "epoch": 0.01, + "learning_rate": 2.5865537883190307e-05, + "loss": 3.9178, + "step": 1474048 + }, + { + "epoch": 0.01, + "learning_rate": 2.5857151935679786e-05, + "loss": 3.9037, + "step": 1474560 + }, + { + "epoch": 0.01, + "learning_rate": 2.5848765988169266e-05, + "loss": 3.8997, + "step": 1475072 + }, + { + "epoch": 0.01, + "learning_rate": 2.5840380040658746e-05, + "loss": 3.9186, + "step": 1475584 + }, + { + "epoch": 0.01, + "learning_rate": 2.5832010471951955e-05, + "loss": 3.9108, + "step": 1476096 + }, + { + "epoch": 0.01, + "learning_rate": 2.5823624524441435e-05, + "loss": 3.9079, + "step": 1476608 + }, + { + "epoch": 0.01, + "learning_rate": 2.5815238576930915e-05, + "loss": 3.9064, + "step": 1477120 + }, + { + "epoch": 0.01, + "learning_rate": 2.58068526294204e-05, + "loss": 3.9105, + "step": 1477632 + }, + { + "epoch": 0.01, + "learning_rate": 2.5798466681909872e-05, + "loss": 3.8951, + "step": 1478144 + }, + { + "epoch": 0.01, + "learning_rate": 2.5790080734399352e-05, + "loss": 3.9166, + "step": 1478656 + }, + { + "epoch": 0.01, + "learning_rate": 2.5781694786888832e-05, + "loss": 3.8952, + "step": 1479168 + }, + { + "epoch": 0.01, + "learning_rate": 2.5773308839378312e-05, + "loss": 3.912, + "step": 1479680 + }, + { + "epoch": 0.01, + "learning_rate": 2.5764939270671524e-05, + "loss": 3.9095, + "step": 1480192 + }, + { + "epoch": 0.01, + "learning_rate": 2.5756553323161004e-05, + "loss": 3.9125, + "step": 1480704 + }, + { + "epoch": 0.01, + "learning_rate": 2.574818375445422e-05, + "loss": 3.9054, + "step": 1481216 + }, + { + "epoch": 0.01, + "learning_rate": 2.57397978069437e-05, + "loss": 3.9127, + "step": 1481728 + }, + { + "epoch": 0.01, + "learning_rate": 2.5731411859433173e-05, + "loss": 3.8895, + "step": 1482240 + }, + { + "epoch": 0.01, + "learning_rate": 2.5723025911922653e-05, + "loss": 3.9073, + "step": 1482752 + }, + { + "epoch": 0.01, + "learning_rate": 2.5714639964412137e-05, + "loss": 3.9141, + "step": 1483264 + }, + { + "epoch": 0.01, + "learning_rate": 2.5706254016901616e-05, + "loss": 3.9113, + "step": 1483776 + }, + { + "epoch": 0.01, + "learning_rate": 2.5697868069391096e-05, + "loss": 3.9001, + "step": 1484288 + }, + { + "epoch": 0.01, + "learning_rate": 2.5689482121880576e-05, + "loss": 3.8979, + "step": 1484800 + }, + { + "epoch": 0.01, + "learning_rate": 2.5681112553173786e-05, + "loss": 3.9001, + "step": 1485312 + }, + { + "epoch": 0.01, + "learning_rate": 2.5672726605663265e-05, + "loss": 3.9112, + "step": 1485824 + }, + { + "epoch": 0.01, + "learning_rate": 2.5664340658152745e-05, + "loss": 3.9169, + "step": 1486336 + }, + { + "epoch": 0.01, + "learning_rate": 2.565595471064223e-05, + "loss": 3.9063, + "step": 1486848 + }, + { + "epoch": 0.01, + "learning_rate": 2.564756876313171e-05, + "loss": 3.9194, + "step": 1487360 + }, + { + "epoch": 0.01, + "learning_rate": 2.563918281562119e-05, + "loss": 3.9218, + "step": 1487872 + }, + { + "epoch": 0.01, + "learning_rate": 2.563079686811067e-05, + "loss": 3.9281, + "step": 1488384 + }, + { + "epoch": 0.01, + "learning_rate": 2.5622427299403878e-05, + "loss": 3.894, + "step": 1488896 + }, + { + "epoch": 0.01, + "learning_rate": 2.5614041351893358e-05, + "loss": 3.9121, + "step": 1489408 + }, + { + "epoch": 0.01, + "learning_rate": 2.5605655404382838e-05, + "loss": 3.9156, + "step": 1489920 + }, + { + "epoch": 0.01, + "learning_rate": 2.559728583567605e-05, + "loss": 3.9037, + "step": 1490432 + }, + { + "epoch": 0.01, + "learning_rate": 2.558889988816553e-05, + "loss": 3.9101, + "step": 1490944 + }, + { + "epoch": 0.01, + "learning_rate": 2.558051394065501e-05, + "loss": 3.9146, + "step": 1491456 + }, + { + "epoch": 0.01, + "learning_rate": 2.557212799314449e-05, + "loss": 3.9192, + "step": 1491968 + }, + { + "epoch": 0.01, + "learning_rate": 2.55637584244377e-05, + "loss": 3.9108, + "step": 1492480 + }, + { + "epoch": 0.01, + "learning_rate": 2.555537247692718e-05, + "loss": 3.9019, + "step": 1492992 + }, + { + "epoch": 0.01, + "learning_rate": 2.5546986529416662e-05, + "loss": 3.9034, + "step": 1493504 + }, + { + "epoch": 0.01, + "learning_rate": 2.5538600581906142e-05, + "loss": 3.9052, + "step": 1494016 + }, + { + "epoch": 0.01, + "learning_rate": 2.5530214634395622e-05, + "loss": 3.9112, + "step": 1494528 + }, + { + "epoch": 0.01, + "learning_rate": 2.552184506568883e-05, + "loss": 3.9166, + "step": 1495040 + }, + { + "epoch": 0.01, + "learning_rate": 2.551345911817831e-05, + "loss": 3.903, + "step": 1495552 + }, + { + "epoch": 0.02, + "learning_rate": 2.550507317066779e-05, + "loss": 3.9116, + "step": 1496064 + }, + { + "epoch": 0.02, + "learning_rate": 2.549668722315727e-05, + "loss": 3.8998, + "step": 1496576 + }, + { + "epoch": 0.02, + "learning_rate": 2.5488301275646755e-05, + "loss": 3.905, + "step": 1497088 + }, + { + "epoch": 0.02, + "learning_rate": 2.5479915328136235e-05, + "loss": 3.911, + "step": 1497600 + }, + { + "epoch": 0.02, + "learning_rate": 2.5471529380625708e-05, + "loss": 3.9068, + "step": 1498112 + }, + { + "epoch": 0.02, + "learning_rate": 2.5463143433115188e-05, + "loss": 3.9179, + "step": 1498624 + }, + { + "epoch": 0.02, + "learning_rate": 2.5454773864408404e-05, + "loss": 3.9122, + "step": 1499136 + }, + { + "epoch": 0.02, + "learning_rate": 2.5446387916897884e-05, + "loss": 3.9029, + "step": 1499648 + }, + { + "epoch": 0.02, + "learning_rate": 2.5438018348191096e-05, + "loss": 3.9116, + "step": 1500160 + }, + { + "epoch": 0.02, + "learning_rate": 2.5429632400680576e-05, + "loss": 3.912, + "step": 1500672 + }, + { + "epoch": 0.02, + "learning_rate": 2.5421246453170056e-05, + "loss": 3.9141, + "step": 1501184 + }, + { + "epoch": 0.02, + "learning_rate": 2.5412876884463265e-05, + "loss": 3.9006, + "step": 1501696 + }, + { + "epoch": 0.02, + "learning_rate": 2.5404490936952745e-05, + "loss": 3.9092, + "step": 1502208 + }, + { + "epoch": 0.02, + "learning_rate": 2.5396104989442225e-05, + "loss": 3.9119, + "step": 1502720 + }, + { + "epoch": 0.02, + "learning_rate": 2.5387719041931708e-05, + "loss": 3.9164, + "step": 1503232 + }, + { + "epoch": 0.02, + "learning_rate": 2.537933309442118e-05, + "loss": 3.895, + "step": 1503744 + }, + { + "epoch": 0.02, + "learning_rate": 2.537094714691066e-05, + "loss": 3.9023, + "step": 1504256 + }, + { + "epoch": 0.02, + "learning_rate": 2.536256119940014e-05, + "loss": 3.915, + "step": 1504768 + }, + { + "epoch": 0.02, + "learning_rate": 2.535417525188962e-05, + "loss": 3.9077, + "step": 1505280 + }, + { + "epoch": 0.02, + "learning_rate": 2.53457893043791e-05, + "loss": 3.899, + "step": 1505792 + }, + { + "epoch": 0.02, + "learning_rate": 2.5337403356868585e-05, + "loss": 3.903, + "step": 1506304 + }, + { + "epoch": 0.02, + "learning_rate": 2.5329017409358065e-05, + "loss": 3.9068, + "step": 1506816 + }, + { + "epoch": 0.02, + "learning_rate": 2.5320631461847545e-05, + "loss": 3.9127, + "step": 1507328 + }, + { + "epoch": 0.02, + "learning_rate": 2.5312261893140754e-05, + "loss": 3.9044, + "step": 1507840 + }, + { + "epoch": 0.02, + "learning_rate": 2.5303875945630234e-05, + "loss": 3.905, + "step": 1508352 + }, + { + "epoch": 0.02, + "learning_rate": 2.5295489998119714e-05, + "loss": 3.9111, + "step": 1508864 + }, + { + "epoch": 0.02, + "learning_rate": 2.5287104050609193e-05, + "loss": 3.9167, + "step": 1509376 + }, + { + "epoch": 0.02, + "learning_rate": 2.5278734481902406e-05, + "loss": 3.9112, + "step": 1509888 + }, + { + "epoch": 0.02, + "learning_rate": 2.5270364913195615e-05, + "loss": 3.906, + "step": 1510400 + }, + { + "epoch": 0.02, + "learning_rate": 2.5261978965685095e-05, + "loss": 3.921, + "step": 1510912 + }, + { + "epoch": 0.02, + "learning_rate": 2.5253593018174575e-05, + "loss": 3.9114, + "step": 1511424 + }, + { + "epoch": 0.02, + "learning_rate": 2.5245207070664055e-05, + "loss": 3.8996, + "step": 1511936 + }, + { + "epoch": 0.02, + "learning_rate": 2.5236821123153538e-05, + "loss": 3.9069, + "step": 1512448 + }, + { + "epoch": 0.02, + "learning_rate": 2.5228435175643018e-05, + "loss": 3.9017, + "step": 1512960 + }, + { + "epoch": 0.02, + "learning_rate": 2.5220049228132498e-05, + "loss": 3.9065, + "step": 1513472 + }, + { + "epoch": 0.02, + "learning_rate": 2.5211663280621978e-05, + "loss": 3.9009, + "step": 1513984 + }, + { + "epoch": 0.02, + "learning_rate": 2.5203293711915187e-05, + "loss": 3.909, + "step": 1514496 + }, + { + "epoch": 0.02, + "learning_rate": 2.5194907764404667e-05, + "loss": 3.8971, + "step": 1515008 + }, + { + "epoch": 0.02, + "learning_rate": 2.5186521816894147e-05, + "loss": 3.9035, + "step": 1515520 + }, + { + "epoch": 0.02, + "learning_rate": 2.517813586938363e-05, + "loss": 3.9003, + "step": 1516032 + }, + { + "epoch": 0.02, + "learning_rate": 2.516976630067684e-05, + "loss": 3.922, + "step": 1516544 + }, + { + "epoch": 0.02, + "learning_rate": 2.516138035316632e-05, + "loss": 3.9129, + "step": 1517056 + }, + { + "epoch": 0.02, + "learning_rate": 2.51529944056558e-05, + "loss": 3.9136, + "step": 1517568 + }, + { + "epoch": 0.02, + "learning_rate": 2.514460845814528e-05, + "loss": 3.8991, + "step": 1518080 + }, + { + "epoch": 0.02, + "learning_rate": 2.5136238889438492e-05, + "loss": 3.9133, + "step": 1518592 + }, + { + "epoch": 0.02, + "learning_rate": 2.5127852941927972e-05, + "loss": 3.9181, + "step": 1519104 + }, + { + "epoch": 0.02, + "learning_rate": 2.511948337322118e-05, + "loss": 3.9077, + "step": 1519616 + }, + { + "epoch": 0.02, + "learning_rate": 2.511109742571066e-05, + "loss": 3.9041, + "step": 1520128 + }, + { + "epoch": 0.02, + "learning_rate": 2.510271147820014e-05, + "loss": 3.9141, + "step": 1520640 + }, + { + "epoch": 0.02, + "learning_rate": 2.509432553068962e-05, + "loss": 3.9079, + "step": 1521152 + }, + { + "epoch": 0.02, + "learning_rate": 2.50859395831791e-05, + "loss": 3.9166, + "step": 1521664 + }, + { + "epoch": 0.02, + "learning_rate": 2.5077553635668584e-05, + "loss": 3.8985, + "step": 1522176 + }, + { + "epoch": 0.02, + "learning_rate": 2.5069167688158064e-05, + "loss": 3.913, + "step": 1522688 + }, + { + "epoch": 0.02, + "learning_rate": 2.5060781740647544e-05, + "loss": 3.9023, + "step": 1523200 + }, + { + "epoch": 0.02, + "learning_rate": 2.5052412171940753e-05, + "loss": 3.9032, + "step": 1523712 + }, + { + "epoch": 0.02, + "learning_rate": 2.5044026224430233e-05, + "loss": 3.9097, + "step": 1524224 + }, + { + "epoch": 0.02, + "learning_rate": 2.5035640276919713e-05, + "loss": 3.9151, + "step": 1524736 + }, + { + "epoch": 0.02, + "learning_rate": 2.502725432940919e-05, + "loss": 3.907, + "step": 1525248 + }, + { + "epoch": 0.02, + "learning_rate": 2.501886838189867e-05, + "loss": 3.9014, + "step": 1525760 + }, + { + "epoch": 0.02, + "learning_rate": 2.5010498813191885e-05, + "loss": 3.9046, + "step": 1526272 + }, + { + "epoch": 0.03, + "eval_loss": 3.9938368797302246, + "eval_runtime": 298.3462, + "eval_samples_per_second": 1279.021, + "eval_steps_per_second": 39.97, + "step": 1526400 + }, + { + "epoch": 1.0, + "learning_rate": 2.5002112865681365e-05, + "loss": 3.911, + "step": 1526784 + }, + { + "epoch": 1.0, + "learning_rate": 2.4993726918170842e-05, + "loss": 3.9052, + "step": 1527296 + }, + { + "epoch": 1.0, + "learning_rate": 2.4985340970660322e-05, + "loss": 3.912, + "step": 1527808 + }, + { + "epoch": 1.0, + "learning_rate": 2.4976971401953534e-05, + "loss": 3.9039, + "step": 1528320 + }, + { + "epoch": 1.0, + "learning_rate": 2.4968585454443014e-05, + "loss": 3.9194, + "step": 1528832 + }, + { + "epoch": 1.0, + "learning_rate": 2.4960199506932494e-05, + "loss": 3.9048, + "step": 1529344 + }, + { + "epoch": 1.0, + "learning_rate": 2.4951813559421974e-05, + "loss": 3.9088, + "step": 1529856 + }, + { + "epoch": 1.0, + "learning_rate": 2.4943427611911454e-05, + "loss": 3.9005, + "step": 1530368 + }, + { + "epoch": 1.0, + "learning_rate": 2.493504166440093e-05, + "loss": 3.9106, + "step": 1530880 + }, + { + "epoch": 1.0, + "learning_rate": 2.492665571689041e-05, + "loss": 3.9142, + "step": 1531392 + }, + { + "epoch": 1.0, + "learning_rate": 2.4918269769379894e-05, + "loss": 3.9087, + "step": 1531904 + }, + { + "epoch": 1.0, + "learning_rate": 2.4909883821869374e-05, + "loss": 3.9123, + "step": 1532416 + }, + { + "epoch": 1.0, + "learning_rate": 2.4901530631966316e-05, + "loss": 3.9019, + "step": 1532928 + }, + { + "epoch": 1.0, + "learning_rate": 2.4893144684455796e-05, + "loss": 3.9039, + "step": 1533440 + }, + { + "epoch": 1.0, + "learning_rate": 2.4884758736945276e-05, + "loss": 3.9037, + "step": 1533952 + }, + { + "epoch": 1.0, + "learning_rate": 2.4876372789434756e-05, + "loss": 3.9005, + "step": 1534464 + }, + { + "epoch": 1.0, + "learning_rate": 2.4867986841924236e-05, + "loss": 3.9053, + "step": 1534976 + }, + { + "epoch": 1.0, + "learning_rate": 2.4859617273217448e-05, + "loss": 3.9037, + "step": 1535488 + }, + { + "epoch": 1.0, + "learning_rate": 2.4851231325706928e-05, + "loss": 3.9057, + "step": 1536000 + }, + { + "epoch": 1.0, + "learning_rate": 2.4842845378196405e-05, + "loss": 3.9188, + "step": 1536512 + }, + { + "epoch": 1.0, + "learning_rate": 2.4834459430685884e-05, + "loss": 3.9128, + "step": 1537024 + }, + { + "epoch": 1.0, + "learning_rate": 2.4826073483175364e-05, + "loss": 3.9079, + "step": 1537536 + }, + { + "epoch": 1.0, + "learning_rate": 2.4817687535664848e-05, + "loss": 3.9147, + "step": 1538048 + }, + { + "epoch": 1.0, + "learning_rate": 2.4809301588154328e-05, + "loss": 3.913, + "step": 1538560 + }, + { + "epoch": 1.0, + "learning_rate": 2.4800932019447537e-05, + "loss": 3.8949, + "step": 1539072 + }, + { + "epoch": 1.0, + "learning_rate": 2.4792546071937017e-05, + "loss": 3.9125, + "step": 1539584 + }, + { + "epoch": 1.0, + "learning_rate": 2.4784160124426497e-05, + "loss": 3.9009, + "step": 1540096 + }, + { + "epoch": 1.0, + "learning_rate": 2.4775774176915977e-05, + "loss": 3.9016, + "step": 1540608 + }, + { + "epoch": 1.0, + "learning_rate": 2.476740460820919e-05, + "loss": 3.8968, + "step": 1541120 + }, + { + "epoch": 1.0, + "learning_rate": 2.475901866069867e-05, + "loss": 3.9063, + "step": 1541632 + }, + { + "epoch": 1.01, + "learning_rate": 2.475063271318815e-05, + "loss": 3.9022, + "step": 1542144 + }, + { + "epoch": 1.01, + "learning_rate": 2.474224676567763e-05, + "loss": 3.9179, + "step": 1542656 + }, + { + "epoch": 1.01, + "learning_rate": 2.473386081816711e-05, + "loss": 3.9077, + "step": 1543168 + }, + { + "epoch": 1.01, + "learning_rate": 2.4725491249460318e-05, + "loss": 3.907, + "step": 1543680 + }, + { + "epoch": 1.01, + "learning_rate": 2.471712168075353e-05, + "loss": 3.9013, + "step": 1544192 + }, + { + "epoch": 1.01, + "learning_rate": 2.470873573324301e-05, + "loss": 3.9094, + "step": 1544704 + }, + { + "epoch": 1.01, + "learning_rate": 2.470034978573249e-05, + "loss": 3.9007, + "step": 1545216 + }, + { + "epoch": 1.01, + "learning_rate": 2.469196383822197e-05, + "loss": 3.9113, + "step": 1545728 + }, + { + "epoch": 1.01, + "learning_rate": 2.468357789071145e-05, + "loss": 3.8928, + "step": 1546240 + }, + { + "epoch": 1.01, + "learning_rate": 2.467519194320093e-05, + "loss": 3.8999, + "step": 1546752 + }, + { + "epoch": 1.01, + "learning_rate": 2.466680599569041e-05, + "loss": 3.9022, + "step": 1547264 + }, + { + "epoch": 1.01, + "learning_rate": 2.465842004817989e-05, + "loss": 3.9156, + "step": 1547776 + }, + { + "epoch": 1.01, + "learning_rate": 2.465003410066937e-05, + "loss": 3.9042, + "step": 1548288 + }, + { + "epoch": 1.01, + "learning_rate": 2.4641664531962583e-05, + "loss": 3.902, + "step": 1548800 + }, + { + "epoch": 1.01, + "learning_rate": 2.463327858445206e-05, + "loss": 3.9056, + "step": 1549312 + }, + { + "epoch": 1.01, + "learning_rate": 2.462489263694154e-05, + "loss": 3.9012, + "step": 1549824 + }, + { + "epoch": 1.01, + "learning_rate": 2.461650668943102e-05, + "loss": 3.9105, + "step": 1550336 + }, + { + "epoch": 1.01, + "learning_rate": 2.4608137120724235e-05, + "loss": 3.8976, + "step": 1550848 + }, + { + "epoch": 1.01, + "learning_rate": 2.459975117321371e-05, + "loss": 3.892, + "step": 1551360 + }, + { + "epoch": 1.01, + "learning_rate": 2.459136522570319e-05, + "loss": 3.912, + "step": 1551872 + }, + { + "epoch": 1.01, + "learning_rate": 2.458297927819267e-05, + "loss": 3.9011, + "step": 1552384 + }, + { + "epoch": 1.01, + "learning_rate": 2.457459333068215e-05, + "loss": 3.9029, + "step": 1552896 + }, + { + "epoch": 1.01, + "learning_rate": 2.456620738317163e-05, + "loss": 3.898, + "step": 1553408 + }, + { + "epoch": 1.01, + "learning_rate": 2.455782143566111e-05, + "loss": 3.9051, + "step": 1553920 + }, + { + "epoch": 1.01, + "learning_rate": 2.454943548815059e-05, + "loss": 3.8889, + "step": 1554432 + }, + { + "epoch": 1.01, + "learning_rate": 2.4541065919443804e-05, + "loss": 3.9032, + "step": 1554944 + }, + { + "epoch": 1.01, + "learning_rate": 2.4532679971933284e-05, + "loss": 3.8922, + "step": 1555456 + }, + { + "epoch": 1.01, + "learning_rate": 2.4524310403226493e-05, + "loss": 3.9027, + "step": 1555968 + }, + { + "epoch": 1.01, + "learning_rate": 2.451594083451971e-05, + "loss": 3.906, + "step": 1556480 + }, + { + "epoch": 1.01, + "learning_rate": 2.4507554887009185e-05, + "loss": 3.9038, + "step": 1556992 + }, + { + "epoch": 1.01, + "learning_rate": 2.4499168939498665e-05, + "loss": 3.8988, + "step": 1557504 + }, + { + "epoch": 1.01, + "learning_rate": 2.4490782991988145e-05, + "loss": 3.9097, + "step": 1558016 + }, + { + "epoch": 1.01, + "learning_rate": 2.4482397044477625e-05, + "loss": 3.8844, + "step": 1558528 + }, + { + "epoch": 1.01, + "learning_rate": 2.4474011096967105e-05, + "loss": 3.8918, + "step": 1559040 + }, + { + "epoch": 1.01, + "learning_rate": 2.4465625149456585e-05, + "loss": 3.9076, + "step": 1559552 + }, + { + "epoch": 1.01, + "learning_rate": 2.4457239201946065e-05, + "loss": 3.9016, + "step": 1560064 + }, + { + "epoch": 1.01, + "learning_rate": 2.4448853254435545e-05, + "loss": 3.8987, + "step": 1560576 + }, + { + "epoch": 1.01, + "learning_rate": 2.4440467306925025e-05, + "loss": 3.8874, + "step": 1561088 + }, + { + "epoch": 1.01, + "learning_rate": 2.4432081359414505e-05, + "loss": 3.8912, + "step": 1561600 + }, + { + "epoch": 1.01, + "learning_rate": 2.4423695411903985e-05, + "loss": 3.9034, + "step": 1562112 + }, + { + "epoch": 1.01, + "learning_rate": 2.4415325843197194e-05, + "loss": 3.911, + "step": 1562624 + }, + { + "epoch": 1.01, + "learning_rate": 2.440695627449041e-05, + "loss": 3.9031, + "step": 1563136 + }, + { + "epoch": 1.01, + "learning_rate": 2.4398570326979886e-05, + "loss": 3.9101, + "step": 1563648 + }, + { + "epoch": 1.01, + "learning_rate": 2.4390184379469366e-05, + "loss": 3.9112, + "step": 1564160 + }, + { + "epoch": 1.01, + "learning_rate": 2.4381798431958846e-05, + "loss": 3.925, + "step": 1564672 + }, + { + "epoch": 1.01, + "learning_rate": 2.4373412484448326e-05, + "loss": 3.8892, + "step": 1565184 + }, + { + "epoch": 1.01, + "learning_rate": 2.4365026536937806e-05, + "loss": 3.9025, + "step": 1565696 + }, + { + "epoch": 1.01, + "learning_rate": 2.435665696823102e-05, + "loss": 3.9114, + "step": 1566208 + }, + { + "epoch": 1.01, + "learning_rate": 2.43482710207205e-05, + "loss": 3.8887, + "step": 1566720 + }, + { + "epoch": 1.01, + "learning_rate": 2.433988507320998e-05, + "loss": 3.907, + "step": 1567232 + }, + { + "epoch": 1.01, + "learning_rate": 2.433149912569946e-05, + "loss": 3.9055, + "step": 1567744 + }, + { + "epoch": 1.01, + "learning_rate": 2.432311317818894e-05, + "loss": 3.9092, + "step": 1568256 + }, + { + "epoch": 1.01, + "learning_rate": 2.431472723067842e-05, + "loss": 3.9075, + "step": 1568768 + }, + { + "epoch": 1.01, + "learning_rate": 2.4306341283167895e-05, + "loss": 3.8932, + "step": 1569280 + }, + { + "epoch": 1.01, + "learning_rate": 2.429797171446111e-05, + "loss": 3.8962, + "step": 1569792 + }, + { + "epoch": 1.01, + "learning_rate": 2.428958576695059e-05, + "loss": 3.8973, + "step": 1570304 + }, + { + "epoch": 1.01, + "learning_rate": 2.42812161982438e-05, + "loss": 3.9024, + "step": 1570816 + }, + { + "epoch": 1.01, + "learning_rate": 2.427283025073328e-05, + "loss": 3.9111, + "step": 1571328 + }, + { + "epoch": 1.01, + "learning_rate": 2.426444430322276e-05, + "loss": 3.8954, + "step": 1571840 + }, + { + "epoch": 1.02, + "learning_rate": 2.425605835571224e-05, + "loss": 3.9026, + "step": 1572352 + }, + { + "epoch": 1.02, + "learning_rate": 2.424767240820172e-05, + "loss": 3.8913, + "step": 1572864 + }, + { + "epoch": 1.02, + "learning_rate": 2.42392864606912e-05, + "loss": 3.8971, + "step": 1573376 + }, + { + "epoch": 1.02, + "learning_rate": 2.4230916891984412e-05, + "loss": 3.9022, + "step": 1573888 + }, + { + "epoch": 1.02, + "learning_rate": 2.4222530944473892e-05, + "loss": 3.9047, + "step": 1574400 + }, + { + "epoch": 1.02, + "learning_rate": 2.421414499696337e-05, + "loss": 3.912, + "step": 1574912 + }, + { + "epoch": 1.02, + "learning_rate": 2.420575904945285e-05, + "loss": 3.9005, + "step": 1575424 + }, + { + "epoch": 1.02, + "learning_rate": 2.4197373101942332e-05, + "loss": 3.8988, + "step": 1575936 + }, + { + "epoch": 1.02, + "learning_rate": 2.418900353323554e-05, + "loss": 3.9015, + "step": 1576448 + }, + { + "epoch": 1.02, + "learning_rate": 2.418061758572502e-05, + "loss": 3.9028, + "step": 1576960 + }, + { + "epoch": 1.02, + "learning_rate": 2.41722316382145e-05, + "loss": 3.9094, + "step": 1577472 + }, + { + "epoch": 1.02, + "learning_rate": 2.416384569070398e-05, + "loss": 3.8915, + "step": 1577984 + }, + { + "epoch": 1.02, + "learning_rate": 2.415545974319346e-05, + "loss": 3.9005, + "step": 1578496 + }, + { + "epoch": 1.02, + "learning_rate": 2.414707379568294e-05, + "loss": 3.9011, + "step": 1579008 + }, + { + "epoch": 1.02, + "learning_rate": 2.4138687848172424e-05, + "loss": 3.908, + "step": 1579520 + }, + { + "epoch": 1.02, + "learning_rate": 2.41303019006619e-05, + "loss": 3.8868, + "step": 1580032 + }, + { + "epoch": 1.02, + "learning_rate": 2.4121932331955113e-05, + "loss": 3.8949, + "step": 1580544 + }, + { + "epoch": 1.02, + "learning_rate": 2.4113562763248322e-05, + "loss": 3.9077, + "step": 1581056 + }, + { + "epoch": 1.02, + "learning_rate": 2.4105176815737802e-05, + "loss": 3.9015, + "step": 1581568 + }, + { + "epoch": 1.02, + "learning_rate": 2.4096790868227286e-05, + "loss": 3.8901, + "step": 1582080 + }, + { + "epoch": 1.02, + "learning_rate": 2.4088404920716766e-05, + "loss": 3.9004, + "step": 1582592 + }, + { + "epoch": 1.02, + "learning_rate": 2.4080018973206246e-05, + "loss": 3.8938, + "step": 1583104 + }, + { + "epoch": 1.02, + "learning_rate": 2.4071633025695722e-05, + "loss": 3.907, + "step": 1583616 + }, + { + "epoch": 1.02, + "learning_rate": 2.4063247078185202e-05, + "loss": 3.8968, + "step": 1584128 + }, + { + "epoch": 1.02, + "learning_rate": 2.4054861130674682e-05, + "loss": 3.8951, + "step": 1584640 + }, + { + "epoch": 1.02, + "learning_rate": 2.4046491561967895e-05, + "loss": 3.9059, + "step": 1585152 + }, + { + "epoch": 1.02, + "learning_rate": 2.4038121993261107e-05, + "loss": 3.9142, + "step": 1585664 + }, + { + "epoch": 1.02, + "learning_rate": 2.4029736045750587e-05, + "loss": 3.9021, + "step": 1586176 + }, + { + "epoch": 1.02, + "learning_rate": 2.4021350098240067e-05, + "loss": 3.8995, + "step": 1586688 + }, + { + "epoch": 1.02, + "learning_rate": 2.4012964150729547e-05, + "loss": 3.9067, + "step": 1587200 + }, + { + "epoch": 1.02, + "learning_rate": 2.4004578203219024e-05, + "loss": 3.9043, + "step": 1587712 + }, + { + "epoch": 1.02, + "learning_rate": 2.399620863451224e-05, + "loss": 3.892, + "step": 1588224 + }, + { + "epoch": 1.02, + "learning_rate": 2.398782268700172e-05, + "loss": 3.9052, + "step": 1588736 + }, + { + "epoch": 1.02, + "learning_rate": 2.3979436739491196e-05, + "loss": 3.8938, + "step": 1589248 + }, + { + "epoch": 1.02, + "learning_rate": 2.3971050791980676e-05, + "loss": 3.8972, + "step": 1589760 + }, + { + "epoch": 1.02, + "learning_rate": 2.396268122327389e-05, + "loss": 3.8942, + "step": 1590272 + }, + { + "epoch": 1.02, + "learning_rate": 2.395429527576337e-05, + "loss": 3.9009, + "step": 1590784 + }, + { + "epoch": 1.02, + "learning_rate": 2.394590932825285e-05, + "loss": 3.8911, + "step": 1591296 + }, + { + "epoch": 1.02, + "learning_rate": 2.3937523380742328e-05, + "loss": 3.8929, + "step": 1591808 + }, + { + "epoch": 1.02, + "learning_rate": 2.3929137433231808e-05, + "loss": 3.8966, + "step": 1592320 + }, + { + "epoch": 1.02, + "learning_rate": 2.3920751485721288e-05, + "loss": 3.9105, + "step": 1592832 + }, + { + "epoch": 1.02, + "learning_rate": 2.3912365538210768e-05, + "loss": 3.9088, + "step": 1593344 + }, + { + "epoch": 1.02, + "learning_rate": 2.3903979590700248e-05, + "loss": 3.9077, + "step": 1593856 + }, + { + "epoch": 1.02, + "learning_rate": 2.3895593643189725e-05, + "loss": 3.8913, + "step": 1594368 + }, + { + "epoch": 1.02, + "learning_rate": 2.388724045328667e-05, + "loss": 3.9091, + "step": 1594880 + }, + { + "epoch": 1.02, + "learning_rate": 2.387885450577615e-05, + "loss": 3.9097, + "step": 1595392 + }, + { + "epoch": 1.02, + "learning_rate": 2.387046855826563e-05, + "loss": 3.9037, + "step": 1595904 + }, + { + "epoch": 1.02, + "learning_rate": 2.386208261075511e-05, + "loss": 3.896, + "step": 1596416 + }, + { + "epoch": 1.02, + "learning_rate": 2.385369666324459e-05, + "loss": 3.9121, + "step": 1596928 + }, + { + "epoch": 1.02, + "learning_rate": 2.384531071573407e-05, + "loss": 3.8989, + "step": 1597440 + }, + { + "epoch": 1.02, + "learning_rate": 2.383692476822355e-05, + "loss": 3.9108, + "step": 1597952 + }, + { + "epoch": 1.02, + "learning_rate": 2.382853882071303e-05, + "loss": 3.8875, + "step": 1598464 + }, + { + "epoch": 1.02, + "learning_rate": 2.3820169252006242e-05, + "loss": 3.9116, + "step": 1598976 + }, + { + "epoch": 1.02, + "learning_rate": 2.3811783304495722e-05, + "loss": 3.8928, + "step": 1599488 + }, + { + "epoch": 1.02, + "learning_rate": 2.380341373578893e-05, + "loss": 3.8938, + "step": 1600000 + }, + { + "epoch": 1.02, + "learning_rate": 2.3795044167082143e-05, + "loss": 3.9035, + "step": 1600512 + }, + { + "epoch": 1.02, + "learning_rate": 2.3786658219571623e-05, + "loss": 3.9045, + "step": 1601024 + }, + { + "epoch": 1.02, + "learning_rate": 2.3778272272061103e-05, + "loss": 3.9037, + "step": 1601536 + }, + { + "epoch": 1.02, + "learning_rate": 2.3769886324550583e-05, + "loss": 3.8917, + "step": 1602048 + }, + { + "epoch": 1.02, + "learning_rate": 2.3761500377040063e-05, + "loss": 3.9033, + "step": 1602560 + }, + { + "epoch": 1.03, + "eval_loss": 3.9913179874420166, + "eval_runtime": 299.346, + "eval_samples_per_second": 1274.749, + "eval_steps_per_second": 39.837, + "step": 1602720 + }, + { + "epoch": 0.0, + "learning_rate": 2.3753114429529543e-05, + "loss": 3.9009, + "step": 1603072 + }, + { + "epoch": 0.0, + "learning_rate": 2.3744728482019023e-05, + "loss": 3.8983, + "step": 1603584 + }, + { + "epoch": 0.0, + "learning_rate": 2.3736342534508503e-05, + "loss": 3.9054, + "step": 1604096 + }, + { + "epoch": 0.0, + "learning_rate": 2.3727956586997983e-05, + "loss": 3.8969, + "step": 1604608 + }, + { + "epoch": 0.0, + "learning_rate": 2.3719570639487463e-05, + "loss": 3.9114, + "step": 1605120 + }, + { + "epoch": 0.0, + "learning_rate": 2.3711184691976943e-05, + "loss": 3.8953, + "step": 1605632 + }, + { + "epoch": 0.0, + "learning_rate": 2.3702798744466423e-05, + "loss": 3.8976, + "step": 1606144 + }, + { + "epoch": 0.0, + "learning_rate": 2.3694412796955903e-05, + "loss": 3.8976, + "step": 1606656 + }, + { + "epoch": 0.0, + "learning_rate": 2.368602684944538e-05, + "loss": 3.9013, + "step": 1607168 + }, + { + "epoch": 0.0, + "learning_rate": 2.367764090193486e-05, + "loss": 3.9049, + "step": 1607680 + }, + { + "epoch": 0.0, + "learning_rate": 2.3669254954424343e-05, + "loss": 3.8994, + "step": 1608192 + }, + { + "epoch": 0.0, + "learning_rate": 2.3660869006913823e-05, + "loss": 3.9073, + "step": 1608704 + }, + { + "epoch": 0.0, + "learning_rate": 2.3652499438207032e-05, + "loss": 3.8939, + "step": 1609216 + }, + { + "epoch": 0.0, + "learning_rate": 2.3644113490696512e-05, + "loss": 3.8974, + "step": 1609728 + }, + { + "epoch": 0.0, + "learning_rate": 2.3635727543185992e-05, + "loss": 3.9007, + "step": 1610240 + }, + { + "epoch": 0.0, + "learning_rate": 2.362734159567547e-05, + "loss": 3.8901, + "step": 1610752 + }, + { + "epoch": 0.0, + "learning_rate": 2.361895564816495e-05, + "loss": 3.8998, + "step": 1611264 + }, + { + "epoch": 0.0, + "learning_rate": 2.3610569700654435e-05, + "loss": 3.8941, + "step": 1611776 + }, + { + "epoch": 0.0, + "learning_rate": 2.3602183753143915e-05, + "loss": 3.8946, + "step": 1612288 + }, + { + "epoch": 0.0, + "learning_rate": 2.359379780563339e-05, + "loss": 3.9152, + "step": 1612800 + }, + { + "epoch": 0.0, + "learning_rate": 2.3585428236926604e-05, + "loss": 3.9043, + "step": 1613312 + }, + { + "epoch": 0.0, + "learning_rate": 2.3577042289416084e-05, + "loss": 3.9079, + "step": 1613824 + }, + { + "epoch": 0.0, + "learning_rate": 2.3568656341905564e-05, + "loss": 3.903, + "step": 1614336 + }, + { + "epoch": 0.0, + "learning_rate": 2.3560270394395044e-05, + "loss": 3.906, + "step": 1614848 + }, + { + "epoch": 0.0, + "learning_rate": 2.3551884446884524e-05, + "loss": 3.8882, + "step": 1615360 + }, + { + "epoch": 0.0, + "learning_rate": 2.3543498499374004e-05, + "loss": 3.9073, + "step": 1615872 + }, + { + "epoch": 0.0, + "learning_rate": 2.3535112551863484e-05, + "loss": 3.8958, + "step": 1616384 + }, + { + "epoch": 0.0, + "learning_rate": 2.3526726604352964e-05, + "loss": 3.8892, + "step": 1616896 + }, + { + "epoch": 0.0, + "learning_rate": 2.3518357035646173e-05, + "loss": 3.892, + "step": 1617408 + }, + { + "epoch": 0.0, + "learning_rate": 2.3509971088135656e-05, + "loss": 3.8972, + "step": 1617920 + }, + { + "epoch": 0.01, + "learning_rate": 2.3501585140625136e-05, + "loss": 3.8979, + "step": 1618432 + }, + { + "epoch": 0.01, + "learning_rate": 2.3493199193114616e-05, + "loss": 3.9077, + "step": 1618944 + }, + { + "epoch": 0.01, + "learning_rate": 2.3484829624407825e-05, + "loss": 3.9058, + "step": 1619456 + }, + { + "epoch": 0.01, + "learning_rate": 2.3476460055701034e-05, + "loss": 3.9005, + "step": 1619968 + }, + { + "epoch": 0.01, + "learning_rate": 2.346809048699425e-05, + "loss": 3.8952, + "step": 1620480 + }, + { + "epoch": 0.01, + "learning_rate": 2.345970453948373e-05, + "loss": 3.899, + "step": 1620992 + }, + { + "epoch": 0.01, + "learning_rate": 2.345131859197321e-05, + "loss": 3.8924, + "step": 1621504 + }, + { + "epoch": 0.01, + "learning_rate": 2.3442932644462687e-05, + "loss": 3.9026, + "step": 1622016 + }, + { + "epoch": 0.01, + "learning_rate": 2.3434546696952166e-05, + "loss": 3.8893, + "step": 1622528 + }, + { + "epoch": 0.01, + "learning_rate": 2.3426160749441646e-05, + "loss": 3.8904, + "step": 1623040 + }, + { + "epoch": 0.01, + "learning_rate": 2.3417774801931126e-05, + "loss": 3.8971, + "step": 1623552 + }, + { + "epoch": 0.01, + "learning_rate": 2.3409388854420606e-05, + "loss": 3.9075, + "step": 1624064 + }, + { + "epoch": 0.01, + "learning_rate": 2.340100290691009e-05, + "loss": 3.8985, + "step": 1624576 + }, + { + "epoch": 0.01, + "learning_rate": 2.33926333382033e-05, + "loss": 3.8945, + "step": 1625088 + }, + { + "epoch": 0.01, + "learning_rate": 2.338424739069278e-05, + "loss": 3.9018, + "step": 1625600 + }, + { + "epoch": 0.01, + "learning_rate": 2.337586144318226e-05, + "loss": 3.8932, + "step": 1626112 + }, + { + "epoch": 0.01, + "learning_rate": 2.336747549567174e-05, + "loss": 3.9047, + "step": 1626624 + }, + { + "epoch": 0.01, + "learning_rate": 2.335908954816122e-05, + "loss": 3.8909, + "step": 1627136 + }, + { + "epoch": 0.01, + "learning_rate": 2.33507036006507e-05, + "loss": 3.8813, + "step": 1627648 + }, + { + "epoch": 0.01, + "learning_rate": 2.334231765314018e-05, + "loss": 3.9022, + "step": 1628160 + }, + { + "epoch": 0.01, + "learning_rate": 2.333394808443339e-05, + "loss": 3.8974, + "step": 1628672 + }, + { + "epoch": 0.01, + "learning_rate": 2.3325562136922868e-05, + "loss": 3.8934, + "step": 1629184 + }, + { + "epoch": 0.01, + "learning_rate": 2.3317176189412348e-05, + "loss": 3.8962, + "step": 1629696 + }, + { + "epoch": 0.01, + "learning_rate": 2.3308790241901828e-05, + "loss": 3.8925, + "step": 1630208 + }, + { + "epoch": 0.01, + "learning_rate": 2.330040429439131e-05, + "loss": 3.8849, + "step": 1630720 + }, + { + "epoch": 0.01, + "learning_rate": 2.329201834688079e-05, + "loss": 3.8928, + "step": 1631232 + }, + { + "epoch": 0.01, + "learning_rate": 2.328363239937027e-05, + "loss": 3.8867, + "step": 1631744 + }, + { + "epoch": 0.01, + "learning_rate": 2.3275246451859747e-05, + "loss": 3.8916, + "step": 1632256 + }, + { + "epoch": 0.01, + "learning_rate": 2.326687688315296e-05, + "loss": 3.9024, + "step": 1632768 + }, + { + "epoch": 0.01, + "learning_rate": 2.325849093564244e-05, + "loss": 3.89, + "step": 1633280 + }, + { + "epoch": 0.01, + "learning_rate": 2.325010498813192e-05, + "loss": 3.8939, + "step": 1633792 + }, + { + "epoch": 0.01, + "learning_rate": 2.32417190406214e-05, + "loss": 3.903, + "step": 1634304 + }, + { + "epoch": 0.01, + "learning_rate": 2.3233349471914612e-05, + "loss": 3.8807, + "step": 1634816 + }, + { + "epoch": 0.01, + "learning_rate": 2.322497990320782e-05, + "loss": 3.8848, + "step": 1635328 + }, + { + "epoch": 0.01, + "learning_rate": 2.32165939556973e-05, + "loss": 3.8989, + "step": 1635840 + }, + { + "epoch": 0.01, + "learning_rate": 2.320820800818678e-05, + "loss": 3.8986, + "step": 1636352 + }, + { + "epoch": 0.01, + "learning_rate": 2.3199822060676265e-05, + "loss": 3.8889, + "step": 1636864 + }, + { + "epoch": 0.01, + "learning_rate": 2.3191436113165744e-05, + "loss": 3.8861, + "step": 1637376 + }, + { + "epoch": 0.01, + "learning_rate": 2.318305016565522e-05, + "loss": 3.8817, + "step": 1637888 + }, + { + "epoch": 0.01, + "learning_rate": 2.31746642181447e-05, + "loss": 3.8975, + "step": 1638400 + }, + { + "epoch": 0.01, + "learning_rate": 2.316627827063418e-05, + "loss": 3.9018, + "step": 1638912 + }, + { + "epoch": 0.01, + "learning_rate": 2.3157908701927393e-05, + "loss": 3.8962, + "step": 1639424 + }, + { + "epoch": 0.01, + "learning_rate": 2.3149522754416873e-05, + "loss": 3.9028, + "step": 1639936 + }, + { + "epoch": 0.01, + "learning_rate": 2.3141136806906353e-05, + "loss": 3.8995, + "step": 1640448 + }, + { + "epoch": 0.01, + "learning_rate": 2.3132750859395833e-05, + "loss": 3.9235, + "step": 1640960 + }, + { + "epoch": 0.01, + "learning_rate": 2.3124381290689046e-05, + "loss": 3.8818, + "step": 1641472 + }, + { + "epoch": 0.01, + "learning_rate": 2.3115995343178522e-05, + "loss": 3.895, + "step": 1641984 + }, + { + "epoch": 0.01, + "learning_rate": 2.3107609395668002e-05, + "loss": 3.905, + "step": 1642496 + }, + { + "epoch": 0.01, + "learning_rate": 2.3099223448157482e-05, + "loss": 3.8822, + "step": 1643008 + }, + { + "epoch": 0.01, + "learning_rate": 2.3090853879450695e-05, + "loss": 3.9015, + "step": 1643520 + }, + { + "epoch": 0.01, + "learning_rate": 2.3082467931940175e-05, + "loss": 3.8976, + "step": 1644032 + }, + { + "epoch": 0.01, + "learning_rate": 2.3074081984429655e-05, + "loss": 3.9026, + "step": 1644544 + }, + { + "epoch": 0.01, + "learning_rate": 2.3065696036919135e-05, + "loss": 3.9004, + "step": 1645056 + }, + { + "epoch": 0.01, + "learning_rate": 2.3057310089408615e-05, + "loss": 3.8851, + "step": 1645568 + }, + { + "epoch": 0.01, + "learning_rate": 2.3048924141898095e-05, + "loss": 3.8982, + "step": 1646080 + }, + { + "epoch": 0.01, + "learning_rate": 2.3040538194387574e-05, + "loss": 3.8824, + "step": 1646592 + }, + { + "epoch": 0.01, + "learning_rate": 2.3032152246877054e-05, + "loss": 3.8985, + "step": 1647104 + }, + { + "epoch": 0.01, + "learning_rate": 2.3023782678170267e-05, + "loss": 3.904, + "step": 1647616 + }, + { + "epoch": 0.01, + "learning_rate": 2.3015413109463476e-05, + "loss": 3.8845, + "step": 1648128 + }, + { + "epoch": 0.02, + "learning_rate": 2.3007027161952956e-05, + "loss": 3.8988, + "step": 1648640 + }, + { + "epoch": 0.02, + "learning_rate": 2.2998641214442436e-05, + "loss": 3.8877, + "step": 1649152 + }, + { + "epoch": 0.02, + "learning_rate": 2.299025526693192e-05, + "loss": 3.8878, + "step": 1649664 + }, + { + "epoch": 0.02, + "learning_rate": 2.29818693194214e-05, + "loss": 3.89, + "step": 1650176 + }, + { + "epoch": 0.02, + "learning_rate": 2.2973483371910876e-05, + "loss": 3.9032, + "step": 1650688 + }, + { + "epoch": 0.02, + "learning_rate": 2.2965113803204088e-05, + "loss": 3.906, + "step": 1651200 + }, + { + "epoch": 0.02, + "learning_rate": 2.2956727855693568e-05, + "loss": 3.8896, + "step": 1651712 + }, + { + "epoch": 0.02, + "learning_rate": 2.2948341908183048e-05, + "loss": 3.8905, + "step": 1652224 + }, + { + "epoch": 0.02, + "learning_rate": 2.2939955960672528e-05, + "loss": 3.8975, + "step": 1652736 + }, + { + "epoch": 0.02, + "learning_rate": 2.293158639196574e-05, + "loss": 3.8921, + "step": 1653248 + }, + { + "epoch": 0.02, + "learning_rate": 2.292320044445522e-05, + "loss": 3.9043, + "step": 1653760 + }, + { + "epoch": 0.02, + "learning_rate": 2.29148144969447e-05, + "loss": 3.8857, + "step": 1654272 + }, + { + "epoch": 0.02, + "learning_rate": 2.2906428549434177e-05, + "loss": 3.8922, + "step": 1654784 + }, + { + "epoch": 0.02, + "learning_rate": 2.2898042601923657e-05, + "loss": 3.8963, + "step": 1655296 + }, + { + "epoch": 0.02, + "learning_rate": 2.2889656654413137e-05, + "loss": 3.9029, + "step": 1655808 + }, + { + "epoch": 0.02, + "learning_rate": 2.288127070690262e-05, + "loss": 3.8795, + "step": 1656320 + }, + { + "epoch": 0.02, + "learning_rate": 2.28728847593921e-05, + "loss": 3.8887, + "step": 1656832 + }, + { + "epoch": 0.02, + "learning_rate": 2.286451519068531e-05, + "loss": 3.8944, + "step": 1657344 + }, + { + "epoch": 0.02, + "learning_rate": 2.285612924317479e-05, + "loss": 3.8959, + "step": 1657856 + }, + { + "epoch": 0.02, + "learning_rate": 2.284774329566427e-05, + "loss": 3.8804, + "step": 1658368 + }, + { + "epoch": 0.02, + "learning_rate": 2.283935734815375e-05, + "loss": 3.8982, + "step": 1658880 + }, + { + "epoch": 0.02, + "learning_rate": 2.283097140064323e-05, + "loss": 3.8823, + "step": 1659392 + }, + { + "epoch": 0.02, + "learning_rate": 2.282258545313271e-05, + "loss": 3.8966, + "step": 1659904 + }, + { + "epoch": 0.02, + "learning_rate": 2.281419950562219e-05, + "loss": 3.8923, + "step": 1660416 + }, + { + "epoch": 0.02, + "learning_rate": 2.28058299369154e-05, + "loss": 3.8884, + "step": 1660928 + }, + { + "epoch": 0.02, + "learning_rate": 2.279744398940488e-05, + "loss": 3.8976, + "step": 1661440 + }, + { + "epoch": 0.02, + "learning_rate": 2.2789058041894358e-05, + "loss": 3.9087, + "step": 1661952 + }, + { + "epoch": 0.02, + "learning_rate": 2.2780672094383838e-05, + "loss": 3.8936, + "step": 1662464 + }, + { + "epoch": 0.02, + "learning_rate": 2.277228614687332e-05, + "loss": 3.8927, + "step": 1662976 + }, + { + "epoch": 0.02, + "learning_rate": 2.27639001993628e-05, + "loss": 3.8994, + "step": 1663488 + }, + { + "epoch": 0.02, + "learning_rate": 2.275551425185228e-05, + "loss": 3.8975, + "step": 1664000 + }, + { + "epoch": 0.02, + "learning_rate": 2.274712830434176e-05, + "loss": 3.8868, + "step": 1664512 + }, + { + "epoch": 0.02, + "learning_rate": 2.273875873563497e-05, + "loss": 3.8944, + "step": 1665024 + }, + { + "epoch": 0.02, + "learning_rate": 2.2730389166928183e-05, + "loss": 3.8899, + "step": 1665536 + }, + { + "epoch": 0.02, + "learning_rate": 2.2722003219417663e-05, + "loss": 3.8929, + "step": 1666048 + }, + { + "epoch": 0.02, + "learning_rate": 2.2713617271907143e-05, + "loss": 3.8922, + "step": 1666560 + }, + { + "epoch": 0.02, + "learning_rate": 2.2705231324396623e-05, + "loss": 3.8896, + "step": 1667072 + }, + { + "epoch": 0.02, + "learning_rate": 2.2696845376886103e-05, + "loss": 3.8887, + "step": 1667584 + }, + { + "epoch": 0.02, + "learning_rate": 2.2688459429375583e-05, + "loss": 3.8834, + "step": 1668096 + }, + { + "epoch": 0.02, + "learning_rate": 2.268007348186506e-05, + "loss": 3.8921, + "step": 1668608 + }, + { + "epoch": 0.02, + "learning_rate": 2.2671687534354543e-05, + "loss": 3.9022, + "step": 1669120 + }, + { + "epoch": 0.02, + "learning_rate": 2.2663317965647755e-05, + "loss": 3.8997, + "step": 1669632 + }, + { + "epoch": 0.02, + "learning_rate": 2.2654932018137235e-05, + "loss": 3.9004, + "step": 1670144 + }, + { + "epoch": 0.02, + "learning_rate": 2.264654607062671e-05, + "loss": 3.8826, + "step": 1670656 + }, + { + "epoch": 0.02, + "learning_rate": 2.263816012311619e-05, + "loss": 3.9054, + "step": 1671168 + }, + { + "epoch": 0.02, + "learning_rate": 2.262977417560567e-05, + "loss": 3.901, + "step": 1671680 + }, + { + "epoch": 0.02, + "learning_rate": 2.2621404606898884e-05, + "loss": 3.8943, + "step": 1672192 + }, + { + "epoch": 0.02, + "learning_rate": 2.2613018659388364e-05, + "loss": 3.8945, + "step": 1672704 + }, + { + "epoch": 0.02, + "learning_rate": 2.2604632711877844e-05, + "loss": 3.8982, + "step": 1673216 + }, + { + "epoch": 0.02, + "learning_rate": 2.2596246764367324e-05, + "loss": 3.8921, + "step": 1673728 + }, + { + "epoch": 0.02, + "learning_rate": 2.2587860816856804e-05, + "loss": 3.9082, + "step": 1674240 + }, + { + "epoch": 0.02, + "learning_rate": 2.2579474869346284e-05, + "loss": 3.8794, + "step": 1674752 + }, + { + "epoch": 0.02, + "learning_rate": 2.2571088921835764e-05, + "loss": 3.901, + "step": 1675264 + }, + { + "epoch": 0.02, + "learning_rate": 2.2562702974325244e-05, + "loss": 3.8831, + "step": 1675776 + }, + { + "epoch": 0.02, + "learning_rate": 2.2554317026814724e-05, + "loss": 3.8896, + "step": 1676288 + }, + { + "epoch": 0.02, + "learning_rate": 2.2545947458107936e-05, + "loss": 3.8962, + "step": 1676800 + }, + { + "epoch": 0.02, + "learning_rate": 2.2537577889401145e-05, + "loss": 3.8931, + "step": 1677312 + }, + { + "epoch": 0.02, + "learning_rate": 2.2529191941890625e-05, + "loss": 3.904, + "step": 1677824 + }, + { + "epoch": 0.02, + "learning_rate": 2.2520805994380105e-05, + "loss": 3.879, + "step": 1678336 + }, + { + "epoch": 0.02, + "learning_rate": 2.2512420046869585e-05, + "loss": 3.8973, + "step": 1678848 + }, + { + "epoch": 0.03, + "eval_loss": 3.988035202026367, + "eval_runtime": 297.0726, + "eval_samples_per_second": 1284.504, + "eval_steps_per_second": 40.142, + "step": 1679040 + }, + { + "epoch": 0.0, + "learning_rate": 2.250403409935907e-05, + "loss": 3.8976, + "step": 1679360 + }, + { + "epoch": 0.0, + "learning_rate": 2.2495648151848545e-05, + "loss": 3.8901, + "step": 1679872 + }, + { + "epoch": 0.0, + "learning_rate": 2.2487262204338025e-05, + "loss": 3.8992, + "step": 1680384 + }, + { + "epoch": 0.0, + "learning_rate": 2.2478876256827505e-05, + "loss": 3.892, + "step": 1680896 + }, + { + "epoch": 0.0, + "learning_rate": 2.2470490309316985e-05, + "loss": 3.8988, + "step": 1681408 + }, + { + "epoch": 0.0, + "learning_rate": 2.2462104361806465e-05, + "loss": 3.8911, + "step": 1681920 + }, + { + "epoch": 0.0, + "learning_rate": 2.2453718414295945e-05, + "loss": 3.8864, + "step": 1682432 + }, + { + "epoch": 0.0, + "learning_rate": 2.2445332466785425e-05, + "loss": 3.8937, + "step": 1682944 + }, + { + "epoch": 0.0, + "learning_rate": 2.2436946519274905e-05, + "loss": 3.8932, + "step": 1683456 + }, + { + "epoch": 0.0, + "learning_rate": 2.2428560571764385e-05, + "loss": 3.8967, + "step": 1683968 + }, + { + "epoch": 0.0, + "learning_rate": 2.2420174624253865e-05, + "loss": 3.8966, + "step": 1684480 + }, + { + "epoch": 0.0, + "learning_rate": 2.2411788676743345e-05, + "loss": 3.8952, + "step": 1684992 + }, + { + "epoch": 0.0, + "learning_rate": 2.240343548684029e-05, + "loss": 3.892, + "step": 1685504 + }, + { + "epoch": 0.0, + "learning_rate": 2.239504953932977e-05, + "loss": 3.8915, + "step": 1686016 + }, + { + "epoch": 0.0, + "learning_rate": 2.238666359181925e-05, + "loss": 3.893, + "step": 1686528 + }, + { + "epoch": 0.0, + "learning_rate": 2.2378277644308726e-05, + "loss": 3.8818, + "step": 1687040 + }, + { + "epoch": 0.0, + "learning_rate": 2.2369891696798206e-05, + "loss": 3.8918, + "step": 1687552 + }, + { + "epoch": 0.0, + "learning_rate": 2.2361505749287686e-05, + "loss": 3.8863, + "step": 1688064 + }, + { + "epoch": 0.0, + "learning_rate": 2.2353119801777166e-05, + "loss": 3.8891, + "step": 1688576 + }, + { + "epoch": 0.0, + "learning_rate": 2.2344733854266646e-05, + "loss": 3.9064, + "step": 1689088 + }, + { + "epoch": 0.0, + "learning_rate": 2.233634790675613e-05, + "loss": 3.8998, + "step": 1689600 + }, + { + "epoch": 0.0, + "learning_rate": 2.2327961959245606e-05, + "loss": 3.8993, + "step": 1690112 + }, + { + "epoch": 0.0, + "learning_rate": 2.2319576011735086e-05, + "loss": 3.8959, + "step": 1690624 + }, + { + "epoch": 0.0, + "learning_rate": 2.2311190064224566e-05, + "loss": 3.8992, + "step": 1691136 + }, + { + "epoch": 0.0, + "learning_rate": 2.2302804116714046e-05, + "loss": 3.8826, + "step": 1691648 + }, + { + "epoch": 0.0, + "learning_rate": 2.2294418169203526e-05, + "loss": 3.901, + "step": 1692160 + }, + { + "epoch": 0.0, + "learning_rate": 2.2286032221693006e-05, + "loss": 3.888, + "step": 1692672 + }, + { + "epoch": 0.0, + "learning_rate": 2.2277646274182486e-05, + "loss": 3.8836, + "step": 1693184 + }, + { + "epoch": 0.0, + "learning_rate": 2.2269276705475698e-05, + "loss": 3.8868, + "step": 1693696 + }, + { + "epoch": 0.0, + "learning_rate": 2.2260890757965178e-05, + "loss": 3.8914, + "step": 1694208 + }, + { + "epoch": 0.01, + "learning_rate": 2.2252504810454658e-05, + "loss": 3.8925, + "step": 1694720 + }, + { + "epoch": 0.01, + "learning_rate": 2.2244135241747867e-05, + "loss": 3.8997, + "step": 1695232 + }, + { + "epoch": 0.01, + "learning_rate": 2.2235749294237347e-05, + "loss": 3.8978, + "step": 1695744 + }, + { + "epoch": 0.01, + "learning_rate": 2.222736334672683e-05, + "loss": 3.8942, + "step": 1696256 + }, + { + "epoch": 0.01, + "learning_rate": 2.221899377802004e-05, + "loss": 3.8834, + "step": 1696768 + }, + { + "epoch": 0.01, + "learning_rate": 2.221060783050952e-05, + "loss": 3.8948, + "step": 1697280 + }, + { + "epoch": 0.01, + "learning_rate": 2.2202221882999e-05, + "loss": 3.8894, + "step": 1697792 + }, + { + "epoch": 0.01, + "learning_rate": 2.219383593548848e-05, + "loss": 3.8886, + "step": 1698304 + }, + { + "epoch": 0.01, + "learning_rate": 2.218544998797796e-05, + "loss": 3.8871, + "step": 1698816 + }, + { + "epoch": 0.01, + "learning_rate": 2.2177080419271172e-05, + "loss": 3.8801, + "step": 1699328 + }, + { + "epoch": 0.01, + "learning_rate": 2.216869447176065e-05, + "loss": 3.8902, + "step": 1699840 + }, + { + "epoch": 0.01, + "learning_rate": 2.216030852425013e-05, + "loss": 3.8971, + "step": 1700352 + }, + { + "epoch": 0.01, + "learning_rate": 2.2151922576739608e-05, + "loss": 3.8942, + "step": 1700864 + }, + { + "epoch": 0.01, + "learning_rate": 2.2143536629229088e-05, + "loss": 3.8863, + "step": 1701376 + }, + { + "epoch": 0.01, + "learning_rate": 2.2135150681718568e-05, + "loss": 3.8952, + "step": 1701888 + }, + { + "epoch": 0.01, + "learning_rate": 2.2126764734208048e-05, + "loss": 3.8857, + "step": 1702400 + }, + { + "epoch": 0.01, + "learning_rate": 2.211837878669753e-05, + "loss": 3.9006, + "step": 1702912 + }, + { + "epoch": 0.01, + "learning_rate": 2.210999283918701e-05, + "loss": 3.8846, + "step": 1703424 + }, + { + "epoch": 0.01, + "learning_rate": 2.210160689167649e-05, + "loss": 3.8721, + "step": 1703936 + }, + { + "epoch": 0.01, + "learning_rate": 2.2093220944165968e-05, + "loss": 3.8969, + "step": 1704448 + }, + { + "epoch": 0.01, + "learning_rate": 2.2084834996655448e-05, + "loss": 3.8926, + "step": 1704960 + }, + { + "epoch": 0.01, + "learning_rate": 2.207646542794866e-05, + "loss": 3.8888, + "step": 1705472 + }, + { + "epoch": 0.01, + "learning_rate": 2.206807948043814e-05, + "loss": 3.8858, + "step": 1705984 + }, + { + "epoch": 0.01, + "learning_rate": 2.205969353292762e-05, + "loss": 3.8853, + "step": 1706496 + }, + { + "epoch": 0.01, + "learning_rate": 2.20513075854171e-05, + "loss": 3.8818, + "step": 1707008 + }, + { + "epoch": 0.01, + "learning_rate": 2.2042938016710313e-05, + "loss": 3.8853, + "step": 1707520 + }, + { + "epoch": 0.01, + "learning_rate": 2.2034568448003522e-05, + "loss": 3.8788, + "step": 1708032 + }, + { + "epoch": 0.01, + "learning_rate": 2.2026182500493002e-05, + "loss": 3.8904, + "step": 1708544 + }, + { + "epoch": 0.01, + "learning_rate": 2.2017796552982485e-05, + "loss": 3.8925, + "step": 1709056 + }, + { + "epoch": 0.01, + "learning_rate": 2.2009410605471965e-05, + "loss": 3.886, + "step": 1709568 + }, + { + "epoch": 0.01, + "learning_rate": 2.200102465796144e-05, + "loss": 3.8851, + "step": 1710080 + }, + { + "epoch": 0.01, + "learning_rate": 2.199263871045092e-05, + "loss": 3.902, + "step": 1710592 + }, + { + "epoch": 0.01, + "learning_rate": 2.19842527629404e-05, + "loss": 3.8718, + "step": 1711104 + }, + { + "epoch": 0.01, + "learning_rate": 2.1975883194233614e-05, + "loss": 3.8763, + "step": 1711616 + }, + { + "epoch": 0.01, + "learning_rate": 2.1967497246723094e-05, + "loss": 3.8913, + "step": 1712128 + }, + { + "epoch": 0.01, + "learning_rate": 2.1959111299212574e-05, + "loss": 3.894, + "step": 1712640 + }, + { + "epoch": 0.01, + "learning_rate": 2.1950725351702054e-05, + "loss": 3.88, + "step": 1713152 + }, + { + "epoch": 0.01, + "learning_rate": 2.1942339404191534e-05, + "loss": 3.8796, + "step": 1713664 + }, + { + "epoch": 0.01, + "learning_rate": 2.1933953456681014e-05, + "loss": 3.8752, + "step": 1714176 + }, + { + "epoch": 0.01, + "learning_rate": 2.1925567509170494e-05, + "loss": 3.8879, + "step": 1714688 + }, + { + "epoch": 0.01, + "learning_rate": 2.1917197940463706e-05, + "loss": 3.8972, + "step": 1715200 + }, + { + "epoch": 0.01, + "learning_rate": 2.1908811992953186e-05, + "loss": 3.8897, + "step": 1715712 + }, + { + "epoch": 0.01, + "learning_rate": 2.1900426045442666e-05, + "loss": 3.8899, + "step": 1716224 + }, + { + "epoch": 0.01, + "learning_rate": 2.1892040097932146e-05, + "loss": 3.8959, + "step": 1716736 + }, + { + "epoch": 0.01, + "learning_rate": 2.1883654150421623e-05, + "loss": 3.9139, + "step": 1717248 + }, + { + "epoch": 0.01, + "learning_rate": 2.1875268202911103e-05, + "loss": 3.879, + "step": 1717760 + }, + { + "epoch": 0.01, + "learning_rate": 2.1866882255400583e-05, + "loss": 3.8882, + "step": 1718272 + }, + { + "epoch": 0.01, + "learning_rate": 2.1858496307890063e-05, + "loss": 3.8963, + "step": 1718784 + }, + { + "epoch": 0.01, + "learning_rate": 2.1850110360379546e-05, + "loss": 3.8761, + "step": 1719296 + }, + { + "epoch": 0.01, + "learning_rate": 2.1841740791672755e-05, + "loss": 3.893, + "step": 1719808 + }, + { + "epoch": 0.01, + "learning_rate": 2.1833354844162235e-05, + "loss": 3.8923, + "step": 1720320 + }, + { + "epoch": 0.01, + "learning_rate": 2.1824968896651715e-05, + "loss": 3.8946, + "step": 1720832 + }, + { + "epoch": 0.01, + "learning_rate": 2.1816582949141195e-05, + "loss": 3.8953, + "step": 1721344 + }, + { + "epoch": 0.01, + "learning_rate": 2.1808213380434407e-05, + "loss": 3.8776, + "step": 1721856 + }, + { + "epoch": 0.01, + "learning_rate": 2.1799827432923887e-05, + "loss": 3.8886, + "step": 1722368 + }, + { + "epoch": 0.01, + "learning_rate": 2.1791441485413367e-05, + "loss": 3.8813, + "step": 1722880 + }, + { + "epoch": 0.01, + "learning_rate": 2.1783055537902847e-05, + "loss": 3.8862, + "step": 1723392 + }, + { + "epoch": 0.01, + "learning_rate": 2.1774685969196056e-05, + "loss": 3.8955, + "step": 1723904 + }, + { + "epoch": 0.01, + "learning_rate": 2.1766300021685536e-05, + "loss": 3.8793, + "step": 1724416 + }, + { + "epoch": 0.02, + "learning_rate": 2.1757914074175016e-05, + "loss": 3.8898, + "step": 1724928 + }, + { + "epoch": 0.02, + "learning_rate": 2.17495281266645e-05, + "loss": 3.881, + "step": 1725440 + }, + { + "epoch": 0.02, + "learning_rate": 2.174115855795771e-05, + "loss": 3.879, + "step": 1725952 + }, + { + "epoch": 0.02, + "learning_rate": 2.173277261044719e-05, + "loss": 3.8881, + "step": 1726464 + }, + { + "epoch": 0.02, + "learning_rate": 2.172438666293667e-05, + "loss": 3.893, + "step": 1726976 + }, + { + "epoch": 0.02, + "learning_rate": 2.1716017094229878e-05, + "loss": 3.9017, + "step": 1727488 + }, + { + "epoch": 0.02, + "learning_rate": 2.170763114671936e-05, + "loss": 3.8849, + "step": 1728000 + }, + { + "epoch": 0.02, + "learning_rate": 2.169924519920884e-05, + "loss": 3.8819, + "step": 1728512 + }, + { + "epoch": 0.02, + "learning_rate": 2.169085925169832e-05, + "loss": 3.8897, + "step": 1729024 + }, + { + "epoch": 0.02, + "learning_rate": 2.16824733041878e-05, + "loss": 3.8864, + "step": 1729536 + }, + { + "epoch": 0.02, + "learning_rate": 2.1674087356677277e-05, + "loss": 3.8945, + "step": 1730048 + }, + { + "epoch": 0.02, + "learning_rate": 2.1665701409166757e-05, + "loss": 3.8835, + "step": 1730560 + }, + { + "epoch": 0.02, + "learning_rate": 2.1657315461656237e-05, + "loss": 3.8842, + "step": 1731072 + }, + { + "epoch": 0.02, + "learning_rate": 2.1648929514145717e-05, + "loss": 3.8879, + "step": 1731584 + }, + { + "epoch": 0.02, + "learning_rate": 2.16405435666352e-05, + "loss": 3.8984, + "step": 1732096 + }, + { + "epoch": 0.02, + "learning_rate": 2.163217399792841e-05, + "loss": 3.8704, + "step": 1732608 + }, + { + "epoch": 0.02, + "learning_rate": 2.162378805041789e-05, + "loss": 3.8874, + "step": 1733120 + }, + { + "epoch": 0.02, + "learning_rate": 2.16154184817111e-05, + "loss": 3.8864, + "step": 1733632 + }, + { + "epoch": 0.02, + "learning_rate": 2.160703253420058e-05, + "loss": 3.892, + "step": 1734144 + }, + { + "epoch": 0.02, + "learning_rate": 2.1598646586690062e-05, + "loss": 3.8736, + "step": 1734656 + }, + { + "epoch": 0.02, + "learning_rate": 2.1590260639179542e-05, + "loss": 3.8909, + "step": 1735168 + }, + { + "epoch": 0.02, + "learning_rate": 2.1581874691669022e-05, + "loss": 3.8844, + "step": 1735680 + }, + { + "epoch": 0.02, + "learning_rate": 2.1573488744158502e-05, + "loss": 3.8851, + "step": 1736192 + }, + { + "epoch": 0.02, + "learning_rate": 2.1565102796647982e-05, + "loss": 3.8917, + "step": 1736704 + }, + { + "epoch": 0.02, + "learning_rate": 2.155671684913746e-05, + "loss": 3.8812, + "step": 1737216 + }, + { + "epoch": 0.02, + "learning_rate": 2.154834728043067e-05, + "loss": 3.8855, + "step": 1737728 + }, + { + "epoch": 0.02, + "learning_rate": 2.1539961332920154e-05, + "loss": 3.9052, + "step": 1738240 + }, + { + "epoch": 0.02, + "learning_rate": 2.153157538540963e-05, + "loss": 3.8875, + "step": 1738752 + }, + { + "epoch": 0.02, + "learning_rate": 2.152318943789911e-05, + "loss": 3.883, + "step": 1739264 + }, + { + "epoch": 0.02, + "learning_rate": 2.1514819869192323e-05, + "loss": 3.8955, + "step": 1739776 + }, + { + "epoch": 0.02, + "learning_rate": 2.1506450300485532e-05, + "loss": 3.8922, + "step": 1740288 + }, + { + "epoch": 0.02, + "learning_rate": 2.1498064352975016e-05, + "loss": 3.8753, + "step": 1740800 + }, + { + "epoch": 0.02, + "learning_rate": 2.1489678405464496e-05, + "loss": 3.8904, + "step": 1741312 + }, + { + "epoch": 0.02, + "learning_rate": 2.1481292457953976e-05, + "loss": 3.8803, + "step": 1741824 + }, + { + "epoch": 0.02, + "learning_rate": 2.1472906510443456e-05, + "loss": 3.8819, + "step": 1742336 + }, + { + "epoch": 0.02, + "learning_rate": 2.1464520562932932e-05, + "loss": 3.8858, + "step": 1742848 + }, + { + "epoch": 0.02, + "learning_rate": 2.1456134615422412e-05, + "loss": 3.8844, + "step": 1743360 + }, + { + "epoch": 0.02, + "learning_rate": 2.1447765046715625e-05, + "loss": 3.8833, + "step": 1743872 + }, + { + "epoch": 0.02, + "learning_rate": 2.1439379099205105e-05, + "loss": 3.8808, + "step": 1744384 + }, + { + "epoch": 0.02, + "learning_rate": 2.1430993151694585e-05, + "loss": 3.8823, + "step": 1744896 + }, + { + "epoch": 0.02, + "learning_rate": 2.1422607204184064e-05, + "loss": 3.8987, + "step": 1745408 + }, + { + "epoch": 0.02, + "learning_rate": 2.1414221256673544e-05, + "loss": 3.8883, + "step": 1745920 + }, + { + "epoch": 0.02, + "learning_rate": 2.1405851687966754e-05, + "loss": 3.8934, + "step": 1746432 + }, + { + "epoch": 0.02, + "learning_rate": 2.1397465740456233e-05, + "loss": 3.8762, + "step": 1746944 + }, + { + "epoch": 0.02, + "learning_rate": 2.1389079792945717e-05, + "loss": 3.9005, + "step": 1747456 + }, + { + "epoch": 0.02, + "learning_rate": 2.1380693845435197e-05, + "loss": 3.8914, + "step": 1747968 + }, + { + "epoch": 0.02, + "learning_rate": 2.1372307897924677e-05, + "loss": 3.8908, + "step": 1748480 + }, + { + "epoch": 0.02, + "learning_rate": 2.1363938329217886e-05, + "loss": 3.8874, + "step": 1748992 + }, + { + "epoch": 0.02, + "learning_rate": 2.1355552381707366e-05, + "loss": 3.893, + "step": 1749504 + }, + { + "epoch": 0.02, + "learning_rate": 2.1347166434196846e-05, + "loss": 3.8834, + "step": 1750016 + }, + { + "epoch": 0.02, + "learning_rate": 2.1338780486686326e-05, + "loss": 3.9032, + "step": 1750528 + }, + { + "epoch": 0.02, + "learning_rate": 2.133039453917581e-05, + "loss": 3.8744, + "step": 1751040 + }, + { + "epoch": 0.02, + "learning_rate": 2.1322008591665286e-05, + "loss": 3.8936, + "step": 1751552 + }, + { + "epoch": 0.02, + "learning_rate": 2.1313622644154766e-05, + "loss": 3.8815, + "step": 1752064 + }, + { + "epoch": 0.02, + "learning_rate": 2.1305236696644246e-05, + "loss": 3.8837, + "step": 1752576 + }, + { + "epoch": 0.02, + "learning_rate": 2.1296867127937458e-05, + "loss": 3.8862, + "step": 1753088 + }, + { + "epoch": 0.02, + "learning_rate": 2.1288481180426938e-05, + "loss": 3.8861, + "step": 1753600 + }, + { + "epoch": 0.02, + "learning_rate": 2.1280095232916418e-05, + "loss": 3.8975, + "step": 1754112 + }, + { + "epoch": 0.02, + "learning_rate": 2.1271709285405898e-05, + "loss": 3.8767, + "step": 1754624 + }, + { + "epoch": 0.02, + "learning_rate": 2.126333971669911e-05, + "loss": 3.8911, + "step": 1755136 + }, + { + "epoch": 0.03, + "eval_loss": 3.985900640487671, + "eval_runtime": 290.955, + "eval_samples_per_second": 1311.512, + "eval_steps_per_second": 40.986, + "step": 1755360 + }, + { + "epoch": 1.0, + "learning_rate": 2.1254953769188587e-05, + "loss": 3.8905, + "step": 1755648 + }, + { + "epoch": 1.0, + "learning_rate": 2.1246567821678067e-05, + "loss": 3.8809, + "step": 1756160 + }, + { + "epoch": 1.0, + "learning_rate": 2.1238181874167547e-05, + "loss": 3.8928, + "step": 1756672 + }, + { + "epoch": 1.0, + "learning_rate": 2.122981230546076e-05, + "loss": 3.8875, + "step": 1757184 + }, + { + "epoch": 1.0, + "learning_rate": 2.122142635795024e-05, + "loss": 3.8927, + "step": 1757696 + }, + { + "epoch": 1.0, + "learning_rate": 2.121304041043972e-05, + "loss": 3.8835, + "step": 1758208 + }, + { + "epoch": 1.0, + "learning_rate": 2.12046544629292e-05, + "loss": 3.8873, + "step": 1758720 + }, + { + "epoch": 1.0, + "learning_rate": 2.1196284894222408e-05, + "loss": 3.8817, + "step": 1759232 + }, + { + "epoch": 1.0, + "learning_rate": 2.1187898946711888e-05, + "loss": 3.8898, + "step": 1759744 + }, + { + "epoch": 1.0, + "learning_rate": 2.117951299920137e-05, + "loss": 3.8921, + "step": 1760256 + }, + { + "epoch": 1.0, + "learning_rate": 2.117112705169085e-05, + "loss": 3.8905, + "step": 1760768 + }, + { + "epoch": 1.0, + "learning_rate": 2.116275748298406e-05, + "loss": 3.8865, + "step": 1761280 + }, + { + "epoch": 1.0, + "learning_rate": 2.1154387914277273e-05, + "loss": 3.886, + "step": 1761792 + }, + { + "epoch": 1.0, + "learning_rate": 2.1146001966766753e-05, + "loss": 3.8832, + "step": 1762304 + }, + { + "epoch": 1.0, + "learning_rate": 2.1137616019256233e-05, + "loss": 3.8889, + "step": 1762816 + }, + { + "epoch": 1.0, + "learning_rate": 2.1129230071745713e-05, + "loss": 3.8738, + "step": 1763328 + }, + { + "epoch": 1.0, + "learning_rate": 2.1120844124235193e-05, + "loss": 3.8854, + "step": 1763840 + }, + { + "epoch": 1.0, + "learning_rate": 2.1112458176724673e-05, + "loss": 3.8819, + "step": 1764352 + }, + { + "epoch": 1.0, + "learning_rate": 2.1104072229214153e-05, + "loss": 3.8835, + "step": 1764864 + }, + { + "epoch": 1.0, + "learning_rate": 2.1095686281703633e-05, + "loss": 3.896, + "step": 1765376 + }, + { + "epoch": 1.0, + "learning_rate": 2.1087300334193113e-05, + "loss": 3.8956, + "step": 1765888 + }, + { + "epoch": 1.0, + "learning_rate": 2.1078914386682593e-05, + "loss": 3.8949, + "step": 1766400 + }, + { + "epoch": 1.0, + "learning_rate": 2.1070528439172073e-05, + "loss": 3.8894, + "step": 1766912 + }, + { + "epoch": 1.0, + "learning_rate": 2.1062142491661553e-05, + "loss": 3.8899, + "step": 1767424 + }, + { + "epoch": 1.0, + "learning_rate": 2.1053772922954765e-05, + "loss": 3.8779, + "step": 1767936 + }, + { + "epoch": 1.0, + "learning_rate": 2.104538697544424e-05, + "loss": 3.8959, + "step": 1768448 + }, + { + "epoch": 1.0, + "learning_rate": 2.1037017406737454e-05, + "loss": 3.8809, + "step": 1768960 + }, + { + "epoch": 1.0, + "learning_rate": 2.1028631459226934e-05, + "loss": 3.8778, + "step": 1769472 + }, + { + "epoch": 1.0, + "learning_rate": 2.1020245511716414e-05, + "loss": 3.8815, + "step": 1769984 + }, + { + "epoch": 1.0, + "learning_rate": 2.1011859564205894e-05, + "loss": 3.8845, + "step": 1770496 + }, + { + "epoch": 1.01, + "learning_rate": 2.1003473616695374e-05, + "loss": 3.8844, + "step": 1771008 + }, + { + "epoch": 1.01, + "learning_rate": 2.0995104047988586e-05, + "loss": 3.8932, + "step": 1771520 + }, + { + "epoch": 1.01, + "learning_rate": 2.0986718100478063e-05, + "loss": 3.8931, + "step": 1772032 + }, + { + "epoch": 1.01, + "learning_rate": 2.0978332152967546e-05, + "loss": 3.8844, + "step": 1772544 + }, + { + "epoch": 1.01, + "learning_rate": 2.096996258426076e-05, + "loss": 3.8792, + "step": 1773056 + }, + { + "epoch": 1.01, + "learning_rate": 2.0961576636750235e-05, + "loss": 3.8911, + "step": 1773568 + }, + { + "epoch": 1.01, + "learning_rate": 2.0953190689239715e-05, + "loss": 3.8866, + "step": 1774080 + }, + { + "epoch": 1.01, + "learning_rate": 2.0944804741729195e-05, + "loss": 3.881, + "step": 1774592 + }, + { + "epoch": 1.01, + "learning_rate": 2.0936418794218675e-05, + "loss": 3.8836, + "step": 1775104 + }, + { + "epoch": 1.01, + "learning_rate": 2.0928032846708155e-05, + "loss": 3.8748, + "step": 1775616 + }, + { + "epoch": 1.01, + "learning_rate": 2.0919646899197635e-05, + "loss": 3.8812, + "step": 1776128 + }, + { + "epoch": 1.01, + "learning_rate": 2.091126095168712e-05, + "loss": 3.8945, + "step": 1776640 + }, + { + "epoch": 1.01, + "learning_rate": 2.0902891382980328e-05, + "loss": 3.8891, + "step": 1777152 + }, + { + "epoch": 1.01, + "learning_rate": 2.0894505435469808e-05, + "loss": 3.8811, + "step": 1777664 + }, + { + "epoch": 1.01, + "learning_rate": 2.0886119487959288e-05, + "loss": 3.8899, + "step": 1778176 + }, + { + "epoch": 1.01, + "learning_rate": 2.0877733540448768e-05, + "loss": 3.878, + "step": 1778688 + }, + { + "epoch": 1.01, + "learning_rate": 2.0869347592938247e-05, + "loss": 3.8918, + "step": 1779200 + }, + { + "epoch": 1.01, + "learning_rate": 2.0860961645427727e-05, + "loss": 3.8828, + "step": 1779712 + }, + { + "epoch": 1.01, + "learning_rate": 2.0852575697917207e-05, + "loss": 3.8627, + "step": 1780224 + }, + { + "epoch": 1.01, + "learning_rate": 2.0844189750406687e-05, + "loss": 3.8909, + "step": 1780736 + }, + { + "epoch": 1.01, + "learning_rate": 2.0835803802896167e-05, + "loss": 3.885, + "step": 1781248 + }, + { + "epoch": 1.01, + "learning_rate": 2.0827417855385647e-05, + "loss": 3.8876, + "step": 1781760 + }, + { + "epoch": 1.01, + "learning_rate": 2.0819031907875124e-05, + "loss": 3.8774, + "step": 1782272 + }, + { + "epoch": 1.01, + "learning_rate": 2.0810645960364604e-05, + "loss": 3.8776, + "step": 1782784 + }, + { + "epoch": 1.01, + "learning_rate": 2.080227639165782e-05, + "loss": 3.8756, + "step": 1783296 + }, + { + "epoch": 1.01, + "learning_rate": 2.07938904441473e-05, + "loss": 3.8763, + "step": 1783808 + }, + { + "epoch": 1.01, + "learning_rate": 2.078552087544051e-05, + "loss": 3.8789, + "step": 1784320 + }, + { + "epoch": 1.01, + "learning_rate": 2.077713492792999e-05, + "loss": 3.8797, + "step": 1784832 + }, + { + "epoch": 1.01, + "learning_rate": 2.076874898041947e-05, + "loss": 3.892, + "step": 1785344 + }, + { + "epoch": 1.01, + "learning_rate": 2.076036303290895e-05, + "loss": 3.8756, + "step": 1785856 + }, + { + "epoch": 1.01, + "learning_rate": 2.075197708539843e-05, + "loss": 3.8798, + "step": 1786368 + }, + { + "epoch": 1.01, + "learning_rate": 2.074359113788791e-05, + "loss": 3.8933, + "step": 1786880 + }, + { + "epoch": 1.01, + "learning_rate": 2.073520519037739e-05, + "loss": 3.8674, + "step": 1787392 + }, + { + "epoch": 1.01, + "learning_rate": 2.072681924286687e-05, + "loss": 3.8681, + "step": 1787904 + }, + { + "epoch": 1.01, + "learning_rate": 2.0718449674160077e-05, + "loss": 3.8898, + "step": 1788416 + }, + { + "epoch": 1.01, + "learning_rate": 2.0710063726649557e-05, + "loss": 3.8858, + "step": 1788928 + }, + { + "epoch": 1.01, + "learning_rate": 2.0701694157942773e-05, + "loss": 3.8739, + "step": 1789440 + }, + { + "epoch": 1.01, + "learning_rate": 2.069330821043225e-05, + "loss": 3.8773, + "step": 1789952 + }, + { + "epoch": 1.01, + "learning_rate": 2.068492226292173e-05, + "loss": 3.8659, + "step": 1790464 + }, + { + "epoch": 1.01, + "learning_rate": 2.067653631541121e-05, + "loss": 3.8858, + "step": 1790976 + }, + { + "epoch": 1.01, + "learning_rate": 2.066815036790069e-05, + "loss": 3.8885, + "step": 1791488 + }, + { + "epoch": 1.01, + "learning_rate": 2.065976442039017e-05, + "loss": 3.8841, + "step": 1792000 + }, + { + "epoch": 1.01, + "learning_rate": 2.065137847287965e-05, + "loss": 3.8833, + "step": 1792512 + }, + { + "epoch": 1.01, + "learning_rate": 2.0643008904172862e-05, + "loss": 3.8915, + "step": 1793024 + }, + { + "epoch": 1.01, + "learning_rate": 2.0634622956662342e-05, + "loss": 3.9051, + "step": 1793536 + }, + { + "epoch": 1.01, + "learning_rate": 2.0626237009151822e-05, + "loss": 3.8744, + "step": 1794048 + }, + { + "epoch": 1.01, + "learning_rate": 2.0617851061641302e-05, + "loss": 3.8803, + "step": 1794560 + }, + { + "epoch": 1.01, + "learning_rate": 2.060948149293451e-05, + "loss": 3.8914, + "step": 1795072 + }, + { + "epoch": 1.01, + "learning_rate": 2.0601095545423994e-05, + "loss": 3.8724, + "step": 1795584 + }, + { + "epoch": 1.01, + "learning_rate": 2.0592725976717204e-05, + "loss": 3.8839, + "step": 1796096 + }, + { + "epoch": 1.01, + "learning_rate": 2.0584340029206684e-05, + "loss": 3.8873, + "step": 1796608 + }, + { + "epoch": 1.01, + "learning_rate": 2.0575954081696163e-05, + "loss": 3.8883, + "step": 1797120 + }, + { + "epoch": 1.01, + "learning_rate": 2.0567568134185643e-05, + "loss": 3.8932, + "step": 1797632 + }, + { + "epoch": 1.01, + "learning_rate": 2.0559182186675123e-05, + "loss": 3.8731, + "step": 1798144 + }, + { + "epoch": 1.01, + "learning_rate": 2.0550796239164603e-05, + "loss": 3.8796, + "step": 1798656 + }, + { + "epoch": 1.01, + "learning_rate": 2.0542410291654083e-05, + "loss": 3.8759, + "step": 1799168 + }, + { + "epoch": 1.01, + "learning_rate": 2.0534024344143563e-05, + "loss": 3.8837, + "step": 1799680 + }, + { + "epoch": 1.01, + "learning_rate": 2.0525638396633043e-05, + "loss": 3.8865, + "step": 1800192 + }, + { + "epoch": 1.01, + "learning_rate": 2.0517268827926252e-05, + "loss": 3.8756, + "step": 1800704 + }, + { + "epoch": 1.02, + "learning_rate": 2.0508882880415732e-05, + "loss": 3.8843, + "step": 1801216 + }, + { + "epoch": 1.02, + "learning_rate": 2.0500496932905212e-05, + "loss": 3.8788, + "step": 1801728 + }, + { + "epoch": 1.02, + "learning_rate": 2.0492110985394696e-05, + "loss": 3.8735, + "step": 1802240 + }, + { + "epoch": 1.02, + "learning_rate": 2.0483725037884175e-05, + "loss": 3.8813, + "step": 1802752 + }, + { + "epoch": 1.02, + "learning_rate": 2.0475339090373655e-05, + "loss": 3.8886, + "step": 1803264 + }, + { + "epoch": 1.02, + "learning_rate": 2.0466953142863135e-05, + "loss": 3.8944, + "step": 1803776 + }, + { + "epoch": 1.02, + "learning_rate": 2.0458567195352612e-05, + "loss": 3.8846, + "step": 1804288 + }, + { + "epoch": 1.02, + "learning_rate": 2.0450197626645824e-05, + "loss": 3.8727, + "step": 1804800 + }, + { + "epoch": 1.02, + "learning_rate": 2.0441811679135304e-05, + "loss": 3.8852, + "step": 1805312 + }, + { + "epoch": 1.02, + "learning_rate": 2.0433425731624788e-05, + "loss": 3.8797, + "step": 1805824 + }, + { + "epoch": 1.02, + "learning_rate": 2.0425039784114264e-05, + "loss": 3.8861, + "step": 1806336 + }, + { + "epoch": 1.02, + "learning_rate": 2.0416670215407477e-05, + "loss": 3.8807, + "step": 1806848 + }, + { + "epoch": 1.02, + "learning_rate": 2.0408284267896957e-05, + "loss": 3.8789, + "step": 1807360 + }, + { + "epoch": 1.02, + "learning_rate": 2.0399898320386433e-05, + "loss": 3.8794, + "step": 1807872 + }, + { + "epoch": 1.02, + "learning_rate": 2.0391512372875913e-05, + "loss": 3.8941, + "step": 1808384 + }, + { + "epoch": 1.02, + "learning_rate": 2.0383126425365397e-05, + "loss": 3.8669, + "step": 1808896 + }, + { + "epoch": 1.02, + "learning_rate": 2.0374740477854877e-05, + "loss": 3.8808, + "step": 1809408 + }, + { + "epoch": 1.02, + "learning_rate": 2.0366370909148086e-05, + "loss": 3.877, + "step": 1809920 + }, + { + "epoch": 1.02, + "learning_rate": 2.0357984961637566e-05, + "loss": 3.8844, + "step": 1810432 + }, + { + "epoch": 1.02, + "learning_rate": 2.0349599014127046e-05, + "loss": 3.8729, + "step": 1810944 + }, + { + "epoch": 1.02, + "learning_rate": 2.0341213066616526e-05, + "loss": 3.8853, + "step": 1811456 + }, + { + "epoch": 1.02, + "learning_rate": 2.0332827119106006e-05, + "loss": 3.8729, + "step": 1811968 + }, + { + "epoch": 1.02, + "learning_rate": 2.032444117159549e-05, + "loss": 3.8833, + "step": 1812480 + }, + { + "epoch": 1.02, + "learning_rate": 2.0316055224084965e-05, + "loss": 3.8869, + "step": 1812992 + }, + { + "epoch": 1.02, + "learning_rate": 2.0307669276574445e-05, + "loss": 3.8708, + "step": 1813504 + }, + { + "epoch": 1.02, + "learning_rate": 2.0299299707867658e-05, + "loss": 3.8787, + "step": 1814016 + }, + { + "epoch": 1.02, + "learning_rate": 2.0290913760357138e-05, + "loss": 3.8979, + "step": 1814528 + }, + { + "epoch": 1.02, + "learning_rate": 2.0282527812846618e-05, + "loss": 3.8845, + "step": 1815040 + }, + { + "epoch": 1.02, + "learning_rate": 2.0274141865336098e-05, + "loss": 3.8791, + "step": 1815552 + }, + { + "epoch": 1.02, + "learning_rate": 2.026577229662931e-05, + "loss": 3.8846, + "step": 1816064 + }, + { + "epoch": 1.02, + "learning_rate": 2.025738634911879e-05, + "loss": 3.8895, + "step": 1816576 + }, + { + "epoch": 1.02, + "learning_rate": 2.0249016780412e-05, + "loss": 3.8744, + "step": 1817088 + }, + { + "epoch": 1.02, + "learning_rate": 2.024063083290148e-05, + "loss": 3.8844, + "step": 1817600 + }, + { + "epoch": 1.02, + "learning_rate": 2.023224488539096e-05, + "loss": 3.8708, + "step": 1818112 + }, + { + "epoch": 1.02, + "learning_rate": 2.022387531668417e-05, + "loss": 3.8777, + "step": 1818624 + }, + { + "epoch": 1.02, + "learning_rate": 2.021548936917365e-05, + "loss": 3.8764, + "step": 1819136 + }, + { + "epoch": 1.02, + "learning_rate": 2.020710342166313e-05, + "loss": 3.8792, + "step": 1819648 + }, + { + "epoch": 1.02, + "learning_rate": 2.019871747415261e-05, + "loss": 3.8772, + "step": 1820160 + }, + { + "epoch": 1.02, + "learning_rate": 2.0190331526642088e-05, + "loss": 3.8771, + "step": 1820672 + }, + { + "epoch": 1.02, + "learning_rate": 2.018194557913157e-05, + "loss": 3.8729, + "step": 1821184 + }, + { + "epoch": 1.02, + "learning_rate": 2.017355963162105e-05, + "loss": 3.8925, + "step": 1821696 + }, + { + "epoch": 1.02, + "learning_rate": 2.016517368411053e-05, + "loss": 3.8878, + "step": 1822208 + }, + { + "epoch": 1.02, + "learning_rate": 2.015678773660001e-05, + "loss": 3.8876, + "step": 1822720 + }, + { + "epoch": 1.02, + "learning_rate": 2.014841816789322e-05, + "loss": 3.8702, + "step": 1823232 + }, + { + "epoch": 1.02, + "learning_rate": 2.01400322203827e-05, + "loss": 3.8969, + "step": 1823744 + }, + { + "epoch": 1.02, + "learning_rate": 2.013164627287218e-05, + "loss": 3.8829, + "step": 1824256 + }, + { + "epoch": 1.02, + "learning_rate": 2.012326032536166e-05, + "loss": 3.8848, + "step": 1824768 + }, + { + "epoch": 1.02, + "learning_rate": 2.0114874377851144e-05, + "loss": 3.8857, + "step": 1825280 + }, + { + "epoch": 1.02, + "learning_rate": 2.010648843034062e-05, + "loss": 3.8837, + "step": 1825792 + }, + { + "epoch": 1.02, + "learning_rate": 2.0098118861633833e-05, + "loss": 3.8793, + "step": 1826304 + }, + { + "epoch": 1.02, + "learning_rate": 2.0089732914123313e-05, + "loss": 3.8959, + "step": 1826816 + }, + { + "epoch": 1.02, + "learning_rate": 2.0081346966612793e-05, + "loss": 3.8712, + "step": 1827328 + }, + { + "epoch": 1.02, + "learning_rate": 2.0072961019102273e-05, + "loss": 3.8877, + "step": 1827840 + }, + { + "epoch": 1.02, + "learning_rate": 2.0064575071591752e-05, + "loss": 3.8763, + "step": 1828352 + }, + { + "epoch": 1.02, + "learning_rate": 2.0056189124081232e-05, + "loss": 3.8791, + "step": 1828864 + }, + { + "epoch": 1.02, + "learning_rate": 2.0047803176570712e-05, + "loss": 3.8794, + "step": 1829376 + }, + { + "epoch": 1.02, + "learning_rate": 2.0039417229060192e-05, + "loss": 3.8791, + "step": 1829888 + }, + { + "epoch": 1.02, + "learning_rate": 2.00310476603534e-05, + "loss": 3.8902, + "step": 1830400 + }, + { + "epoch": 1.02, + "learning_rate": 2.002266171284288e-05, + "loss": 3.8757, + "step": 1830912 + }, + { + "epoch": 1.02, + "learning_rate": 2.0014275765332365e-05, + "loss": 3.8831, + "step": 1831424 + }, + { + "epoch": 1.03, + "eval_loss": 3.98386549949646, + "eval_runtime": 291.6692, + "eval_samples_per_second": 1308.301, + "eval_steps_per_second": 40.885, + "step": 1831680 + }, + { + "epoch": 0.0, + "learning_rate": 2.0005889817821845e-05, + "loss": 3.8846, + "step": 1831936 + }, + { + "epoch": 0.0, + "learning_rate": 1.9997503870311325e-05, + "loss": 3.8787, + "step": 1832448 + }, + { + "epoch": 0.0, + "learning_rate": 1.99891179228008e-05, + "loss": 3.8812, + "step": 1832960 + }, + { + "epoch": 0.0, + "learning_rate": 1.998073197529028e-05, + "loss": 3.8786, + "step": 1833472 + }, + { + "epoch": 0.0, + "learning_rate": 1.997234602777976e-05, + "loss": 3.8911, + "step": 1833984 + }, + { + "epoch": 0.0, + "learning_rate": 1.996396008026924e-05, + "loss": 3.8777, + "step": 1834496 + }, + { + "epoch": 0.0, + "learning_rate": 1.995557413275872e-05, + "loss": 3.8839, + "step": 1835008 + }, + { + "epoch": 0.0, + "learning_rate": 1.9947188185248204e-05, + "loss": 3.8782, + "step": 1835520 + }, + { + "epoch": 0.0, + "learning_rate": 1.9938802237737684e-05, + "loss": 3.8807, + "step": 1836032 + }, + { + "epoch": 0.0, + "learning_rate": 1.993041629022716e-05, + "loss": 3.8882, + "step": 1836544 + }, + { + "epoch": 0.0, + "learning_rate": 1.992203034271664e-05, + "loss": 3.882, + "step": 1837056 + }, + { + "epoch": 0.0, + "learning_rate": 1.991364439520612e-05, + "loss": 3.881, + "step": 1837568 + }, + { + "epoch": 0.0, + "learning_rate": 1.9905274826499333e-05, + "loss": 3.8869, + "step": 1838080 + }, + { + "epoch": 0.0, + "learning_rate": 1.9896888878988813e-05, + "loss": 3.8707, + "step": 1838592 + }, + { + "epoch": 0.0, + "learning_rate": 1.9888502931478293e-05, + "loss": 3.8804, + "step": 1839104 + }, + { + "epoch": 0.0, + "learning_rate": 1.9880116983967773e-05, + "loss": 3.8711, + "step": 1839616 + }, + { + "epoch": 0.0, + "learning_rate": 1.9871731036457253e-05, + "loss": 3.8816, + "step": 1840128 + }, + { + "epoch": 0.0, + "learning_rate": 1.9863345088946733e-05, + "loss": 3.8758, + "step": 1840640 + }, + { + "epoch": 0.0, + "learning_rate": 1.9854959141436213e-05, + "loss": 3.8741, + "step": 1841152 + }, + { + "epoch": 0.0, + "learning_rate": 1.984657319392569e-05, + "loss": 3.889, + "step": 1841664 + }, + { + "epoch": 0.0, + "learning_rate": 1.9838187246415173e-05, + "loss": 3.8936, + "step": 1842176 + }, + { + "epoch": 0.0, + "learning_rate": 1.9829801298904653e-05, + "loss": 3.8916, + "step": 1842688 + }, + { + "epoch": 0.0, + "learning_rate": 1.9821415351394133e-05, + "loss": 3.8804, + "step": 1843200 + }, + { + "epoch": 0.0, + "learning_rate": 1.9813029403883613e-05, + "loss": 3.8819, + "step": 1843712 + }, + { + "epoch": 0.0, + "learning_rate": 1.9804659835176822e-05, + "loss": 3.8766, + "step": 1844224 + }, + { + "epoch": 0.0, + "learning_rate": 1.9796273887666302e-05, + "loss": 3.8847, + "step": 1844736 + }, + { + "epoch": 0.0, + "learning_rate": 1.9787887940155782e-05, + "loss": 3.8809, + "step": 1845248 + }, + { + "epoch": 0.0, + "learning_rate": 1.9779501992645265e-05, + "loss": 3.8768, + "step": 1845760 + }, + { + "epoch": 0.0, + "learning_rate": 1.9771132423938474e-05, + "loss": 3.8738, + "step": 1846272 + }, + { + "epoch": 0.0, + "learning_rate": 1.9762746476427954e-05, + "loss": 3.8793, + "step": 1846784 + }, + { + "epoch": 0.01, + "learning_rate": 1.9754360528917434e-05, + "loss": 3.8732, + "step": 1847296 + }, + { + "epoch": 0.01, + "learning_rate": 1.9745974581406914e-05, + "loss": 3.8898, + "step": 1847808 + }, + { + "epoch": 0.01, + "learning_rate": 1.9737605012700127e-05, + "loss": 3.8842, + "step": 1848320 + }, + { + "epoch": 0.01, + "learning_rate": 1.9729219065189607e-05, + "loss": 3.8801, + "step": 1848832 + }, + { + "epoch": 0.01, + "learning_rate": 1.9720833117679087e-05, + "loss": 3.8746, + "step": 1849344 + }, + { + "epoch": 0.01, + "learning_rate": 1.9712479927776028e-05, + "loss": 3.8838, + "step": 1849856 + }, + { + "epoch": 0.01, + "learning_rate": 1.9704093980265508e-05, + "loss": 3.8808, + "step": 1850368 + }, + { + "epoch": 0.01, + "learning_rate": 1.9695708032754988e-05, + "loss": 3.8776, + "step": 1850880 + }, + { + "epoch": 0.01, + "learning_rate": 1.9687322085244468e-05, + "loss": 3.8774, + "step": 1851392 + }, + { + "epoch": 0.01, + "learning_rate": 1.9678936137733948e-05, + "loss": 3.8672, + "step": 1851904 + }, + { + "epoch": 0.01, + "learning_rate": 1.9670550190223428e-05, + "loss": 3.871, + "step": 1852416 + }, + { + "epoch": 0.01, + "learning_rate": 1.9662164242712908e-05, + "loss": 3.8882, + "step": 1852928 + }, + { + "epoch": 0.01, + "learning_rate": 1.9653778295202388e-05, + "loss": 3.8862, + "step": 1853440 + }, + { + "epoch": 0.01, + "learning_rate": 1.9645392347691868e-05, + "loss": 3.8706, + "step": 1853952 + }, + { + "epoch": 0.01, + "learning_rate": 1.9637006400181344e-05, + "loss": 3.8848, + "step": 1854464 + }, + { + "epoch": 0.01, + "learning_rate": 1.9628620452670828e-05, + "loss": 3.8718, + "step": 1854976 + }, + { + "epoch": 0.01, + "learning_rate": 1.962025088396404e-05, + "loss": 3.8855, + "step": 1855488 + }, + { + "epoch": 0.01, + "learning_rate": 1.961186493645352e-05, + "loss": 3.877, + "step": 1856000 + }, + { + "epoch": 0.01, + "learning_rate": 1.9603478988942997e-05, + "loss": 3.8518, + "step": 1856512 + }, + { + "epoch": 0.01, + "learning_rate": 1.9595093041432477e-05, + "loss": 3.8889, + "step": 1857024 + }, + { + "epoch": 0.01, + "learning_rate": 1.9586707093921957e-05, + "loss": 3.878, + "step": 1857536 + }, + { + "epoch": 0.01, + "learning_rate": 1.9578321146411437e-05, + "loss": 3.8818, + "step": 1858048 + }, + { + "epoch": 0.01, + "learning_rate": 1.956995157770465e-05, + "loss": 3.8739, + "step": 1858560 + }, + { + "epoch": 0.01, + "learning_rate": 1.956156563019413e-05, + "loss": 3.8732, + "step": 1859072 + }, + { + "epoch": 0.01, + "learning_rate": 1.955317968268361e-05, + "loss": 3.868, + "step": 1859584 + }, + { + "epoch": 0.01, + "learning_rate": 1.954479373517309e-05, + "loss": 3.8716, + "step": 1860096 + }, + { + "epoch": 0.01, + "learning_rate": 1.953640778766257e-05, + "loss": 3.8744, + "step": 1860608 + }, + { + "epoch": 0.01, + "learning_rate": 1.952802184015205e-05, + "loss": 3.8705, + "step": 1861120 + }, + { + "epoch": 0.01, + "learning_rate": 1.951963589264153e-05, + "loss": 3.8861, + "step": 1861632 + }, + { + "epoch": 0.01, + "learning_rate": 1.951124994513101e-05, + "loss": 3.8701, + "step": 1862144 + }, + { + "epoch": 0.01, + "learning_rate": 1.950288037642422e-05, + "loss": 3.875, + "step": 1862656 + }, + { + "epoch": 0.01, + "learning_rate": 1.94944944289137e-05, + "loss": 3.889, + "step": 1863168 + }, + { + "epoch": 0.01, + "learning_rate": 1.948612486020691e-05, + "loss": 3.8635, + "step": 1863680 + }, + { + "epoch": 0.01, + "learning_rate": 1.947773891269639e-05, + "loss": 3.8636, + "step": 1864192 + }, + { + "epoch": 0.01, + "learning_rate": 1.9469352965185874e-05, + "loss": 3.8819, + "step": 1864704 + }, + { + "epoch": 0.01, + "learning_rate": 1.946096701767535e-05, + "loss": 3.8802, + "step": 1865216 + }, + { + "epoch": 0.01, + "learning_rate": 1.945258107016483e-05, + "loss": 3.8705, + "step": 1865728 + }, + { + "epoch": 0.01, + "learning_rate": 1.944419512265431e-05, + "loss": 3.8705, + "step": 1866240 + }, + { + "epoch": 0.01, + "learning_rate": 1.943580917514379e-05, + "loss": 3.8654, + "step": 1866752 + }, + { + "epoch": 0.01, + "learning_rate": 1.942742322763327e-05, + "loss": 3.8766, + "step": 1867264 + }, + { + "epoch": 0.01, + "learning_rate": 1.941903728012275e-05, + "loss": 3.8819, + "step": 1867776 + }, + { + "epoch": 0.01, + "learning_rate": 1.9410667711415962e-05, + "loss": 3.8772, + "step": 1868288 + }, + { + "epoch": 0.01, + "learning_rate": 1.9402281763905442e-05, + "loss": 3.8805, + "step": 1868800 + }, + { + "epoch": 0.01, + "learning_rate": 1.9393895816394922e-05, + "loss": 3.8845, + "step": 1869312 + }, + { + "epoch": 0.01, + "learning_rate": 1.938552624768813e-05, + "loss": 3.8991, + "step": 1869824 + }, + { + "epoch": 0.01, + "learning_rate": 1.937714030017761e-05, + "loss": 3.8679, + "step": 1870336 + }, + { + "epoch": 0.01, + "learning_rate": 1.936875435266709e-05, + "loss": 3.8791, + "step": 1870848 + }, + { + "epoch": 0.01, + "learning_rate": 1.9360368405156575e-05, + "loss": 3.882, + "step": 1871360 + }, + { + "epoch": 0.01, + "learning_rate": 1.9351982457646055e-05, + "loss": 3.8693, + "step": 1871872 + }, + { + "epoch": 0.01, + "learning_rate": 1.934359651013553e-05, + "loss": 3.8735, + "step": 1872384 + }, + { + "epoch": 0.01, + "learning_rate": 1.933521056262501e-05, + "loss": 3.8863, + "step": 1872896 + }, + { + "epoch": 0.01, + "learning_rate": 1.932682461511449e-05, + "loss": 3.8809, + "step": 1873408 + }, + { + "epoch": 0.01, + "learning_rate": 1.931843866760397e-05, + "loss": 3.8866, + "step": 1873920 + }, + { + "epoch": 0.01, + "learning_rate": 1.9310069098897184e-05, + "loss": 3.8657, + "step": 1874432 + }, + { + "epoch": 0.01, + "learning_rate": 1.9301683151386664e-05, + "loss": 3.8716, + "step": 1874944 + }, + { + "epoch": 0.01, + "learning_rate": 1.9293297203876143e-05, + "loss": 3.8725, + "step": 1875456 + }, + { + "epoch": 0.01, + "learning_rate": 1.9284911256365623e-05, + "loss": 3.8793, + "step": 1875968 + }, + { + "epoch": 0.01, + "learning_rate": 1.9276541687658833e-05, + "loss": 3.8812, + "step": 1876480 + }, + { + "epoch": 0.01, + "learning_rate": 1.9268155740148312e-05, + "loss": 3.8723, + "step": 1876992 + }, + { + "epoch": 0.02, + "learning_rate": 1.9259769792637792e-05, + "loss": 3.8699, + "step": 1877504 + }, + { + "epoch": 0.02, + "learning_rate": 1.9251383845127276e-05, + "loss": 3.877, + "step": 1878016 + }, + { + "epoch": 0.02, + "learning_rate": 1.9242997897616756e-05, + "loss": 3.8675, + "step": 1878528 + }, + { + "epoch": 0.02, + "learning_rate": 1.9234628328909965e-05, + "loss": 3.8762, + "step": 1879040 + }, + { + "epoch": 0.02, + "learning_rate": 1.9226242381399445e-05, + "loss": 3.8846, + "step": 1879552 + }, + { + "epoch": 0.02, + "learning_rate": 1.9217856433888925e-05, + "loss": 3.8857, + "step": 1880064 + }, + { + "epoch": 0.02, + "learning_rate": 1.9209470486378405e-05, + "loss": 3.8762, + "step": 1880576 + }, + { + "epoch": 0.02, + "learning_rate": 1.920111729647535e-05, + "loss": 3.8697, + "step": 1881088 + }, + { + "epoch": 0.02, + "learning_rate": 1.919274772776856e-05, + "loss": 3.8785, + "step": 1881600 + }, + { + "epoch": 0.02, + "learning_rate": 1.918436178025804e-05, + "loss": 3.8741, + "step": 1882112 + }, + { + "epoch": 0.02, + "learning_rate": 1.917597583274752e-05, + "loss": 3.883, + "step": 1882624 + }, + { + "epoch": 0.02, + "learning_rate": 1.9167589885237e-05, + "loss": 3.8771, + "step": 1883136 + }, + { + "epoch": 0.02, + "learning_rate": 1.915920393772648e-05, + "loss": 3.8691, + "step": 1883648 + }, + { + "epoch": 0.02, + "learning_rate": 1.915081799021596e-05, + "loss": 3.8844, + "step": 1884160 + }, + { + "epoch": 0.02, + "learning_rate": 1.914243204270544e-05, + "loss": 3.8836, + "step": 1884672 + }, + { + "epoch": 0.02, + "learning_rate": 1.913404609519492e-05, + "loss": 3.8605, + "step": 1885184 + }, + { + "epoch": 0.02, + "learning_rate": 1.91256601476844e-05, + "loss": 3.8734, + "step": 1885696 + }, + { + "epoch": 0.02, + "learning_rate": 1.9117290578977608e-05, + "loss": 3.8687, + "step": 1886208 + }, + { + "epoch": 0.02, + "learning_rate": 1.910890463146709e-05, + "loss": 3.8823, + "step": 1886720 + }, + { + "epoch": 0.02, + "learning_rate": 1.910051868395657e-05, + "loss": 3.8654, + "step": 1887232 + }, + { + "epoch": 0.02, + "learning_rate": 1.909213273644605e-05, + "loss": 3.8813, + "step": 1887744 + }, + { + "epoch": 0.02, + "learning_rate": 1.908374678893553e-05, + "loss": 3.8673, + "step": 1888256 + }, + { + "epoch": 0.02, + "learning_rate": 1.9075360841425007e-05, + "loss": 3.8791, + "step": 1888768 + }, + { + "epoch": 0.02, + "learning_rate": 1.906699127271822e-05, + "loss": 3.8774, + "step": 1889280 + }, + { + "epoch": 0.02, + "learning_rate": 1.90586053252077e-05, + "loss": 3.87, + "step": 1889792 + }, + { + "epoch": 0.02, + "learning_rate": 1.9050219377697183e-05, + "loss": 3.8734, + "step": 1890304 + }, + { + "epoch": 0.02, + "learning_rate": 1.904183343018666e-05, + "loss": 3.8909, + "step": 1890816 + }, + { + "epoch": 0.02, + "learning_rate": 1.903344748267614e-05, + "loss": 3.8756, + "step": 1891328 + }, + { + "epoch": 0.02, + "learning_rate": 1.902506153516562e-05, + "loss": 3.8746, + "step": 1891840 + }, + { + "epoch": 0.02, + "learning_rate": 1.90166755876551e-05, + "loss": 3.8792, + "step": 1892352 + }, + { + "epoch": 0.02, + "learning_rate": 1.900830601894831e-05, + "loss": 3.8813, + "step": 1892864 + }, + { + "epoch": 0.02, + "learning_rate": 1.8999920071437792e-05, + "loss": 3.8743, + "step": 1893376 + }, + { + "epoch": 0.02, + "learning_rate": 1.8991534123927272e-05, + "loss": 3.8775, + "step": 1893888 + }, + { + "epoch": 0.02, + "learning_rate": 1.8983148176416752e-05, + "loss": 3.8661, + "step": 1894400 + }, + { + "epoch": 0.02, + "learning_rate": 1.8974762228906232e-05, + "loss": 3.8741, + "step": 1894912 + }, + { + "epoch": 0.02, + "learning_rate": 1.8966376281395712e-05, + "loss": 3.8702, + "step": 1895424 + }, + { + "epoch": 0.02, + "learning_rate": 1.895800671268892e-05, + "loss": 3.8743, + "step": 1895936 + }, + { + "epoch": 0.02, + "learning_rate": 1.89496207651784e-05, + "loss": 3.8696, + "step": 1896448 + }, + { + "epoch": 0.02, + "learning_rate": 1.8941234817667884e-05, + "loss": 3.8738, + "step": 1896960 + }, + { + "epoch": 0.02, + "learning_rate": 1.8932848870157364e-05, + "loss": 3.8676, + "step": 1897472 + }, + { + "epoch": 0.02, + "learning_rate": 1.892446292264684e-05, + "loss": 3.8902, + "step": 1897984 + }, + { + "epoch": 0.02, + "learning_rate": 1.8916093353940053e-05, + "loss": 3.8767, + "step": 1898496 + }, + { + "epoch": 0.02, + "learning_rate": 1.8907707406429533e-05, + "loss": 3.8858, + "step": 1899008 + }, + { + "epoch": 0.02, + "learning_rate": 1.8899321458919013e-05, + "loss": 3.8635, + "step": 1899520 + }, + { + "epoch": 0.02, + "learning_rate": 1.8890935511408493e-05, + "loss": 3.8927, + "step": 1900032 + }, + { + "epoch": 0.02, + "learning_rate": 1.8882549563897973e-05, + "loss": 3.8743, + "step": 1900544 + }, + { + "epoch": 0.02, + "learning_rate": 1.8874163616387453e-05, + "loss": 3.8816, + "step": 1901056 + }, + { + "epoch": 0.02, + "learning_rate": 1.8865777668876933e-05, + "loss": 3.8787, + "step": 1901568 + }, + { + "epoch": 0.02, + "learning_rate": 1.8857391721366413e-05, + "loss": 3.8747, + "step": 1902080 + }, + { + "epoch": 0.02, + "learning_rate": 1.8849022152659622e-05, + "loss": 3.8774, + "step": 1902592 + }, + { + "epoch": 0.02, + "learning_rate": 1.8840636205149105e-05, + "loss": 3.8912, + "step": 1903104 + }, + { + "epoch": 0.02, + "learning_rate": 1.8832250257638585e-05, + "loss": 3.8621, + "step": 1903616 + }, + { + "epoch": 0.02, + "learning_rate": 1.8823864310128065e-05, + "loss": 3.8859, + "step": 1904128 + }, + { + "epoch": 0.02, + "learning_rate": 1.8815478362617545e-05, + "loss": 3.8752, + "step": 1904640 + }, + { + "epoch": 0.02, + "learning_rate": 1.8807108793910754e-05, + "loss": 3.8669, + "step": 1905152 + }, + { + "epoch": 0.02, + "learning_rate": 1.8798739225203967e-05, + "loss": 3.8739, + "step": 1905664 + }, + { + "epoch": 0.02, + "learning_rate": 1.8790353277693447e-05, + "loss": 3.8741, + "step": 1906176 + }, + { + "epoch": 0.02, + "learning_rate": 1.8781967330182927e-05, + "loss": 3.8877, + "step": 1906688 + }, + { + "epoch": 0.02, + "learning_rate": 1.8773581382672407e-05, + "loss": 3.8728, + "step": 1907200 + }, + { + "epoch": 0.02, + "learning_rate": 1.8765195435161887e-05, + "loss": 3.8761, + "step": 1907712 + }, + { + "epoch": 0.03, + "eval_loss": 3.9819412231445312, + "eval_runtime": 297.4582, + "eval_samples_per_second": 1282.839, + "eval_steps_per_second": 40.09, + "step": 1908000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8756809487651367e-05, + "loss": 3.8744, + "step": 1908224 + }, + { + "epoch": 0.0, + "learning_rate": 1.8748423540140843e-05, + "loss": 3.8742, + "step": 1908736 + }, + { + "epoch": 0.0, + "learning_rate": 1.8740037592630323e-05, + "loss": 3.8738, + "step": 1909248 + }, + { + "epoch": 0.0, + "learning_rate": 1.8731651645119806e-05, + "loss": 3.8767, + "step": 1909760 + }, + { + "epoch": 0.0, + "learning_rate": 1.8723265697609286e-05, + "loss": 3.8877, + "step": 1910272 + }, + { + "epoch": 0.0, + "learning_rate": 1.8714879750098766e-05, + "loss": 3.87, + "step": 1910784 + }, + { + "epoch": 0.0, + "learning_rate": 1.8706493802588246e-05, + "loss": 3.8783, + "step": 1911296 + }, + { + "epoch": 0.0, + "learning_rate": 1.8698107855077726e-05, + "loss": 3.8723, + "step": 1911808 + }, + { + "epoch": 0.0, + "learning_rate": 1.8689721907567203e-05, + "loss": 3.8775, + "step": 1912320 + }, + { + "epoch": 0.0, + "learning_rate": 1.8681335960056683e-05, + "loss": 3.8832, + "step": 1912832 + }, + { + "epoch": 0.0, + "learning_rate": 1.8672950012546163e-05, + "loss": 3.8744, + "step": 1913344 + }, + { + "epoch": 0.0, + "learning_rate": 1.8664564065035646e-05, + "loss": 3.8754, + "step": 1913856 + }, + { + "epoch": 0.0, + "learning_rate": 1.8656194496328855e-05, + "loss": 3.8844, + "step": 1914368 + }, + { + "epoch": 0.0, + "learning_rate": 1.8647808548818335e-05, + "loss": 3.8626, + "step": 1914880 + }, + { + "epoch": 0.0, + "learning_rate": 1.8639422601307815e-05, + "loss": 3.8743, + "step": 1915392 + }, + { + "epoch": 0.0, + "learning_rate": 1.8631036653797295e-05, + "loss": 3.8639, + "step": 1915904 + }, + { + "epoch": 0.0, + "learning_rate": 1.8622650706286775e-05, + "loss": 3.8763, + "step": 1916416 + }, + { + "epoch": 0.0, + "learning_rate": 1.8614264758776255e-05, + "loss": 3.8701, + "step": 1916928 + }, + { + "epoch": 0.0, + "learning_rate": 1.8605878811265735e-05, + "loss": 3.8734, + "step": 1917440 + }, + { + "epoch": 0.0, + "learning_rate": 1.8597492863755215e-05, + "loss": 3.8847, + "step": 1917952 + }, + { + "epoch": 0.0, + "learning_rate": 1.8589123295048427e-05, + "loss": 3.8851, + "step": 1918464 + }, + { + "epoch": 0.0, + "learning_rate": 1.8580737347537907e-05, + "loss": 3.8851, + "step": 1918976 + }, + { + "epoch": 0.0, + "learning_rate": 1.8572351400027384e-05, + "loss": 3.8788, + "step": 1919488 + }, + { + "epoch": 0.0, + "learning_rate": 1.8563965452516864e-05, + "loss": 3.8728, + "step": 1920000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8555579505006347e-05, + "loss": 3.8684, + "step": 1920512 + }, + { + "epoch": 0.0, + "learning_rate": 1.8547193557495827e-05, + "loss": 3.8801, + "step": 1921024 + }, + { + "epoch": 0.0, + "learning_rate": 1.8538807609985307e-05, + "loss": 3.8753, + "step": 1921536 + }, + { + "epoch": 0.0, + "learning_rate": 1.8530421662474787e-05, + "loss": 3.8736, + "step": 1922048 + }, + { + "epoch": 0.0, + "learning_rate": 1.8522052093767996e-05, + "loss": 3.8683, + "step": 1922560 + }, + { + "epoch": 0.0, + "learning_rate": 1.8513666146257476e-05, + "loss": 3.8728, + "step": 1923072 + }, + { + "epoch": 0.01, + "learning_rate": 1.8505280198746956e-05, + "loss": 3.8668, + "step": 1923584 + }, + { + "epoch": 0.01, + "learning_rate": 1.849689425123644e-05, + "loss": 3.884, + "step": 1924096 + }, + { + "epoch": 0.01, + "learning_rate": 1.8488508303725916e-05, + "loss": 3.8819, + "step": 1924608 + }, + { + "epoch": 0.01, + "learning_rate": 1.8480122356215396e-05, + "loss": 3.8742, + "step": 1925120 + }, + { + "epoch": 0.01, + "learning_rate": 1.8471736408704876e-05, + "loss": 3.8701, + "step": 1925632 + }, + { + "epoch": 0.01, + "learning_rate": 1.846336683999809e-05, + "loss": 3.8737, + "step": 1926144 + }, + { + "epoch": 0.01, + "learning_rate": 1.84549972712913e-05, + "loss": 3.8783, + "step": 1926656 + }, + { + "epoch": 0.01, + "learning_rate": 1.844661132378078e-05, + "loss": 3.8719, + "step": 1927168 + }, + { + "epoch": 0.01, + "learning_rate": 1.843822537627026e-05, + "loss": 3.8734, + "step": 1927680 + }, + { + "epoch": 0.01, + "learning_rate": 1.8429839428759737e-05, + "loss": 3.8615, + "step": 1928192 + }, + { + "epoch": 0.01, + "learning_rate": 1.8421453481249217e-05, + "loss": 3.8691, + "step": 1928704 + }, + { + "epoch": 0.01, + "learning_rate": 1.8413067533738697e-05, + "loss": 3.8779, + "step": 1929216 + }, + { + "epoch": 0.01, + "learning_rate": 1.8404681586228177e-05, + "loss": 3.881, + "step": 1929728 + }, + { + "epoch": 0.01, + "learning_rate": 1.8396295638717657e-05, + "loss": 3.8719, + "step": 1930240 + }, + { + "epoch": 0.01, + "learning_rate": 1.838790969120714e-05, + "loss": 3.874, + "step": 1930752 + }, + { + "epoch": 0.01, + "learning_rate": 1.837952374369662e-05, + "loss": 3.8725, + "step": 1931264 + }, + { + "epoch": 0.01, + "learning_rate": 1.8371137796186097e-05, + "loss": 3.8766, + "step": 1931776 + }, + { + "epoch": 0.01, + "learning_rate": 1.8362751848675577e-05, + "loss": 3.8741, + "step": 1932288 + }, + { + "epoch": 0.01, + "learning_rate": 1.835438227996879e-05, + "loss": 3.8462, + "step": 1932800 + }, + { + "epoch": 0.01, + "learning_rate": 1.834599633245827e-05, + "loss": 3.8815, + "step": 1933312 + }, + { + "epoch": 0.01, + "learning_rate": 1.833761038494775e-05, + "loss": 3.8736, + "step": 1933824 + }, + { + "epoch": 0.01, + "learning_rate": 1.832922443743723e-05, + "loss": 3.8786, + "step": 1934336 + }, + { + "epoch": 0.01, + "learning_rate": 1.832083848992671e-05, + "loss": 3.8688, + "step": 1934848 + }, + { + "epoch": 0.01, + "learning_rate": 1.831245254241619e-05, + "loss": 3.8655, + "step": 1935360 + }, + { + "epoch": 0.01, + "learning_rate": 1.830406659490567e-05, + "loss": 3.8643, + "step": 1935872 + }, + { + "epoch": 0.01, + "learning_rate": 1.8295697026198878e-05, + "loss": 3.8627, + "step": 1936384 + }, + { + "epoch": 0.01, + "learning_rate": 1.828731107868836e-05, + "loss": 3.8726, + "step": 1936896 + }, + { + "epoch": 0.01, + "learning_rate": 1.827892513117784e-05, + "loss": 3.8596, + "step": 1937408 + }, + { + "epoch": 0.01, + "learning_rate": 1.827053918366732e-05, + "loss": 3.8794, + "step": 1937920 + }, + { + "epoch": 0.01, + "learning_rate": 1.82621532361568e-05, + "loss": 3.8698, + "step": 1938432 + }, + { + "epoch": 0.01, + "learning_rate": 1.8253767288646278e-05, + "loss": 3.8648, + "step": 1938944 + }, + { + "epoch": 0.01, + "learning_rate": 1.8245381341135758e-05, + "loss": 3.8874, + "step": 1939456 + }, + { + "epoch": 0.01, + "learning_rate": 1.8236995393625238e-05, + "loss": 3.8572, + "step": 1939968 + }, + { + "epoch": 0.01, + "learning_rate": 1.8228642203722183e-05, + "loss": 3.8555, + "step": 1940480 + }, + { + "epoch": 0.01, + "learning_rate": 1.8220256256211663e-05, + "loss": 3.8791, + "step": 1940992 + }, + { + "epoch": 0.01, + "learning_rate": 1.8211870308701143e-05, + "loss": 3.8739, + "step": 1941504 + }, + { + "epoch": 0.01, + "learning_rate": 1.8203484361190623e-05, + "loss": 3.8646, + "step": 1942016 + }, + { + "epoch": 0.01, + "learning_rate": 1.81950984136801e-05, + "loss": 3.8667, + "step": 1942528 + }, + { + "epoch": 0.01, + "learning_rate": 1.818671246616958e-05, + "loss": 3.8534, + "step": 1943040 + }, + { + "epoch": 0.01, + "learning_rate": 1.8178326518659063e-05, + "loss": 3.8742, + "step": 1943552 + }, + { + "epoch": 0.01, + "learning_rate": 1.8169940571148543e-05, + "loss": 3.875, + "step": 1944064 + }, + { + "epoch": 0.01, + "learning_rate": 1.8161571002441752e-05, + "loss": 3.8761, + "step": 1944576 + }, + { + "epoch": 0.01, + "learning_rate": 1.8153185054931232e-05, + "loss": 3.8729, + "step": 1945088 + }, + { + "epoch": 0.01, + "learning_rate": 1.814479910742071e-05, + "loss": 3.8772, + "step": 1945600 + }, + { + "epoch": 0.01, + "learning_rate": 1.8136429538713924e-05, + "loss": 3.8938, + "step": 1946112 + }, + { + "epoch": 0.01, + "learning_rate": 1.8128043591203404e-05, + "loss": 3.8668, + "step": 1946624 + }, + { + "epoch": 0.01, + "learning_rate": 1.8119657643692884e-05, + "loss": 3.8783, + "step": 1947136 + }, + { + "epoch": 0.01, + "learning_rate": 1.8111271696182364e-05, + "loss": 3.8729, + "step": 1947648 + }, + { + "epoch": 0.01, + "learning_rate": 1.8102885748671844e-05, + "loss": 3.8684, + "step": 1948160 + }, + { + "epoch": 0.01, + "learning_rate": 1.8094499801161324e-05, + "loss": 3.8653, + "step": 1948672 + }, + { + "epoch": 0.01, + "learning_rate": 1.8086130232454533e-05, + "loss": 3.8832, + "step": 1949184 + }, + { + "epoch": 0.01, + "learning_rate": 1.8077744284944016e-05, + "loss": 3.8754, + "step": 1949696 + }, + { + "epoch": 0.01, + "learning_rate": 1.8069358337433496e-05, + "loss": 3.8807, + "step": 1950208 + }, + { + "epoch": 0.01, + "learning_rate": 1.8060972389922976e-05, + "loss": 3.8612, + "step": 1950720 + }, + { + "epoch": 0.01, + "learning_rate": 1.8052586442412456e-05, + "loss": 3.8682, + "step": 1951232 + }, + { + "epoch": 0.01, + "learning_rate": 1.8044200494901933e-05, + "loss": 3.8688, + "step": 1951744 + }, + { + "epoch": 0.01, + "learning_rate": 1.8035814547391413e-05, + "loss": 3.8725, + "step": 1952256 + }, + { + "epoch": 0.01, + "learning_rate": 1.8027444978684625e-05, + "loss": 3.8748, + "step": 1952768 + }, + { + "epoch": 0.01, + "learning_rate": 1.8019059031174105e-05, + "loss": 3.8703, + "step": 1953280 + }, + { + "epoch": 0.02, + "learning_rate": 1.8010673083663585e-05, + "loss": 3.8602, + "step": 1953792 + }, + { + "epoch": 0.02, + "learning_rate": 1.8002287136153065e-05, + "loss": 3.8739, + "step": 1954304 + }, + { + "epoch": 0.02, + "learning_rate": 1.7993917567446278e-05, + "loss": 3.8656, + "step": 1954816 + }, + { + "epoch": 0.02, + "learning_rate": 1.7985531619935754e-05, + "loss": 3.8675, + "step": 1955328 + }, + { + "epoch": 0.02, + "learning_rate": 1.7977145672425234e-05, + "loss": 3.8781, + "step": 1955840 + }, + { + "epoch": 0.02, + "learning_rate": 1.7968759724914717e-05, + "loss": 3.882, + "step": 1956352 + }, + { + "epoch": 0.02, + "learning_rate": 1.7960373777404197e-05, + "loss": 3.8704, + "step": 1956864 + }, + { + "epoch": 0.02, + "learning_rate": 1.7952004208697407e-05, + "loss": 3.8665, + "step": 1957376 + }, + { + "epoch": 0.02, + "learning_rate": 1.7943618261186886e-05, + "loss": 3.8685, + "step": 1957888 + }, + { + "epoch": 0.02, + "learning_rate": 1.7935232313676366e-05, + "loss": 3.8686, + "step": 1958400 + }, + { + "epoch": 0.02, + "learning_rate": 1.7926846366165846e-05, + "loss": 3.8781, + "step": 1958912 + }, + { + "epoch": 0.02, + "learning_rate": 1.7918460418655326e-05, + "loss": 3.8704, + "step": 1959424 + }, + { + "epoch": 0.02, + "learning_rate": 1.791007447114481e-05, + "loss": 3.8664, + "step": 1959936 + }, + { + "epoch": 0.02, + "learning_rate": 1.7901688523634286e-05, + "loss": 3.8723, + "step": 1960448 + }, + { + "epoch": 0.02, + "learning_rate": 1.78933189549275e-05, + "loss": 3.8782, + "step": 1960960 + }, + { + "epoch": 0.02, + "learning_rate": 1.788493300741698e-05, + "loss": 3.8561, + "step": 1961472 + }, + { + "epoch": 0.02, + "learning_rate": 1.787654705990646e-05, + "loss": 3.8702, + "step": 1961984 + }, + { + "epoch": 0.02, + "learning_rate": 1.786816111239594e-05, + "loss": 3.8616, + "step": 1962496 + }, + { + "epoch": 0.02, + "learning_rate": 1.785977516488542e-05, + "loss": 3.8761, + "step": 1963008 + }, + { + "epoch": 0.02, + "learning_rate": 1.78513892173749e-05, + "loss": 3.8598, + "step": 1963520 + }, + { + "epoch": 0.02, + "learning_rate": 1.784300326986438e-05, + "loss": 3.8734, + "step": 1964032 + }, + { + "epoch": 0.02, + "learning_rate": 1.7834633701157588e-05, + "loss": 3.8592, + "step": 1964544 + }, + { + "epoch": 0.02, + "learning_rate": 1.7826247753647068e-05, + "loss": 3.8765, + "step": 1965056 + }, + { + "epoch": 0.02, + "learning_rate": 1.7817861806136547e-05, + "loss": 3.8712, + "step": 1965568 + }, + { + "epoch": 0.02, + "learning_rate": 1.7809475858626027e-05, + "loss": 3.8619, + "step": 1966080 + }, + { + "epoch": 0.02, + "learning_rate": 1.780108991111551e-05, + "loss": 3.8707, + "step": 1966592 + }, + { + "epoch": 0.02, + "learning_rate": 1.779272034240872e-05, + "loss": 3.8852, + "step": 1967104 + }, + { + "epoch": 0.02, + "learning_rate": 1.77843343948982e-05, + "loss": 3.8691, + "step": 1967616 + }, + { + "epoch": 0.02, + "learning_rate": 1.777594844738768e-05, + "loss": 3.8734, + "step": 1968128 + }, + { + "epoch": 0.02, + "learning_rate": 1.776756249987716e-05, + "loss": 3.8718, + "step": 1968640 + }, + { + "epoch": 0.02, + "learning_rate": 1.775917655236664e-05, + "loss": 3.8743, + "step": 1969152 + }, + { + "epoch": 0.02, + "learning_rate": 1.775079060485612e-05, + "loss": 3.8728, + "step": 1969664 + }, + { + "epoch": 0.02, + "learning_rate": 1.77424046573456e-05, + "loss": 3.8673, + "step": 1970176 + }, + { + "epoch": 0.02, + "learning_rate": 1.773401870983508e-05, + "loss": 3.8608, + "step": 1970688 + }, + { + "epoch": 0.02, + "learning_rate": 1.7725649141128292e-05, + "loss": 3.8676, + "step": 1971200 + }, + { + "epoch": 0.02, + "learning_rate": 1.771726319361777e-05, + "loss": 3.8677, + "step": 1971712 + }, + { + "epoch": 0.02, + "learning_rate": 1.770887724610725e-05, + "loss": 3.868, + "step": 1972224 + }, + { + "epoch": 0.02, + "learning_rate": 1.7700491298596732e-05, + "loss": 3.8673, + "step": 1972736 + }, + { + "epoch": 0.02, + "learning_rate": 1.769212172988994e-05, + "loss": 3.8684, + "step": 1973248 + }, + { + "epoch": 0.02, + "learning_rate": 1.7683752161183154e-05, + "loss": 3.8621, + "step": 1973760 + }, + { + "epoch": 0.02, + "learning_rate": 1.7675366213672633e-05, + "loss": 3.8825, + "step": 1974272 + }, + { + "epoch": 0.02, + "learning_rate": 1.7666980266162113e-05, + "loss": 3.8694, + "step": 1974784 + }, + { + "epoch": 0.02, + "learning_rate": 1.7658594318651593e-05, + "loss": 3.8783, + "step": 1975296 + }, + { + "epoch": 0.02, + "learning_rate": 1.7650224749944806e-05, + "loss": 3.8577, + "step": 1975808 + }, + { + "epoch": 0.02, + "learning_rate": 1.7641838802434286e-05, + "loss": 3.8843, + "step": 1976320 + }, + { + "epoch": 0.02, + "learning_rate": 1.7633452854923766e-05, + "loss": 3.8758, + "step": 1976832 + }, + { + "epoch": 0.02, + "learning_rate": 1.7625066907413242e-05, + "loss": 3.8751, + "step": 1977344 + }, + { + "epoch": 0.02, + "learning_rate": 1.7616697338706455e-05, + "loss": 3.871, + "step": 1977856 + }, + { + "epoch": 0.02, + "learning_rate": 1.7608327769999667e-05, + "loss": 3.8711, + "step": 1978368 + }, + { + "epoch": 0.02, + "learning_rate": 1.7599941822489147e-05, + "loss": 3.8729, + "step": 1978880 + }, + { + "epoch": 0.02, + "learning_rate": 1.7591555874978627e-05, + "loss": 3.885, + "step": 1979392 + }, + { + "epoch": 0.02, + "learning_rate": 1.7583169927468107e-05, + "loss": 3.8579, + "step": 1979904 + }, + { + "epoch": 0.02, + "learning_rate": 1.7574783979957587e-05, + "loss": 3.8778, + "step": 1980416 + }, + { + "epoch": 0.02, + "learning_rate": 1.7566398032447064e-05, + "loss": 3.8678, + "step": 1980928 + }, + { + "epoch": 0.02, + "learning_rate": 1.7558012084936547e-05, + "loss": 3.8663, + "step": 1981440 + }, + { + "epoch": 0.02, + "learning_rate": 1.7549626137426027e-05, + "loss": 3.87, + "step": 1981952 + }, + { + "epoch": 0.02, + "learning_rate": 1.7541240189915507e-05, + "loss": 3.8674, + "step": 1982464 + }, + { + "epoch": 0.02, + "learning_rate": 1.7532854242404987e-05, + "loss": 3.8765, + "step": 1982976 + }, + { + "epoch": 0.02, + "learning_rate": 1.7524484673698196e-05, + "loss": 3.8736, + "step": 1983488 + }, + { + "epoch": 0.02, + "learning_rate": 1.7516098726187676e-05, + "loss": 3.8693, + "step": 1984000 + }, + { + "epoch": 0.03, + "eval_loss": 3.98002290725708, + "eval_runtime": 289.8311, + "eval_samples_per_second": 1316.598, + "eval_steps_per_second": 41.145, + "step": 1984320 + }, + { + "epoch": 0.0, + "learning_rate": 1.7507712778677156e-05, + "loss": 3.8699, + "step": 1984512 + }, + { + "epoch": 0.0, + "learning_rate": 1.7499326831166636e-05, + "loss": 3.8685, + "step": 1985024 + }, + { + "epoch": 0.0, + "learning_rate": 1.749094088365612e-05, + "loss": 3.8684, + "step": 1985536 + }, + { + "epoch": 0.0, + "learning_rate": 1.7482554936145596e-05, + "loss": 3.8739, + "step": 1986048 + }, + { + "epoch": 0.0, + "learning_rate": 1.7474168988635076e-05, + "loss": 3.8797, + "step": 1986560 + }, + { + "epoch": 0.0, + "learning_rate": 1.7465783041124556e-05, + "loss": 3.8644, + "step": 1987072 + }, + { + "epoch": 0.0, + "learning_rate": 1.7457397093614036e-05, + "loss": 3.8716, + "step": 1987584 + }, + { + "epoch": 0.0, + "learning_rate": 1.7449011146103516e-05, + "loss": 3.8701, + "step": 1988096 + }, + { + "epoch": 0.0, + "learning_rate": 1.7440625198592996e-05, + "loss": 3.8693, + "step": 1988608 + }, + { + "epoch": 0.0, + "learning_rate": 1.743223925108248e-05, + "loss": 3.8746, + "step": 1989120 + }, + { + "epoch": 0.0, + "learning_rate": 1.7423853303571955e-05, + "loss": 3.8699, + "step": 1989632 + }, + { + "epoch": 0.0, + "learning_rate": 1.7415467356061435e-05, + "loss": 3.8737, + "step": 1990144 + }, + { + "epoch": 0.0, + "learning_rate": 1.7407097787354648e-05, + "loss": 3.8803, + "step": 1990656 + }, + { + "epoch": 0.0, + "learning_rate": 1.7398711839844124e-05, + "loss": 3.8592, + "step": 1991168 + }, + { + "epoch": 0.0, + "learning_rate": 1.7390325892333604e-05, + "loss": 3.8693, + "step": 1991680 + }, + { + "epoch": 0.0, + "learning_rate": 1.7381939944823088e-05, + "loss": 3.8573, + "step": 1992192 + }, + { + "epoch": 0.0, + "learning_rate": 1.7373553997312568e-05, + "loss": 3.8718, + "step": 1992704 + }, + { + "epoch": 0.0, + "learning_rate": 1.7365168049802048e-05, + "loss": 3.8663, + "step": 1993216 + }, + { + "epoch": 0.0, + "learning_rate": 1.7356798481095257e-05, + "loss": 3.8656, + "step": 1993728 + }, + { + "epoch": 0.0, + "learning_rate": 1.7348412533584737e-05, + "loss": 3.8769, + "step": 1994240 + }, + { + "epoch": 0.0, + "learning_rate": 1.7340026586074217e-05, + "loss": 3.8773, + "step": 1994752 + }, + { + "epoch": 0.0, + "learning_rate": 1.7331640638563697e-05, + "loss": 3.8758, + "step": 1995264 + }, + { + "epoch": 0.0, + "learning_rate": 1.732325469105318e-05, + "loss": 3.8769, + "step": 1995776 + }, + { + "epoch": 0.0, + "learning_rate": 1.731486874354266e-05, + "loss": 3.8677, + "step": 1996288 + }, + { + "epoch": 0.0, + "learning_rate": 1.7306482796032137e-05, + "loss": 3.8683, + "step": 1996800 + }, + { + "epoch": 0.0, + "learning_rate": 1.7298096848521616e-05, + "loss": 3.8692, + "step": 1997312 + }, + { + "epoch": 0.0, + "learning_rate": 1.7289710901011096e-05, + "loss": 3.8696, + "step": 1997824 + }, + { + "epoch": 0.0, + "learning_rate": 1.7281324953500576e-05, + "loss": 3.8691, + "step": 1998336 + }, + { + "epoch": 0.0, + "learning_rate": 1.7272939005990056e-05, + "loss": 3.8652, + "step": 1998848 + }, + { + "epoch": 0.0, + "learning_rate": 1.7264553058479536e-05, + "loss": 3.8659, + "step": 1999360 + }, + { + "epoch": 0.01, + "learning_rate": 1.725618348977275e-05, + "loss": 3.8659, + "step": 1999872 + }, + { + "epoch": 0.01, + "learning_rate": 1.724779754226223e-05, + "loss": 3.8714, + "step": 2000384 + }, + { + "epoch": 0.01, + "learning_rate": 1.723941159475171e-05, + "loss": 3.8791, + "step": 2000896 + }, + { + "epoch": 0.01, + "learning_rate": 1.723102564724119e-05, + "loss": 3.87, + "step": 2001408 + }, + { + "epoch": 0.01, + "learning_rate": 1.7222656078534398e-05, + "loss": 3.8659, + "step": 2001920 + }, + { + "epoch": 0.01, + "learning_rate": 1.721428650982761e-05, + "loss": 3.8642, + "step": 2002432 + }, + { + "epoch": 0.01, + "learning_rate": 1.720590056231709e-05, + "loss": 3.8756, + "step": 2002944 + }, + { + "epoch": 0.01, + "learning_rate": 1.719751461480657e-05, + "loss": 3.8684, + "step": 2003456 + }, + { + "epoch": 0.01, + "learning_rate": 1.718914504609978e-05, + "loss": 3.8691, + "step": 2003968 + }, + { + "epoch": 0.01, + "learning_rate": 1.718075909858926e-05, + "loss": 3.8536, + "step": 2004480 + }, + { + "epoch": 0.01, + "learning_rate": 1.7172373151078743e-05, + "loss": 3.8676, + "step": 2004992 + }, + { + "epoch": 0.01, + "learning_rate": 1.7163987203568222e-05, + "loss": 3.8687, + "step": 2005504 + }, + { + "epoch": 0.01, + "learning_rate": 1.7155601256057702e-05, + "loss": 3.8759, + "step": 2006016 + }, + { + "epoch": 0.01, + "learning_rate": 1.7147215308547182e-05, + "loss": 3.8686, + "step": 2006528 + }, + { + "epoch": 0.01, + "learning_rate": 1.7138829361036662e-05, + "loss": 3.8699, + "step": 2007040 + }, + { + "epoch": 0.01, + "learning_rate": 1.713044341352614e-05, + "loss": 3.865, + "step": 2007552 + }, + { + "epoch": 0.01, + "learning_rate": 1.712205746601562e-05, + "loss": 3.8718, + "step": 2008064 + }, + { + "epoch": 0.01, + "learning_rate": 1.7113671518505102e-05, + "loss": 3.8692, + "step": 2008576 + }, + { + "epoch": 0.01, + "learning_rate": 1.7105285570994582e-05, + "loss": 3.8416, + "step": 2009088 + }, + { + "epoch": 0.01, + "learning_rate": 1.709691600228779e-05, + "loss": 3.8752, + "step": 2009600 + }, + { + "epoch": 0.01, + "learning_rate": 1.7088546433581004e-05, + "loss": 3.867, + "step": 2010112 + }, + { + "epoch": 0.01, + "learning_rate": 1.7080160486070484e-05, + "loss": 3.876, + "step": 2010624 + }, + { + "epoch": 0.01, + "learning_rate": 1.7071790917363696e-05, + "loss": 3.8628, + "step": 2011136 + }, + { + "epoch": 0.01, + "learning_rate": 1.7063404969853176e-05, + "loss": 3.863, + "step": 2011648 + }, + { + "epoch": 0.01, + "learning_rate": 1.7055019022342656e-05, + "loss": 3.8573, + "step": 2012160 + }, + { + "epoch": 0.01, + "learning_rate": 1.7046633074832136e-05, + "loss": 3.8589, + "step": 2012672 + }, + { + "epoch": 0.01, + "learning_rate": 1.7038247127321613e-05, + "loss": 3.8723, + "step": 2013184 + }, + { + "epoch": 0.01, + "learning_rate": 1.7029861179811093e-05, + "loss": 3.8502, + "step": 2013696 + }, + { + "epoch": 0.01, + "learning_rate": 1.7021475232300573e-05, + "loss": 3.8747, + "step": 2014208 + }, + { + "epoch": 0.01, + "learning_rate": 1.7013089284790053e-05, + "loss": 3.8631, + "step": 2014720 + }, + { + "epoch": 0.01, + "learning_rate": 1.7004703337279536e-05, + "loss": 3.8584, + "step": 2015232 + }, + { + "epoch": 0.01, + "learning_rate": 1.6996317389769016e-05, + "loss": 3.8818, + "step": 2015744 + }, + { + "epoch": 0.01, + "learning_rate": 1.6987931442258496e-05, + "loss": 3.8561, + "step": 2016256 + }, + { + "epoch": 0.01, + "learning_rate": 1.6979545494747972e-05, + "loss": 3.8506, + "step": 2016768 + }, + { + "epoch": 0.01, + "learning_rate": 1.6971175926041185e-05, + "loss": 3.8719, + "step": 2017280 + }, + { + "epoch": 0.01, + "learning_rate": 1.6962789978530665e-05, + "loss": 3.8684, + "step": 2017792 + }, + { + "epoch": 0.01, + "learning_rate": 1.6954404031020145e-05, + "loss": 3.8576, + "step": 2018304 + }, + { + "epoch": 0.01, + "learning_rate": 1.6946018083509625e-05, + "loss": 3.8631, + "step": 2018816 + }, + { + "epoch": 0.01, + "learning_rate": 1.6937648514802837e-05, + "loss": 3.8489, + "step": 2019328 + }, + { + "epoch": 0.01, + "learning_rate": 1.6929262567292317e-05, + "loss": 3.8657, + "step": 2019840 + }, + { + "epoch": 0.01, + "learning_rate": 1.6920876619781794e-05, + "loss": 3.8723, + "step": 2020352 + }, + { + "epoch": 0.01, + "learning_rate": 1.6912490672271274e-05, + "loss": 3.8706, + "step": 2020864 + }, + { + "epoch": 0.01, + "learning_rate": 1.6904104724760757e-05, + "loss": 3.8678, + "step": 2021376 + }, + { + "epoch": 0.01, + "learning_rate": 1.6895735156053966e-05, + "loss": 3.873, + "step": 2021888 + }, + { + "epoch": 0.01, + "learning_rate": 1.688736558734718e-05, + "loss": 3.8863, + "step": 2022400 + }, + { + "epoch": 0.01, + "learning_rate": 1.687897963983666e-05, + "loss": 3.8652, + "step": 2022912 + }, + { + "epoch": 0.01, + "learning_rate": 1.687059369232614e-05, + "loss": 3.8686, + "step": 2023424 + }, + { + "epoch": 0.01, + "learning_rate": 1.686220774481562e-05, + "loss": 3.8656, + "step": 2023936 + }, + { + "epoch": 0.01, + "learning_rate": 1.68538217973051e-05, + "loss": 3.8672, + "step": 2024448 + }, + { + "epoch": 0.01, + "learning_rate": 1.684543584979458e-05, + "loss": 3.8582, + "step": 2024960 + }, + { + "epoch": 0.01, + "learning_rate": 1.6837049902284058e-05, + "loss": 3.8781, + "step": 2025472 + }, + { + "epoch": 0.01, + "learning_rate": 1.6828663954773538e-05, + "loss": 3.8701, + "step": 2025984 + }, + { + "epoch": 0.01, + "learning_rate": 1.6820294386066747e-05, + "loss": 3.8774, + "step": 2026496 + }, + { + "epoch": 0.01, + "learning_rate": 1.6811908438556227e-05, + "loss": 3.854, + "step": 2027008 + }, + { + "epoch": 0.01, + "learning_rate": 1.680352249104571e-05, + "loss": 3.8627, + "step": 2027520 + }, + { + "epoch": 0.01, + "learning_rate": 1.679513654353519e-05, + "loss": 3.8637, + "step": 2028032 + }, + { + "epoch": 0.01, + "learning_rate": 1.67867669748284e-05, + "loss": 3.8664, + "step": 2028544 + }, + { + "epoch": 0.01, + "learning_rate": 1.6778397406121612e-05, + "loss": 3.868, + "step": 2029056 + }, + { + "epoch": 0.01, + "learning_rate": 1.677001145861109e-05, + "loss": 3.8707, + "step": 2029568 + }, + { + "epoch": 0.01, + "learning_rate": 1.6761625511100572e-05, + "loss": 3.8555, + "step": 2030080 + }, + { + "epoch": 0.02, + "learning_rate": 1.6753239563590052e-05, + "loss": 3.8669, + "step": 2030592 + }, + { + "epoch": 0.02, + "learning_rate": 1.6744853616079532e-05, + "loss": 3.8604, + "step": 2031104 + }, + { + "epoch": 0.02, + "learning_rate": 1.673648404737274e-05, + "loss": 3.8609, + "step": 2031616 + }, + { + "epoch": 0.02, + "learning_rate": 1.672809809986222e-05, + "loss": 3.8746, + "step": 2032128 + }, + { + "epoch": 0.02, + "learning_rate": 1.67197121523517e-05, + "loss": 3.8775, + "step": 2032640 + }, + { + "epoch": 0.02, + "learning_rate": 1.671132620484118e-05, + "loss": 3.8645, + "step": 2033152 + }, + { + "epoch": 0.02, + "learning_rate": 1.670294025733066e-05, + "loss": 3.8642, + "step": 2033664 + }, + { + "epoch": 0.02, + "learning_rate": 1.6694570688623873e-05, + "loss": 3.866, + "step": 2034176 + }, + { + "epoch": 0.02, + "learning_rate": 1.6686184741113353e-05, + "loss": 3.8598, + "step": 2034688 + }, + { + "epoch": 0.02, + "learning_rate": 1.6677798793602833e-05, + "loss": 3.8731, + "step": 2035200 + }, + { + "epoch": 0.02, + "learning_rate": 1.6669412846092313e-05, + "loss": 3.8644, + "step": 2035712 + }, + { + "epoch": 0.02, + "learning_rate": 1.6661026898581793e-05, + "loss": 3.8669, + "step": 2036224 + }, + { + "epoch": 0.02, + "learning_rate": 1.6652657329875006e-05, + "loss": 3.8693, + "step": 2036736 + }, + { + "epoch": 0.02, + "learning_rate": 1.6644271382364486e-05, + "loss": 3.8659, + "step": 2037248 + }, + { + "epoch": 0.02, + "learning_rate": 1.6635885434853966e-05, + "loss": 3.8613, + "step": 2037760 + }, + { + "epoch": 0.02, + "learning_rate": 1.6627499487343446e-05, + "loss": 3.8611, + "step": 2038272 + }, + { + "epoch": 0.02, + "learning_rate": 1.6619129918636655e-05, + "loss": 3.8548, + "step": 2038784 + }, + { + "epoch": 0.02, + "learning_rate": 1.6610743971126135e-05, + "loss": 3.8701, + "step": 2039296 + }, + { + "epoch": 0.02, + "learning_rate": 1.6602358023615615e-05, + "loss": 3.8624, + "step": 2039808 + }, + { + "epoch": 0.02, + "learning_rate": 1.6593972076105095e-05, + "loss": 3.8632, + "step": 2040320 + }, + { + "epoch": 0.02, + "learning_rate": 1.6585586128594575e-05, + "loss": 3.851, + "step": 2040832 + }, + { + "epoch": 0.02, + "learning_rate": 1.6577200181084054e-05, + "loss": 3.8692, + "step": 2041344 + }, + { + "epoch": 0.02, + "learning_rate": 1.6568830612377267e-05, + "loss": 3.8718, + "step": 2041856 + }, + { + "epoch": 0.02, + "learning_rate": 1.6560444664866744e-05, + "loss": 3.8593, + "step": 2042368 + }, + { + "epoch": 0.02, + "learning_rate": 1.6552058717356227e-05, + "loss": 3.8672, + "step": 2042880 + }, + { + "epoch": 0.02, + "learning_rate": 1.6543672769845707e-05, + "loss": 3.8787, + "step": 2043392 + }, + { + "epoch": 0.02, + "learning_rate": 1.653530320113892e-05, + "loss": 3.8609, + "step": 2043904 + }, + { + "epoch": 0.02, + "learning_rate": 1.6526917253628396e-05, + "loss": 3.8713, + "step": 2044416 + }, + { + "epoch": 0.02, + "learning_rate": 1.6518531306117876e-05, + "loss": 3.8665, + "step": 2044928 + }, + { + "epoch": 0.02, + "learning_rate": 1.6510145358607356e-05, + "loss": 3.869, + "step": 2045440 + }, + { + "epoch": 0.02, + "learning_rate": 1.6501775789900568e-05, + "loss": 3.8695, + "step": 2045952 + }, + { + "epoch": 0.02, + "learning_rate": 1.6493389842390048e-05, + "loss": 3.8605, + "step": 2046464 + }, + { + "epoch": 0.02, + "learning_rate": 1.6485003894879528e-05, + "loss": 3.8601, + "step": 2046976 + }, + { + "epoch": 0.02, + "learning_rate": 1.6476617947369008e-05, + "loss": 3.8641, + "step": 2047488 + }, + { + "epoch": 0.02, + "learning_rate": 1.6468231999858488e-05, + "loss": 3.8655, + "step": 2048000 + }, + { + "epoch": 0.02, + "learning_rate": 1.6459846052347968e-05, + "loss": 3.8642, + "step": 2048512 + }, + { + "epoch": 0.02, + "learning_rate": 1.6451460104837448e-05, + "loss": 3.8544, + "step": 2049024 + }, + { + "epoch": 0.02, + "learning_rate": 1.6443074157326928e-05, + "loss": 3.8648, + "step": 2049536 + }, + { + "epoch": 0.02, + "learning_rate": 1.6434688209816408e-05, + "loss": 3.8524, + "step": 2050048 + }, + { + "epoch": 0.02, + "learning_rate": 1.642631864110962e-05, + "loss": 3.8788, + "step": 2050560 + }, + { + "epoch": 0.02, + "learning_rate": 1.64179326935991e-05, + "loss": 3.8653, + "step": 2051072 + }, + { + "epoch": 0.02, + "learning_rate": 1.640956312489231e-05, + "loss": 3.8728, + "step": 2051584 + }, + { + "epoch": 0.02, + "learning_rate": 1.640117717738179e-05, + "loss": 3.8565, + "step": 2052096 + }, + { + "epoch": 0.02, + "learning_rate": 1.639279122987127e-05, + "loss": 3.8759, + "step": 2052608 + }, + { + "epoch": 0.02, + "learning_rate": 1.638440528236075e-05, + "loss": 3.8716, + "step": 2053120 + }, + { + "epoch": 0.02, + "learning_rate": 1.637601933485023e-05, + "loss": 3.8669, + "step": 2053632 + }, + { + "epoch": 0.02, + "learning_rate": 1.6367649766143442e-05, + "loss": 3.8688, + "step": 2054144 + }, + { + "epoch": 0.02, + "learning_rate": 1.6359263818632922e-05, + "loss": 3.8635, + "step": 2054656 + }, + { + "epoch": 0.02, + "learning_rate": 1.6350877871122398e-05, + "loss": 3.8675, + "step": 2055168 + }, + { + "epoch": 0.02, + "learning_rate": 1.634249192361188e-05, + "loss": 3.8802, + "step": 2055680 + }, + { + "epoch": 0.02, + "learning_rate": 1.633410597610136e-05, + "loss": 3.8561, + "step": 2056192 + }, + { + "epoch": 0.02, + "learning_rate": 1.632572002859084e-05, + "loss": 3.8693, + "step": 2056704 + }, + { + "epoch": 0.02, + "learning_rate": 1.631735045988405e-05, + "loss": 3.8625, + "step": 2057216 + }, + { + "epoch": 0.02, + "learning_rate": 1.630896451237353e-05, + "loss": 3.8653, + "step": 2057728 + }, + { + "epoch": 0.02, + "learning_rate": 1.630057856486301e-05, + "loss": 3.8626, + "step": 2058240 + }, + { + "epoch": 0.02, + "learning_rate": 1.629219261735249e-05, + "loss": 3.8618, + "step": 2058752 + }, + { + "epoch": 0.02, + "learning_rate": 1.6283806669841974e-05, + "loss": 3.8721, + "step": 2059264 + }, + { + "epoch": 0.02, + "learning_rate": 1.6275437101135183e-05, + "loss": 3.8703, + "step": 2059776 + }, + { + "epoch": 0.02, + "learning_rate": 1.6267051153624663e-05, + "loss": 3.8642, + "step": 2060288 + }, + { + "epoch": 0.03, + "eval_loss": 3.9782962799072266, + "eval_runtime": 293.7623, + "eval_samples_per_second": 1298.979, + "eval_steps_per_second": 40.594, + "step": 2060640 + }, + { + "epoch": 0.0, + "learning_rate": 1.6258665206114143e-05, + "loss": 3.8633, + "step": 2060800 + }, + { + "epoch": 0.0, + "learning_rate": 1.6250279258603623e-05, + "loss": 3.8634, + "step": 2061312 + }, + { + "epoch": 0.0, + "learning_rate": 1.6241893311093103e-05, + "loss": 3.8663, + "step": 2061824 + }, + { + "epoch": 0.0, + "learning_rate": 1.6233507363582583e-05, + "loss": 3.8671, + "step": 2062336 + }, + { + "epoch": 0.0, + "learning_rate": 1.6225121416072063e-05, + "loss": 3.8772, + "step": 2062848 + }, + { + "epoch": 0.0, + "learning_rate": 1.6216735468561543e-05, + "loss": 3.8605, + "step": 2063360 + }, + { + "epoch": 0.0, + "learning_rate": 1.6208349521051023e-05, + "loss": 3.8699, + "step": 2063872 + }, + { + "epoch": 0.0, + "learning_rate": 1.6199963573540503e-05, + "loss": 3.8653, + "step": 2064384 + }, + { + "epoch": 0.0, + "learning_rate": 1.6191577626029982e-05, + "loss": 3.8636, + "step": 2064896 + }, + { + "epoch": 0.0, + "learning_rate": 1.618319167851946e-05, + "loss": 3.8649, + "step": 2065408 + }, + { + "epoch": 0.0, + "learning_rate": 1.617480573100894e-05, + "loss": 3.8725, + "step": 2065920 + }, + { + "epoch": 0.0, + "learning_rate": 1.6166419783498422e-05, + "loss": 3.8662, + "step": 2066432 + }, + { + "epoch": 0.0, + "learning_rate": 1.6158050214791635e-05, + "loss": 3.8738, + "step": 2066944 + }, + { + "epoch": 0.0, + "learning_rate": 1.614966426728111e-05, + "loss": 3.8537, + "step": 2067456 + }, + { + "epoch": 0.0, + "learning_rate": 1.614127831977059e-05, + "loss": 3.8621, + "step": 2067968 + }, + { + "epoch": 0.0, + "learning_rate": 1.613289237226007e-05, + "loss": 3.8484, + "step": 2068480 + }, + { + "epoch": 0.0, + "learning_rate": 1.612450642474955e-05, + "loss": 3.8734, + "step": 2068992 + }, + { + "epoch": 0.0, + "learning_rate": 1.611612047723903e-05, + "loss": 3.8611, + "step": 2069504 + }, + { + "epoch": 0.0, + "learning_rate": 1.6107734529728515e-05, + "loss": 3.8599, + "step": 2070016 + }, + { + "epoch": 0.0, + "learning_rate": 1.6099348582217995e-05, + "loss": 3.8715, + "step": 2070528 + }, + { + "epoch": 0.0, + "learning_rate": 1.6090979013511204e-05, + "loss": 3.8724, + "step": 2071040 + }, + { + "epoch": 0.0, + "learning_rate": 1.6082593066000684e-05, + "loss": 3.8703, + "step": 2071552 + }, + { + "epoch": 0.0, + "learning_rate": 1.6074207118490164e-05, + "loss": 3.8718, + "step": 2072064 + }, + { + "epoch": 0.0, + "learning_rate": 1.6065821170979643e-05, + "loss": 3.8642, + "step": 2072576 + }, + { + "epoch": 0.0, + "learning_rate": 1.6057435223469123e-05, + "loss": 3.8655, + "step": 2073088 + }, + { + "epoch": 0.0, + "learning_rate": 1.6049049275958603e-05, + "loss": 3.8687, + "step": 2073600 + }, + { + "epoch": 0.0, + "learning_rate": 1.6040679707251816e-05, + "loss": 3.8566, + "step": 2074112 + }, + { + "epoch": 0.0, + "learning_rate": 1.6032293759741292e-05, + "loss": 3.8652, + "step": 2074624 + }, + { + "epoch": 0.0, + "learning_rate": 1.6023907812230772e-05, + "loss": 3.8628, + "step": 2075136 + }, + { + "epoch": 0.0, + "learning_rate": 1.6015521864720252e-05, + "loss": 3.8588, + "step": 2075648 + }, + { + "epoch": 0.01, + "learning_rate": 1.6007135917209736e-05, + "loss": 3.8605, + "step": 2076160 + }, + { + "epoch": 0.01, + "learning_rate": 1.5998749969699216e-05, + "loss": 3.8685, + "step": 2076672 + }, + { + "epoch": 0.01, + "learning_rate": 1.5990364022188696e-05, + "loss": 3.8702, + "step": 2077184 + }, + { + "epoch": 0.01, + "learning_rate": 1.5981978074678176e-05, + "loss": 3.8711, + "step": 2077696 + }, + { + "epoch": 0.01, + "learning_rate": 1.5973608505971385e-05, + "loss": 3.8594, + "step": 2078208 + }, + { + "epoch": 0.01, + "learning_rate": 1.5965238937264597e-05, + "loss": 3.8609, + "step": 2078720 + }, + { + "epoch": 0.01, + "learning_rate": 1.5956852989754077e-05, + "loss": 3.8716, + "step": 2079232 + }, + { + "epoch": 0.01, + "learning_rate": 1.5948467042243557e-05, + "loss": 3.8582, + "step": 2079744 + }, + { + "epoch": 0.01, + "learning_rate": 1.5940081094733037e-05, + "loss": 3.8658, + "step": 2080256 + }, + { + "epoch": 0.01, + "learning_rate": 1.5931695147222517e-05, + "loss": 3.8533, + "step": 2080768 + }, + { + "epoch": 0.01, + "learning_rate": 1.5923309199711997e-05, + "loss": 3.8571, + "step": 2081280 + }, + { + "epoch": 0.01, + "learning_rate": 1.5914923252201473e-05, + "loss": 3.8622, + "step": 2081792 + }, + { + "epoch": 0.01, + "learning_rate": 1.5906537304690953e-05, + "loss": 3.8703, + "step": 2082304 + }, + { + "epoch": 0.01, + "learning_rate": 1.5898151357180437e-05, + "loss": 3.8644, + "step": 2082816 + }, + { + "epoch": 0.01, + "learning_rate": 1.588978178847365e-05, + "loss": 3.8615, + "step": 2083328 + }, + { + "epoch": 0.01, + "learning_rate": 1.5881395840963126e-05, + "loss": 3.8641, + "step": 2083840 + }, + { + "epoch": 0.01, + "learning_rate": 1.587302627225634e-05, + "loss": 3.8638, + "step": 2084352 + }, + { + "epoch": 0.01, + "learning_rate": 1.5864640324745818e-05, + "loss": 3.8668, + "step": 2084864 + }, + { + "epoch": 0.01, + "learning_rate": 1.5856254377235298e-05, + "loss": 3.8403, + "step": 2085376 + }, + { + "epoch": 0.01, + "learning_rate": 1.5847868429724778e-05, + "loss": 3.866, + "step": 2085888 + }, + { + "epoch": 0.01, + "learning_rate": 1.5839482482214258e-05, + "loss": 3.8619, + "step": 2086400 + }, + { + "epoch": 0.01, + "learning_rate": 1.5831096534703738e-05, + "loss": 3.8705, + "step": 2086912 + }, + { + "epoch": 0.01, + "learning_rate": 1.5822710587193218e-05, + "loss": 3.8595, + "step": 2087424 + }, + { + "epoch": 0.01, + "learning_rate": 1.5814324639682698e-05, + "loss": 3.8538, + "step": 2087936 + }, + { + "epoch": 0.01, + "learning_rate": 1.5805955070975907e-05, + "loss": 3.856, + "step": 2088448 + }, + { + "epoch": 0.01, + "learning_rate": 1.579756912346539e-05, + "loss": 3.8534, + "step": 2088960 + }, + { + "epoch": 0.01, + "learning_rate": 1.57891995547586e-05, + "loss": 3.8664, + "step": 2089472 + }, + { + "epoch": 0.01, + "learning_rate": 1.578081360724808e-05, + "loss": 3.8453, + "step": 2089984 + }, + { + "epoch": 0.01, + "learning_rate": 1.577242765973756e-05, + "loss": 3.8733, + "step": 2090496 + }, + { + "epoch": 0.01, + "learning_rate": 1.576404171222704e-05, + "loss": 3.8585, + "step": 2091008 + }, + { + "epoch": 0.01, + "learning_rate": 1.5755672143520252e-05, + "loss": 3.8512, + "step": 2091520 + }, + { + "epoch": 0.01, + "learning_rate": 1.5747286196009732e-05, + "loss": 3.8759, + "step": 2092032 + }, + { + "epoch": 0.01, + "learning_rate": 1.5738900248499212e-05, + "loss": 3.8511, + "step": 2092544 + }, + { + "epoch": 0.01, + "learning_rate": 1.5730514300988692e-05, + "loss": 3.8488, + "step": 2093056 + }, + { + "epoch": 0.01, + "learning_rate": 1.5722128353478172e-05, + "loss": 3.8657, + "step": 2093568 + }, + { + "epoch": 0.01, + "learning_rate": 1.571374240596765e-05, + "loss": 3.8649, + "step": 2094080 + }, + { + "epoch": 0.01, + "learning_rate": 1.5705356458457128e-05, + "loss": 3.8492, + "step": 2094592 + }, + { + "epoch": 0.01, + "learning_rate": 1.5696986889750344e-05, + "loss": 3.863, + "step": 2095104 + }, + { + "epoch": 0.01, + "learning_rate": 1.5688600942239824e-05, + "loss": 3.8433, + "step": 2095616 + }, + { + "epoch": 0.01, + "learning_rate": 1.5680231373533033e-05, + "loss": 3.8597, + "step": 2096128 + }, + { + "epoch": 0.01, + "learning_rate": 1.5671845426022513e-05, + "loss": 3.8681, + "step": 2096640 + }, + { + "epoch": 0.01, + "learning_rate": 1.5663459478511993e-05, + "loss": 3.8642, + "step": 2097152 + }, + { + "epoch": 0.01, + "learning_rate": 1.5655073531001473e-05, + "loss": 3.864, + "step": 2097664 + }, + { + "epoch": 0.01, + "learning_rate": 1.5646687583490953e-05, + "loss": 3.8671, + "step": 2098176 + }, + { + "epoch": 0.01, + "learning_rate": 1.5638301635980433e-05, + "loss": 3.881, + "step": 2098688 + }, + { + "epoch": 0.01, + "learning_rate": 1.5629915688469913e-05, + "loss": 3.8598, + "step": 2099200 + }, + { + "epoch": 0.01, + "learning_rate": 1.5621529740959393e-05, + "loss": 3.8672, + "step": 2099712 + }, + { + "epoch": 0.01, + "learning_rate": 1.5613143793448873e-05, + "loss": 3.858, + "step": 2100224 + }, + { + "epoch": 0.01, + "learning_rate": 1.5604757845938353e-05, + "loss": 3.8608, + "step": 2100736 + }, + { + "epoch": 0.01, + "learning_rate": 1.5596371898427833e-05, + "loss": 3.8557, + "step": 2101248 + }, + { + "epoch": 0.01, + "learning_rate": 1.558798595091731e-05, + "loss": 3.871, + "step": 2101760 + }, + { + "epoch": 0.01, + "learning_rate": 1.5579616382210525e-05, + "loss": 3.8654, + "step": 2102272 + }, + { + "epoch": 0.01, + "learning_rate": 1.5571230434700005e-05, + "loss": 3.8718, + "step": 2102784 + }, + { + "epoch": 0.01, + "learning_rate": 1.5562844487189482e-05, + "loss": 3.8545, + "step": 2103296 + }, + { + "epoch": 0.01, + "learning_rate": 1.555445853967896e-05, + "loss": 3.8582, + "step": 2103808 + }, + { + "epoch": 0.01, + "learning_rate": 1.5546088970972174e-05, + "loss": 3.8586, + "step": 2104320 + }, + { + "epoch": 0.01, + "learning_rate": 1.5537703023461654e-05, + "loss": 3.8598, + "step": 2104832 + }, + { + "epoch": 0.01, + "learning_rate": 1.5529317075951134e-05, + "loss": 3.8636, + "step": 2105344 + }, + { + "epoch": 0.01, + "learning_rate": 1.5520931128440614e-05, + "loss": 3.8671, + "step": 2105856 + }, + { + "epoch": 0.01, + "learning_rate": 1.5512561559733826e-05, + "loss": 3.8536, + "step": 2106368 + }, + { + "epoch": 0.02, + "learning_rate": 1.5504191991027036e-05, + "loss": 3.8606, + "step": 2106880 + }, + { + "epoch": 0.02, + "learning_rate": 1.5495806043516516e-05, + "loss": 3.8565, + "step": 2107392 + }, + { + "epoch": 0.02, + "learning_rate": 1.5487420096006e-05, + "loss": 3.8533, + "step": 2107904 + }, + { + "epoch": 0.02, + "learning_rate": 1.547903414849548e-05, + "loss": 3.8678, + "step": 2108416 + }, + { + "epoch": 0.02, + "learning_rate": 1.5470664579788688e-05, + "loss": 3.874, + "step": 2108928 + }, + { + "epoch": 0.02, + "learning_rate": 1.5462278632278168e-05, + "loss": 3.8636, + "step": 2109440 + }, + { + "epoch": 0.02, + "learning_rate": 1.5453892684767648e-05, + "loss": 3.8538, + "step": 2109952 + }, + { + "epoch": 0.02, + "learning_rate": 1.5445506737257128e-05, + "loss": 3.8633, + "step": 2110464 + }, + { + "epoch": 0.02, + "learning_rate": 1.5437120789746608e-05, + "loss": 3.8534, + "step": 2110976 + }, + { + "epoch": 0.02, + "learning_rate": 1.5428734842236088e-05, + "loss": 3.8653, + "step": 2111488 + }, + { + "epoch": 0.02, + "learning_rate": 1.54203652735293e-05, + "loss": 3.8652, + "step": 2112000 + }, + { + "epoch": 0.02, + "learning_rate": 1.541197932601878e-05, + "loss": 3.8554, + "step": 2112512 + }, + { + "epoch": 0.02, + "learning_rate": 1.5403593378508257e-05, + "loss": 3.8651, + "step": 2113024 + }, + { + "epoch": 0.02, + "learning_rate": 1.5395207430997737e-05, + "loss": 3.8594, + "step": 2113536 + }, + { + "epoch": 0.02, + "learning_rate": 1.5386821483487217e-05, + "loss": 3.8581, + "step": 2114048 + }, + { + "epoch": 0.02, + "learning_rate": 1.53784355359767e-05, + "loss": 3.8557, + "step": 2114560 + }, + { + "epoch": 0.02, + "learning_rate": 1.537006596726991e-05, + "loss": 3.8536, + "step": 2115072 + }, + { + "epoch": 0.02, + "learning_rate": 1.536168001975939e-05, + "loss": 3.8629, + "step": 2115584 + }, + { + "epoch": 0.02, + "learning_rate": 1.535329407224887e-05, + "loss": 3.862, + "step": 2116096 + }, + { + "epoch": 0.02, + "learning_rate": 1.534490812473835e-05, + "loss": 3.8557, + "step": 2116608 + }, + { + "epoch": 0.02, + "learning_rate": 1.533652217722783e-05, + "loss": 3.8484, + "step": 2117120 + }, + { + "epoch": 0.02, + "learning_rate": 1.532813622971731e-05, + "loss": 3.8621, + "step": 2117632 + }, + { + "epoch": 0.02, + "learning_rate": 1.531975028220679e-05, + "loss": 3.867, + "step": 2118144 + }, + { + "epoch": 0.02, + "learning_rate": 1.531136433469627e-05, + "loss": 3.8523, + "step": 2118656 + }, + { + "epoch": 0.02, + "learning_rate": 1.530299476598948e-05, + "loss": 3.8644, + "step": 2119168 + }, + { + "epoch": 0.02, + "learning_rate": 1.529460881847896e-05, + "loss": 3.8713, + "step": 2119680 + }, + { + "epoch": 0.02, + "learning_rate": 1.5286222870968438e-05, + "loss": 3.8609, + "step": 2120192 + }, + { + "epoch": 0.02, + "learning_rate": 1.5277836923457918e-05, + "loss": 3.8615, + "step": 2120704 + }, + { + "epoch": 0.02, + "learning_rate": 1.52694509759474e-05, + "loss": 3.8643, + "step": 2121216 + }, + { + "epoch": 0.02, + "learning_rate": 1.526108140724061e-05, + "loss": 3.8633, + "step": 2121728 + }, + { + "epoch": 0.02, + "learning_rate": 1.5252711838533823e-05, + "loss": 3.8652, + "step": 2122240 + }, + { + "epoch": 0.02, + "learning_rate": 1.5244325891023303e-05, + "loss": 3.8542, + "step": 2122752 + }, + { + "epoch": 0.02, + "learning_rate": 1.5235956322316513e-05, + "loss": 3.855, + "step": 2123264 + }, + { + "epoch": 0.02, + "learning_rate": 1.5227570374805993e-05, + "loss": 3.8599, + "step": 2123776 + }, + { + "epoch": 0.02, + "learning_rate": 1.5219184427295475e-05, + "loss": 3.8596, + "step": 2124288 + }, + { + "epoch": 0.02, + "learning_rate": 1.5210798479784955e-05, + "loss": 3.8557, + "step": 2124800 + }, + { + "epoch": 0.02, + "learning_rate": 1.5202412532274435e-05, + "loss": 3.8554, + "step": 2125312 + }, + { + "epoch": 0.02, + "learning_rate": 1.5194026584763913e-05, + "loss": 3.8555, + "step": 2125824 + }, + { + "epoch": 0.02, + "learning_rate": 1.5185657016057126e-05, + "loss": 3.8505, + "step": 2126336 + }, + { + "epoch": 0.02, + "learning_rate": 1.5177271068546606e-05, + "loss": 3.8716, + "step": 2126848 + }, + { + "epoch": 0.02, + "learning_rate": 1.5168885121036084e-05, + "loss": 3.8588, + "step": 2127360 + }, + { + "epoch": 0.02, + "learning_rate": 1.5160499173525564e-05, + "loss": 3.8721, + "step": 2127872 + }, + { + "epoch": 0.02, + "learning_rate": 1.5152113226015044e-05, + "loss": 3.8492, + "step": 2128384 + }, + { + "epoch": 0.02, + "learning_rate": 1.5143727278504524e-05, + "loss": 3.8708, + "step": 2128896 + }, + { + "epoch": 0.02, + "learning_rate": 1.5135341330994004e-05, + "loss": 3.8671, + "step": 2129408 + }, + { + "epoch": 0.02, + "learning_rate": 1.5126955383483485e-05, + "loss": 3.8627, + "step": 2129920 + }, + { + "epoch": 0.02, + "learning_rate": 1.5118569435972965e-05, + "loss": 3.8585, + "step": 2130432 + }, + { + "epoch": 0.02, + "learning_rate": 1.5110183488462442e-05, + "loss": 3.8638, + "step": 2130944 + }, + { + "epoch": 0.02, + "learning_rate": 1.5101813919755656e-05, + "loss": 3.8654, + "step": 2131456 + }, + { + "epoch": 0.02, + "learning_rate": 1.5093427972245136e-05, + "loss": 3.8713, + "step": 2131968 + }, + { + "epoch": 0.02, + "learning_rate": 1.5085042024734614e-05, + "loss": 3.8539, + "step": 2132480 + }, + { + "epoch": 0.02, + "learning_rate": 1.5076656077224094e-05, + "loss": 3.859, + "step": 2132992 + }, + { + "epoch": 0.02, + "learning_rate": 1.5068270129713574e-05, + "loss": 3.859, + "step": 2133504 + }, + { + "epoch": 0.02, + "learning_rate": 1.5059900561006787e-05, + "loss": 3.8592, + "step": 2134016 + }, + { + "epoch": 0.02, + "learning_rate": 1.5051514613496265e-05, + "loss": 3.8564, + "step": 2134528 + }, + { + "epoch": 0.02, + "learning_rate": 1.5043128665985745e-05, + "loss": 3.8629, + "step": 2135040 + }, + { + "epoch": 0.02, + "learning_rate": 1.5034742718475225e-05, + "loss": 3.8668, + "step": 2135552 + }, + { + "epoch": 0.02, + "learning_rate": 1.5026356770964706e-05, + "loss": 3.8627, + "step": 2136064 + }, + { + "epoch": 0.02, + "learning_rate": 1.5017970823454186e-05, + "loss": 3.8582, + "step": 2136576 + }, + { + "epoch": 0.03, + "eval_loss": 3.976229190826416, + "eval_runtime": 293.9109, + "eval_samples_per_second": 1298.322, + "eval_steps_per_second": 40.574, + "step": 2136960 + }, + { + "epoch": 1.0, + "learning_rate": 1.5009601254747396e-05, + "loss": 3.8588, + "step": 2137088 + }, + { + "epoch": 1.0, + "learning_rate": 1.5001215307236877e-05, + "loss": 3.8542, + "step": 2137600 + }, + { + "epoch": 1.0, + "learning_rate": 1.4992829359726357e-05, + "loss": 3.8625, + "step": 2138112 + }, + { + "epoch": 1.0, + "learning_rate": 1.4984443412215837e-05, + "loss": 3.8631, + "step": 2138624 + }, + { + "epoch": 1.0, + "learning_rate": 1.4976073843509048e-05, + "loss": 3.8653, + "step": 2139136 + }, + { + "epoch": 1.0, + "learning_rate": 1.4967687895998528e-05, + "loss": 3.8606, + "step": 2139648 + }, + { + "epoch": 1.0, + "learning_rate": 1.4959301948488008e-05, + "loss": 3.8651, + "step": 2140160 + }, + { + "epoch": 1.0, + "learning_rate": 1.4950916000977488e-05, + "loss": 3.8598, + "step": 2140672 + }, + { + "epoch": 1.0, + "learning_rate": 1.494253005346697e-05, + "loss": 3.8558, + "step": 2141184 + }, + { + "epoch": 1.0, + "learning_rate": 1.4934144105956446e-05, + "loss": 3.8617, + "step": 2141696 + }, + { + "epoch": 1.0, + "learning_rate": 1.4925758158445926e-05, + "loss": 3.8675, + "step": 2142208 + }, + { + "epoch": 1.0, + "learning_rate": 1.491738858973914e-05, + "loss": 3.8579, + "step": 2142720 + }, + { + "epoch": 1.0, + "learning_rate": 1.490901902103235e-05, + "loss": 3.8756, + "step": 2143232 + }, + { + "epoch": 1.0, + "learning_rate": 1.4900633073521831e-05, + "loss": 3.8453, + "step": 2143744 + }, + { + "epoch": 1.0, + "learning_rate": 1.489224712601131e-05, + "loss": 3.8568, + "step": 2144256 + }, + { + "epoch": 1.0, + "learning_rate": 1.488386117850079e-05, + "loss": 3.8463, + "step": 2144768 + }, + { + "epoch": 1.0, + "learning_rate": 1.4875475230990269e-05, + "loss": 3.8688, + "step": 2145280 + }, + { + "epoch": 1.0, + "learning_rate": 1.4867089283479749e-05, + "loss": 3.8543, + "step": 2145792 + }, + { + "epoch": 1.0, + "learning_rate": 1.4858703335969229e-05, + "loss": 3.8552, + "step": 2146304 + }, + { + "epoch": 1.0, + "learning_rate": 1.4850317388458709e-05, + "loss": 3.8642, + "step": 2146816 + }, + { + "epoch": 1.0, + "learning_rate": 1.4841931440948189e-05, + "loss": 3.8715, + "step": 2147328 + }, + { + "epoch": 1.0, + "learning_rate": 1.483354549343767e-05, + "loss": 3.8658, + "step": 2147840 + }, + { + "epoch": 1.0, + "learning_rate": 1.482515954592715e-05, + "loss": 3.8665, + "step": 2148352 + }, + { + "epoch": 1.0, + "learning_rate": 1.4816789977220361e-05, + "loss": 3.8605, + "step": 2148864 + }, + { + "epoch": 1.0, + "learning_rate": 1.4808404029709841e-05, + "loss": 3.8638, + "step": 2149376 + }, + { + "epoch": 1.0, + "learning_rate": 1.4800018082199321e-05, + "loss": 3.861, + "step": 2149888 + }, + { + "epoch": 1.0, + "learning_rate": 1.4791632134688801e-05, + "loss": 3.8509, + "step": 2150400 + }, + { + "epoch": 1.0, + "learning_rate": 1.478324618717828e-05, + "loss": 3.8591, + "step": 2150912 + }, + { + "epoch": 1.0, + "learning_rate": 1.477486023966776e-05, + "loss": 3.8587, + "step": 2151424 + }, + { + "epoch": 1.0, + "learning_rate": 1.476647429215724e-05, + "loss": 3.8522, + "step": 2151936 + }, + { + "epoch": 1.01, + "learning_rate": 1.475808834464672e-05, + "loss": 3.8588, + "step": 2152448 + }, + { + "epoch": 1.01, + "learning_rate": 1.474971877593993e-05, + "loss": 3.8586, + "step": 2152960 + }, + { + "epoch": 1.01, + "learning_rate": 1.474133282842941e-05, + "loss": 3.8666, + "step": 2153472 + }, + { + "epoch": 1.01, + "learning_rate": 1.4732946880918892e-05, + "loss": 3.8686, + "step": 2153984 + }, + { + "epoch": 1.01, + "learning_rate": 1.4724560933408372e-05, + "loss": 3.8546, + "step": 2154496 + }, + { + "epoch": 1.01, + "learning_rate": 1.471619136470158e-05, + "loss": 3.855, + "step": 2155008 + }, + { + "epoch": 1.01, + "learning_rate": 1.4707821795994795e-05, + "loss": 3.8676, + "step": 2155520 + }, + { + "epoch": 1.01, + "learning_rate": 1.4699435848484275e-05, + "loss": 3.8499, + "step": 2156032 + }, + { + "epoch": 1.01, + "learning_rate": 1.4691049900973753e-05, + "loss": 3.8614, + "step": 2156544 + }, + { + "epoch": 1.01, + "learning_rate": 1.4682663953463233e-05, + "loss": 3.855, + "step": 2157056 + }, + { + "epoch": 1.01, + "learning_rate": 1.4674294384756446e-05, + "loss": 3.8507, + "step": 2157568 + }, + { + "epoch": 1.01, + "learning_rate": 1.4665908437245924e-05, + "loss": 3.8586, + "step": 2158080 + }, + { + "epoch": 1.01, + "learning_rate": 1.4657522489735404e-05, + "loss": 3.8677, + "step": 2158592 + }, + { + "epoch": 1.01, + "learning_rate": 1.4649136542224884e-05, + "loss": 3.8559, + "step": 2159104 + }, + { + "epoch": 1.01, + "learning_rate": 1.4640750594714364e-05, + "loss": 3.8584, + "step": 2159616 + }, + { + "epoch": 1.01, + "learning_rate": 1.4632364647203845e-05, + "loss": 3.8588, + "step": 2160128 + }, + { + "epoch": 1.01, + "learning_rate": 1.4623978699693325e-05, + "loss": 3.8584, + "step": 2160640 + }, + { + "epoch": 1.01, + "learning_rate": 1.4615592752182805e-05, + "loss": 3.8642, + "step": 2161152 + }, + { + "epoch": 1.01, + "learning_rate": 1.4607223183476016e-05, + "loss": 3.8371, + "step": 2161664 + }, + { + "epoch": 1.01, + "learning_rate": 1.4598853614769225e-05, + "loss": 3.8622, + "step": 2162176 + }, + { + "epoch": 1.01, + "learning_rate": 1.4590467667258707e-05, + "loss": 3.8539, + "step": 2162688 + }, + { + "epoch": 1.01, + "learning_rate": 1.458209809855192e-05, + "loss": 3.8675, + "step": 2163200 + }, + { + "epoch": 1.01, + "learning_rate": 1.4573712151041396e-05, + "loss": 3.8535, + "step": 2163712 + }, + { + "epoch": 1.01, + "learning_rate": 1.4565326203530877e-05, + "loss": 3.8524, + "step": 2164224 + }, + { + "epoch": 1.01, + "learning_rate": 1.4556940256020357e-05, + "loss": 3.8481, + "step": 2164736 + }, + { + "epoch": 1.01, + "learning_rate": 1.4548554308509837e-05, + "loss": 3.8486, + "step": 2165248 + }, + { + "epoch": 1.01, + "learning_rate": 1.4540168360999317e-05, + "loss": 3.8628, + "step": 2165760 + }, + { + "epoch": 1.01, + "learning_rate": 1.4531782413488797e-05, + "loss": 3.8373, + "step": 2166272 + }, + { + "epoch": 1.01, + "learning_rate": 1.4523396465978279e-05, + "loss": 3.8687, + "step": 2166784 + }, + { + "epoch": 1.01, + "learning_rate": 1.4515010518467756e-05, + "loss": 3.8558, + "step": 2167296 + }, + { + "epoch": 1.01, + "learning_rate": 1.4506624570957235e-05, + "loss": 3.8437, + "step": 2167808 + }, + { + "epoch": 1.01, + "learning_rate": 1.4498238623446717e-05, + "loss": 3.8727, + "step": 2168320 + }, + { + "epoch": 1.01, + "learning_rate": 1.4489852675936197e-05, + "loss": 3.8437, + "step": 2168832 + }, + { + "epoch": 1.01, + "learning_rate": 1.4481483107229408e-05, + "loss": 3.8422, + "step": 2169344 + }, + { + "epoch": 1.01, + "learning_rate": 1.4473097159718888e-05, + "loss": 3.8577, + "step": 2169856 + }, + { + "epoch": 1.01, + "learning_rate": 1.4464711212208368e-05, + "loss": 3.8634, + "step": 2170368 + }, + { + "epoch": 1.01, + "learning_rate": 1.4456325264697848e-05, + "loss": 3.8485, + "step": 2170880 + }, + { + "epoch": 1.01, + "learning_rate": 1.4447939317187328e-05, + "loss": 3.8587, + "step": 2171392 + }, + { + "epoch": 1.01, + "learning_rate": 1.4439569748480538e-05, + "loss": 3.8381, + "step": 2171904 + }, + { + "epoch": 1.01, + "learning_rate": 1.4431183800970018e-05, + "loss": 3.8553, + "step": 2172416 + }, + { + "epoch": 1.01, + "learning_rate": 1.44227978534595e-05, + "loss": 3.8632, + "step": 2172928 + }, + { + "epoch": 1.01, + "learning_rate": 1.441441190594898e-05, + "loss": 3.8616, + "step": 2173440 + }, + { + "epoch": 1.01, + "learning_rate": 1.440602595843846e-05, + "loss": 3.8558, + "step": 2173952 + }, + { + "epoch": 1.01, + "learning_rate": 1.4397640010927938e-05, + "loss": 3.861, + "step": 2174464 + }, + { + "epoch": 1.01, + "learning_rate": 1.4389254063417418e-05, + "loss": 3.8768, + "step": 2174976 + }, + { + "epoch": 1.01, + "learning_rate": 1.4380868115906898e-05, + "loss": 3.856, + "step": 2175488 + }, + { + "epoch": 1.01, + "learning_rate": 1.4372498547200109e-05, + "loss": 3.8657, + "step": 2176000 + }, + { + "epoch": 1.01, + "learning_rate": 1.4364112599689589e-05, + "loss": 3.8501, + "step": 2176512 + }, + { + "epoch": 1.01, + "learning_rate": 1.4355726652179069e-05, + "loss": 3.8577, + "step": 2177024 + }, + { + "epoch": 1.01, + "learning_rate": 1.4347357083472281e-05, + "loss": 3.8491, + "step": 2177536 + }, + { + "epoch": 1.01, + "learning_rate": 1.433897113596176e-05, + "loss": 3.8667, + "step": 2178048 + }, + { + "epoch": 1.01, + "learning_rate": 1.433058518845124e-05, + "loss": 3.8614, + "step": 2178560 + }, + { + "epoch": 1.01, + "learning_rate": 1.432219924094072e-05, + "loss": 3.8697, + "step": 2179072 + }, + { + "epoch": 1.01, + "learning_rate": 1.4313813293430201e-05, + "loss": 3.8498, + "step": 2179584 + }, + { + "epoch": 1.01, + "learning_rate": 1.4305427345919681e-05, + "loss": 3.8517, + "step": 2180096 + }, + { + "epoch": 1.01, + "learning_rate": 1.4297041398409161e-05, + "loss": 3.8507, + "step": 2180608 + }, + { + "epoch": 1.01, + "learning_rate": 1.4288671829702372e-05, + "loss": 3.8607, + "step": 2181120 + }, + { + "epoch": 1.01, + "learning_rate": 1.4280285882191852e-05, + "loss": 3.8537, + "step": 2181632 + }, + { + "epoch": 1.01, + "learning_rate": 1.4271899934681332e-05, + "loss": 3.861, + "step": 2182144 + }, + { + "epoch": 1.01, + "learning_rate": 1.4263513987170812e-05, + "loss": 3.8522, + "step": 2182656 + }, + { + "epoch": 1.02, + "learning_rate": 1.425512803966029e-05, + "loss": 3.8546, + "step": 2183168 + }, + { + "epoch": 1.02, + "learning_rate": 1.4246758470953502e-05, + "loss": 3.8519, + "step": 2183680 + }, + { + "epoch": 1.02, + "learning_rate": 1.4238372523442982e-05, + "loss": 3.8513, + "step": 2184192 + }, + { + "epoch": 1.02, + "learning_rate": 1.4229986575932464e-05, + "loss": 3.8602, + "step": 2184704 + }, + { + "epoch": 1.02, + "learning_rate": 1.422160062842194e-05, + "loss": 3.8716, + "step": 2185216 + }, + { + "epoch": 1.02, + "learning_rate": 1.421321468091142e-05, + "loss": 3.8582, + "step": 2185728 + }, + { + "epoch": 1.02, + "learning_rate": 1.4204828733400902e-05, + "loss": 3.8512, + "step": 2186240 + }, + { + "epoch": 1.02, + "learning_rate": 1.4196442785890382e-05, + "loss": 3.8561, + "step": 2186752 + }, + { + "epoch": 1.02, + "learning_rate": 1.4188056838379862e-05, + "loss": 3.8523, + "step": 2187264 + }, + { + "epoch": 1.02, + "learning_rate": 1.4179670890869342e-05, + "loss": 3.8623, + "step": 2187776 + }, + { + "epoch": 1.02, + "learning_rate": 1.4171301322162553e-05, + "loss": 3.8578, + "step": 2188288 + }, + { + "epoch": 1.02, + "learning_rate": 1.4162931753455764e-05, + "loss": 3.8481, + "step": 2188800 + }, + { + "epoch": 1.02, + "learning_rate": 1.4154545805945244e-05, + "loss": 3.8612, + "step": 2189312 + }, + { + "epoch": 1.02, + "learning_rate": 1.4146159858434724e-05, + "loss": 3.857, + "step": 2189824 + }, + { + "epoch": 1.02, + "learning_rate": 1.4137773910924204e-05, + "loss": 3.8527, + "step": 2190336 + }, + { + "epoch": 1.02, + "learning_rate": 1.4129387963413685e-05, + "loss": 3.8497, + "step": 2190848 + }, + { + "epoch": 1.02, + "learning_rate": 1.4121018394706894e-05, + "loss": 3.8524, + "step": 2191360 + }, + { + "epoch": 1.02, + "learning_rate": 1.4112632447196374e-05, + "loss": 3.8555, + "step": 2191872 + }, + { + "epoch": 1.02, + "learning_rate": 1.4104246499685856e-05, + "loss": 3.8566, + "step": 2192384 + }, + { + "epoch": 1.02, + "learning_rate": 1.4095860552175336e-05, + "loss": 3.8509, + "step": 2192896 + }, + { + "epoch": 1.02, + "learning_rate": 1.4087474604664816e-05, + "loss": 3.8442, + "step": 2193408 + }, + { + "epoch": 1.02, + "learning_rate": 1.4079088657154296e-05, + "loss": 3.8551, + "step": 2193920 + }, + { + "epoch": 1.02, + "learning_rate": 1.4070702709643774e-05, + "loss": 3.8633, + "step": 2194432 + }, + { + "epoch": 1.02, + "learning_rate": 1.4062316762133254e-05, + "loss": 3.8533, + "step": 2194944 + }, + { + "epoch": 1.02, + "learning_rate": 1.4053963572230197e-05, + "loss": 3.8555, + "step": 2195456 + }, + { + "epoch": 1.02, + "learning_rate": 1.4045577624719677e-05, + "loss": 3.8639, + "step": 2195968 + }, + { + "epoch": 1.02, + "learning_rate": 1.4037191677209157e-05, + "loss": 3.8592, + "step": 2196480 + }, + { + "epoch": 1.02, + "learning_rate": 1.4028805729698639e-05, + "loss": 3.857, + "step": 2196992 + }, + { + "epoch": 1.02, + "learning_rate": 1.4020419782188119e-05, + "loss": 3.8591, + "step": 2197504 + }, + { + "epoch": 1.02, + "learning_rate": 1.4012050213481328e-05, + "loss": 3.8588, + "step": 2198016 + }, + { + "epoch": 1.02, + "learning_rate": 1.400366426597081e-05, + "loss": 3.865, + "step": 2198528 + }, + { + "epoch": 1.02, + "learning_rate": 1.399527831846029e-05, + "loss": 3.8464, + "step": 2199040 + }, + { + "epoch": 1.02, + "learning_rate": 1.398689237094977e-05, + "loss": 3.8544, + "step": 2199552 + }, + { + "epoch": 1.02, + "learning_rate": 1.3978506423439248e-05, + "loss": 3.8504, + "step": 2200064 + }, + { + "epoch": 1.02, + "learning_rate": 1.3970120475928728e-05, + "loss": 3.8552, + "step": 2200576 + }, + { + "epoch": 1.02, + "learning_rate": 1.396175090722194e-05, + "loss": 3.8543, + "step": 2201088 + }, + { + "epoch": 1.02, + "learning_rate": 1.3953364959711418e-05, + "loss": 3.8509, + "step": 2201600 + }, + { + "epoch": 1.02, + "learning_rate": 1.3944979012200898e-05, + "loss": 3.8466, + "step": 2202112 + }, + { + "epoch": 1.02, + "learning_rate": 1.3936593064690378e-05, + "loss": 3.8485, + "step": 2202624 + }, + { + "epoch": 1.02, + "learning_rate": 1.3928207117179858e-05, + "loss": 3.867, + "step": 2203136 + }, + { + "epoch": 1.02, + "learning_rate": 1.3919837548473069e-05, + "loss": 3.858, + "step": 2203648 + }, + { + "epoch": 1.02, + "learning_rate": 1.3911451600962549e-05, + "loss": 3.8638, + "step": 2204160 + }, + { + "epoch": 1.02, + "learning_rate": 1.3903065653452029e-05, + "loss": 3.8504, + "step": 2204672 + }, + { + "epoch": 1.02, + "learning_rate": 1.389469608474524e-05, + "loss": 3.8633, + "step": 2205184 + }, + { + "epoch": 1.02, + "learning_rate": 1.388631013723472e-05, + "loss": 3.8644, + "step": 2205696 + }, + { + "epoch": 1.02, + "learning_rate": 1.3877924189724201e-05, + "loss": 3.8578, + "step": 2206208 + }, + { + "epoch": 1.02, + "learning_rate": 1.3869538242213681e-05, + "loss": 3.8531, + "step": 2206720 + }, + { + "epoch": 1.02, + "learning_rate": 1.3861152294703161e-05, + "loss": 3.8586, + "step": 2207232 + }, + { + "epoch": 1.02, + "learning_rate": 1.3852766347192641e-05, + "loss": 3.863, + "step": 2207744 + }, + { + "epoch": 1.02, + "learning_rate": 1.3844380399682121e-05, + "loss": 3.8667, + "step": 2208256 + }, + { + "epoch": 1.02, + "learning_rate": 1.38359944521716e-05, + "loss": 3.8521, + "step": 2208768 + }, + { + "epoch": 1.02, + "learning_rate": 1.382760850466108e-05, + "loss": 3.8555, + "step": 2209280 + }, + { + "epoch": 1.02, + "learning_rate": 1.381922255715056e-05, + "loss": 3.8578, + "step": 2209792 + }, + { + "epoch": 1.02, + "learning_rate": 1.3810836609640041e-05, + "loss": 3.8577, + "step": 2210304 + }, + { + "epoch": 1.02, + "learning_rate": 1.3802450662129521e-05, + "loss": 3.8497, + "step": 2210816 + }, + { + "epoch": 1.02, + "learning_rate": 1.3794081093422732e-05, + "loss": 3.8612, + "step": 2211328 + }, + { + "epoch": 1.02, + "learning_rate": 1.3785695145912212e-05, + "loss": 3.8524, + "step": 2211840 + }, + { + "epoch": 1.02, + "learning_rate": 1.3777309198401692e-05, + "loss": 3.8631, + "step": 2212352 + }, + { + "epoch": 1.02, + "learning_rate": 1.3768923250891172e-05, + "loss": 3.8532, + "step": 2212864 + }, + { + "epoch": 1.03, + "eval_loss": 3.9748947620391846, + "eval_runtime": 294.0024, + "eval_samples_per_second": 1297.918, + "eval_steps_per_second": 40.561, + "step": 2213280 + }, + { + "epoch": 0.0, + "learning_rate": 1.3760553682184382e-05, + "loss": 3.8688, + "step": 2213376 + }, + { + "epoch": 0.0, + "learning_rate": 1.3752167734673862e-05, + "loss": 3.8511, + "step": 2213888 + }, + { + "epoch": 0.0, + "learning_rate": 1.3743781787163342e-05, + "loss": 3.8568, + "step": 2214400 + }, + { + "epoch": 0.0, + "learning_rate": 1.3735395839652822e-05, + "loss": 3.8614, + "step": 2214912 + }, + { + "epoch": 0.0, + "learning_rate": 1.3727009892142304e-05, + "loss": 3.8595, + "step": 2215424 + }, + { + "epoch": 0.0, + "learning_rate": 1.371862394463178e-05, + "loss": 3.8581, + "step": 2215936 + }, + { + "epoch": 0.0, + "learning_rate": 1.371023799712126e-05, + "loss": 3.8571, + "step": 2216448 + }, + { + "epoch": 0.0, + "learning_rate": 1.3701852049610742e-05, + "loss": 3.8541, + "step": 2216960 + }, + { + "epoch": 0.0, + "learning_rate": 1.3693466102100222e-05, + "loss": 3.8538, + "step": 2217472 + }, + { + "epoch": 0.0, + "learning_rate": 1.3685080154589702e-05, + "loss": 3.8625, + "step": 2217984 + }, + { + "epoch": 0.0, + "learning_rate": 1.3676694207079182e-05, + "loss": 3.8586, + "step": 2218496 + }, + { + "epoch": 0.0, + "learning_rate": 1.3668308259568664e-05, + "loss": 3.8572, + "step": 2219008 + }, + { + "epoch": 0.0, + "learning_rate": 1.3659938690861873e-05, + "loss": 3.8693, + "step": 2219520 + }, + { + "epoch": 0.0, + "learning_rate": 1.3651552743351353e-05, + "loss": 3.842, + "step": 2220032 + }, + { + "epoch": 0.0, + "learning_rate": 1.3643166795840834e-05, + "loss": 3.8543, + "step": 2220544 + }, + { + "epoch": 0.0, + "learning_rate": 1.3634780848330311e-05, + "loss": 3.8404, + "step": 2221056 + }, + { + "epoch": 0.0, + "learning_rate": 1.3626394900819791e-05, + "loss": 3.865, + "step": 2221568 + }, + { + "epoch": 0.0, + "learning_rate": 1.3618008953309273e-05, + "loss": 3.8504, + "step": 2222080 + }, + { + "epoch": 0.0, + "learning_rate": 1.3609623005798753e-05, + "loss": 3.8525, + "step": 2222592 + }, + { + "epoch": 0.0, + "learning_rate": 1.3601237058288232e-05, + "loss": 3.8564, + "step": 2223104 + }, + { + "epoch": 0.0, + "learning_rate": 1.3592851110777712e-05, + "loss": 3.8669, + "step": 2223616 + }, + { + "epoch": 0.0, + "learning_rate": 1.3584465163267192e-05, + "loss": 3.8592, + "step": 2224128 + }, + { + "epoch": 0.0, + "learning_rate": 1.357607921575667e-05, + "loss": 3.8653, + "step": 2224640 + }, + { + "epoch": 0.0, + "learning_rate": 1.356769326824615e-05, + "loss": 3.8558, + "step": 2225152 + }, + { + "epoch": 0.0, + "learning_rate": 1.3559323699539365e-05, + "loss": 3.8628, + "step": 2225664 + }, + { + "epoch": 0.0, + "learning_rate": 1.3550937752028845e-05, + "loss": 3.8521, + "step": 2226176 + }, + { + "epoch": 0.0, + "learning_rate": 1.3542551804518321e-05, + "loss": 3.8524, + "step": 2226688 + }, + { + "epoch": 0.0, + "learning_rate": 1.3534165857007803e-05, + "loss": 3.8526, + "step": 2227200 + }, + { + "epoch": 0.0, + "learning_rate": 1.3525796288301015e-05, + "loss": 3.855, + "step": 2227712 + }, + { + "epoch": 0.0, + "learning_rate": 1.3517410340790492e-05, + "loss": 3.8483, + "step": 2228224 + }, + { + "epoch": 0.01, + "learning_rate": 1.3509040772083706e-05, + "loss": 3.8538, + "step": 2228736 + }, + { + "epoch": 0.01, + "learning_rate": 1.3500654824573186e-05, + "loss": 3.8572, + "step": 2229248 + }, + { + "epoch": 0.01, + "learning_rate": 1.3492268877062666e-05, + "loss": 3.8637, + "step": 2229760 + }, + { + "epoch": 0.01, + "learning_rate": 1.3483882929552144e-05, + "loss": 3.8612, + "step": 2230272 + }, + { + "epoch": 0.01, + "learning_rate": 1.3475496982041624e-05, + "loss": 3.8506, + "step": 2230784 + }, + { + "epoch": 0.01, + "learning_rate": 1.3467127413334837e-05, + "loss": 3.8523, + "step": 2231296 + }, + { + "epoch": 0.01, + "learning_rate": 1.3458757844628048e-05, + "loss": 3.8665, + "step": 2231808 + }, + { + "epoch": 0.01, + "learning_rate": 1.3450371897117528e-05, + "loss": 3.8402, + "step": 2232320 + }, + { + "epoch": 0.01, + "learning_rate": 1.3441985949607007e-05, + "loss": 3.8597, + "step": 2232832 + }, + { + "epoch": 0.01, + "learning_rate": 1.3433600002096489e-05, + "loss": 3.8506, + "step": 2233344 + }, + { + "epoch": 0.01, + "learning_rate": 1.3425214054585966e-05, + "loss": 3.8428, + "step": 2233856 + }, + { + "epoch": 0.01, + "learning_rate": 1.3416828107075446e-05, + "loss": 3.8548, + "step": 2234368 + }, + { + "epoch": 0.01, + "learning_rate": 1.340845853836866e-05, + "loss": 3.8628, + "step": 2234880 + }, + { + "epoch": 0.01, + "learning_rate": 1.340007259085814e-05, + "loss": 3.8542, + "step": 2235392 + }, + { + "epoch": 0.01, + "learning_rate": 1.3391686643347618e-05, + "loss": 3.8549, + "step": 2235904 + }, + { + "epoch": 0.01, + "learning_rate": 1.3383300695837098e-05, + "loss": 3.8543, + "step": 2236416 + }, + { + "epoch": 0.01, + "learning_rate": 1.3374914748326578e-05, + "loss": 3.853, + "step": 2236928 + }, + { + "epoch": 0.01, + "learning_rate": 1.3366528800816058e-05, + "loss": 3.8613, + "step": 2237440 + }, + { + "epoch": 0.01, + "learning_rate": 1.3358142853305538e-05, + "loss": 3.834, + "step": 2237952 + }, + { + "epoch": 0.01, + "learning_rate": 1.334975690579502e-05, + "loss": 3.8526, + "step": 2238464 + }, + { + "epoch": 0.01, + "learning_rate": 1.3341370958284496e-05, + "loss": 3.8536, + "step": 2238976 + }, + { + "epoch": 0.01, + "learning_rate": 1.3332985010773976e-05, + "loss": 3.8664, + "step": 2239488 + }, + { + "epoch": 0.01, + "learning_rate": 1.3324599063263458e-05, + "loss": 3.8465, + "step": 2240000 + }, + { + "epoch": 0.01, + "learning_rate": 1.3316213115752938e-05, + "loss": 3.8527, + "step": 2240512 + }, + { + "epoch": 0.01, + "learning_rate": 1.3307843547046148e-05, + "loss": 3.8377, + "step": 2241024 + }, + { + "epoch": 0.01, + "learning_rate": 1.3299457599535628e-05, + "loss": 3.8473, + "step": 2241536 + }, + { + "epoch": 0.01, + "learning_rate": 1.3291071652025108e-05, + "loss": 3.8609, + "step": 2242048 + }, + { + "epoch": 0.01, + "learning_rate": 1.3282685704514588e-05, + "loss": 3.8321, + "step": 2242560 + }, + { + "epoch": 0.01, + "learning_rate": 1.3274316135807799e-05, + "loss": 3.8644, + "step": 2243072 + }, + { + "epoch": 0.01, + "learning_rate": 1.3265930188297279e-05, + "loss": 3.8538, + "step": 2243584 + }, + { + "epoch": 0.01, + "learning_rate": 1.3257544240786759e-05, + "loss": 3.8442, + "step": 2244096 + }, + { + "epoch": 0.01, + "learning_rate": 1.3249158293276239e-05, + "loss": 3.8664, + "step": 2244608 + }, + { + "epoch": 0.01, + "learning_rate": 1.324077234576572e-05, + "loss": 3.8414, + "step": 2245120 + }, + { + "epoch": 0.01, + "learning_rate": 1.32323863982552e-05, + "loss": 3.8387, + "step": 2245632 + }, + { + "epoch": 0.01, + "learning_rate": 1.3224000450744677e-05, + "loss": 3.8513, + "step": 2246144 + }, + { + "epoch": 0.01, + "learning_rate": 1.3215614503234159e-05, + "loss": 3.8614, + "step": 2246656 + }, + { + "epoch": 0.01, + "learning_rate": 1.3207244934527371e-05, + "loss": 3.8439, + "step": 2247168 + }, + { + "epoch": 0.01, + "learning_rate": 1.3198858987016851e-05, + "loss": 3.8521, + "step": 2247680 + }, + { + "epoch": 0.01, + "learning_rate": 1.319047303950633e-05, + "loss": 3.8339, + "step": 2248192 + }, + { + "epoch": 0.01, + "learning_rate": 1.3182103470799542e-05, + "loss": 3.8511, + "step": 2248704 + }, + { + "epoch": 0.01, + "learning_rate": 1.3173717523289022e-05, + "loss": 3.8577, + "step": 2249216 + }, + { + "epoch": 0.01, + "learning_rate": 1.3165331575778504e-05, + "loss": 3.8633, + "step": 2249728 + }, + { + "epoch": 0.01, + "learning_rate": 1.315694562826798e-05, + "loss": 3.8526, + "step": 2250240 + }, + { + "epoch": 0.01, + "learning_rate": 1.314855968075746e-05, + "loss": 3.8582, + "step": 2250752 + }, + { + "epoch": 0.01, + "learning_rate": 1.3140173733246942e-05, + "loss": 3.8686, + "step": 2251264 + }, + { + "epoch": 0.01, + "learning_rate": 1.3131804164540151e-05, + "loss": 3.8551, + "step": 2251776 + }, + { + "epoch": 0.01, + "learning_rate": 1.312341821702963e-05, + "loss": 3.8566, + "step": 2252288 + }, + { + "epoch": 0.01, + "learning_rate": 1.3115032269519112e-05, + "loss": 3.8507, + "step": 2252800 + }, + { + "epoch": 0.01, + "learning_rate": 1.3106646322008592e-05, + "loss": 3.8541, + "step": 2253312 + }, + { + "epoch": 0.01, + "learning_rate": 1.3098260374498072e-05, + "loss": 3.847, + "step": 2253824 + }, + { + "epoch": 0.01, + "learning_rate": 1.3089874426987552e-05, + "loss": 3.8561, + "step": 2254336 + }, + { + "epoch": 0.01, + "learning_rate": 1.3081488479477034e-05, + "loss": 3.8528, + "step": 2254848 + }, + { + "epoch": 0.01, + "learning_rate": 1.307310253196651e-05, + "loss": 3.867, + "step": 2255360 + }, + { + "epoch": 0.01, + "learning_rate": 1.3064732963259723e-05, + "loss": 3.854, + "step": 2255872 + }, + { + "epoch": 0.01, + "learning_rate": 1.3056363394552934e-05, + "loss": 3.8445, + "step": 2256384 + }, + { + "epoch": 0.01, + "learning_rate": 1.3047977447042414e-05, + "loss": 3.8456, + "step": 2256896 + }, + { + "epoch": 0.01, + "learning_rate": 1.3039591499531895e-05, + "loss": 3.8577, + "step": 2257408 + }, + { + "epoch": 0.01, + "learning_rate": 1.3031205552021375e-05, + "loss": 3.8445, + "step": 2257920 + }, + { + "epoch": 0.01, + "learning_rate": 1.3022819604510855e-05, + "loss": 3.859, + "step": 2258432 + }, + { + "epoch": 0.01, + "learning_rate": 1.3014433657000334e-05, + "loss": 3.8495, + "step": 2258944 + }, + { + "epoch": 0.02, + "learning_rate": 1.3006047709489814e-05, + "loss": 3.8475, + "step": 2259456 + }, + { + "epoch": 0.02, + "learning_rate": 1.2997661761979294e-05, + "loss": 3.8495, + "step": 2259968 + }, + { + "epoch": 0.02, + "learning_rate": 1.2989292193272506e-05, + "loss": 3.8505, + "step": 2260480 + }, + { + "epoch": 0.02, + "learning_rate": 1.2980906245761984e-05, + "loss": 3.8575, + "step": 2260992 + }, + { + "epoch": 0.02, + "learning_rate": 1.2972536677055197e-05, + "loss": 3.864, + "step": 2261504 + }, + { + "epoch": 0.02, + "learning_rate": 1.2964150729544677e-05, + "loss": 3.8597, + "step": 2262016 + }, + { + "epoch": 0.02, + "learning_rate": 1.2955764782034158e-05, + "loss": 3.8447, + "step": 2262528 + }, + { + "epoch": 0.02, + "learning_rate": 1.2947378834523635e-05, + "loss": 3.8545, + "step": 2263040 + }, + { + "epoch": 0.02, + "learning_rate": 1.2938992887013115e-05, + "loss": 3.8464, + "step": 2263552 + }, + { + "epoch": 0.02, + "learning_rate": 1.2930606939502597e-05, + "loss": 3.8557, + "step": 2264064 + }, + { + "epoch": 0.02, + "learning_rate": 1.2922220991992076e-05, + "loss": 3.8603, + "step": 2264576 + }, + { + "epoch": 0.02, + "learning_rate": 1.2913835044481556e-05, + "loss": 3.8436, + "step": 2265088 + }, + { + "epoch": 0.02, + "learning_rate": 1.2905465475774767e-05, + "loss": 3.8598, + "step": 2265600 + }, + { + "epoch": 0.02, + "learning_rate": 1.2897079528264247e-05, + "loss": 3.8527, + "step": 2266112 + }, + { + "epoch": 0.02, + "learning_rate": 1.2888709959557458e-05, + "loss": 3.8518, + "step": 2266624 + }, + { + "epoch": 0.02, + "learning_rate": 1.2880324012046938e-05, + "loss": 3.8477, + "step": 2267136 + }, + { + "epoch": 0.02, + "learning_rate": 1.2871938064536418e-05, + "loss": 3.8462, + "step": 2267648 + }, + { + "epoch": 0.02, + "learning_rate": 1.2863552117025898e-05, + "loss": 3.8526, + "step": 2268160 + }, + { + "epoch": 0.02, + "learning_rate": 1.2855166169515378e-05, + "loss": 3.8538, + "step": 2268672 + }, + { + "epoch": 0.02, + "learning_rate": 1.284678022200486e-05, + "loss": 3.8476, + "step": 2269184 + }, + { + "epoch": 0.02, + "learning_rate": 1.283839427449434e-05, + "loss": 3.8404, + "step": 2269696 + }, + { + "epoch": 0.02, + "learning_rate": 1.283002470578755e-05, + "loss": 3.851, + "step": 2270208 + }, + { + "epoch": 0.02, + "learning_rate": 1.282163875827703e-05, + "loss": 3.8618, + "step": 2270720 + }, + { + "epoch": 0.02, + "learning_rate": 1.281325281076651e-05, + "loss": 3.8482, + "step": 2271232 + }, + { + "epoch": 0.02, + "learning_rate": 1.2804883242059721e-05, + "loss": 3.8524, + "step": 2271744 + }, + { + "epoch": 0.02, + "learning_rate": 1.27964972945492e-05, + "loss": 3.8565, + "step": 2272256 + }, + { + "epoch": 0.02, + "learning_rate": 1.278811134703868e-05, + "loss": 3.8615, + "step": 2272768 + }, + { + "epoch": 0.02, + "learning_rate": 1.277972539952816e-05, + "loss": 3.8537, + "step": 2273280 + }, + { + "epoch": 0.02, + "learning_rate": 1.2771339452017639e-05, + "loss": 3.8541, + "step": 2273792 + }, + { + "epoch": 0.02, + "learning_rate": 1.2762953504507119e-05, + "loss": 3.8603, + "step": 2274304 + }, + { + "epoch": 0.02, + "learning_rate": 1.2754567556996599e-05, + "loss": 3.8586, + "step": 2274816 + }, + { + "epoch": 0.02, + "learning_rate": 1.274618160948608e-05, + "loss": 3.8448, + "step": 2275328 + }, + { + "epoch": 0.02, + "learning_rate": 1.273779566197556e-05, + "loss": 3.8521, + "step": 2275840 + }, + { + "epoch": 0.02, + "learning_rate": 1.272940971446504e-05, + "loss": 3.8437, + "step": 2276352 + }, + { + "epoch": 0.02, + "learning_rate": 1.2721040145758251e-05, + "loss": 3.8551, + "step": 2276864 + }, + { + "epoch": 0.02, + "learning_rate": 1.2712654198247731e-05, + "loss": 3.8512, + "step": 2277376 + }, + { + "epoch": 0.02, + "learning_rate": 1.2704268250737211e-05, + "loss": 3.8437, + "step": 2277888 + }, + { + "epoch": 0.02, + "learning_rate": 1.2695882303226691e-05, + "loss": 3.8425, + "step": 2278400 + }, + { + "epoch": 0.02, + "learning_rate": 1.2687512734519902e-05, + "loss": 3.8488, + "step": 2278912 + }, + { + "epoch": 0.02, + "learning_rate": 1.2679126787009382e-05, + "loss": 3.8621, + "step": 2279424 + }, + { + "epoch": 0.02, + "learning_rate": 1.2670740839498862e-05, + "loss": 3.8561, + "step": 2279936 + }, + { + "epoch": 0.02, + "learning_rate": 1.2662354891988343e-05, + "loss": 3.8571, + "step": 2280448 + }, + { + "epoch": 0.02, + "learning_rate": 1.265396894447782e-05, + "loss": 3.8464, + "step": 2280960 + }, + { + "epoch": 0.02, + "learning_rate": 1.2645599375771033e-05, + "loss": 3.8615, + "step": 2281472 + }, + { + "epoch": 0.02, + "learning_rate": 1.2637213428260514e-05, + "loss": 3.8624, + "step": 2281984 + }, + { + "epoch": 0.02, + "learning_rate": 1.262882748074999e-05, + "loss": 3.8574, + "step": 2282496 + }, + { + "epoch": 0.02, + "learning_rate": 1.262044153323947e-05, + "loss": 3.8489, + "step": 2283008 + }, + { + "epoch": 0.02, + "learning_rate": 1.2612071964532685e-05, + "loss": 3.8559, + "step": 2283520 + }, + { + "epoch": 0.02, + "learning_rate": 1.2603686017022165e-05, + "loss": 3.8605, + "step": 2284032 + }, + { + "epoch": 0.02, + "learning_rate": 1.2595300069511643e-05, + "loss": 3.8607, + "step": 2284544 + }, + { + "epoch": 0.02, + "learning_rate": 1.2586914122001123e-05, + "loss": 3.8489, + "step": 2285056 + }, + { + "epoch": 0.02, + "learning_rate": 1.2578528174490603e-05, + "loss": 3.8472, + "step": 2285568 + }, + { + "epoch": 0.02, + "learning_rate": 1.2570142226980083e-05, + "loss": 3.856, + "step": 2286080 + }, + { + "epoch": 0.02, + "learning_rate": 1.2561756279469563e-05, + "loss": 3.8519, + "step": 2286592 + }, + { + "epoch": 0.02, + "learning_rate": 1.2553386710762774e-05, + "loss": 3.8462, + "step": 2287104 + }, + { + "epoch": 0.02, + "learning_rate": 1.2545000763252254e-05, + "loss": 3.8584, + "step": 2287616 + }, + { + "epoch": 0.02, + "learning_rate": 1.2536614815741735e-05, + "loss": 3.8498, + "step": 2288128 + }, + { + "epoch": 0.02, + "learning_rate": 1.2528228868231215e-05, + "loss": 3.8638, + "step": 2288640 + }, + { + "epoch": 0.02, + "learning_rate": 1.2519842920720695e-05, + "loss": 3.8436, + "step": 2289152 + }, + { + "epoch": 0.03, + "eval_loss": 3.9733269214630127, + "eval_runtime": 293.8227, + "eval_samples_per_second": 1298.712, + "eval_steps_per_second": 40.586, + "step": 2289600 + }, + { + "epoch": 1.0, + "learning_rate": 1.2511456973210174e-05, + "loss": 3.8554, + "step": 2289664 + }, + { + "epoch": 1.0, + "learning_rate": 1.2503071025699653e-05, + "loss": 3.8496, + "step": 2290176 + }, + { + "epoch": 1.0, + "learning_rate": 1.2494685078189133e-05, + "loss": 3.8527, + "step": 2290688 + }, + { + "epoch": 1.0, + "learning_rate": 1.2486315509482344e-05, + "loss": 3.8588, + "step": 2291200 + }, + { + "epoch": 1.0, + "learning_rate": 1.2477929561971826e-05, + "loss": 3.8561, + "step": 2291712 + }, + { + "epoch": 1.0, + "learning_rate": 1.2469559993265037e-05, + "loss": 3.8555, + "step": 2292224 + }, + { + "epoch": 1.0, + "learning_rate": 1.2461174045754517e-05, + "loss": 3.8519, + "step": 2292736 + }, + { + "epoch": 1.0, + "learning_rate": 1.2452788098243997e-05, + "loss": 3.8523, + "step": 2293248 + }, + { + "epoch": 1.0, + "learning_rate": 1.2444402150733477e-05, + "loss": 3.8501, + "step": 2293760 + }, + { + "epoch": 1.0, + "learning_rate": 1.2436016203222955e-05, + "loss": 3.8559, + "step": 2294272 + }, + { + "epoch": 1.0, + "learning_rate": 1.2427646634516167e-05, + "loss": 3.8555, + "step": 2294784 + }, + { + "epoch": 1.0, + "learning_rate": 1.2419260687005647e-05, + "loss": 3.8559, + "step": 2295296 + }, + { + "epoch": 1.0, + "learning_rate": 1.241089111829886e-05, + "loss": 3.8637, + "step": 2295808 + }, + { + "epoch": 1.0, + "learning_rate": 1.2402505170788338e-05, + "loss": 3.842, + "step": 2296320 + }, + { + "epoch": 1.0, + "learning_rate": 1.2394119223277818e-05, + "loss": 3.8477, + "step": 2296832 + }, + { + "epoch": 1.0, + "learning_rate": 1.2385733275767298e-05, + "loss": 3.8381, + "step": 2297344 + }, + { + "epoch": 1.0, + "learning_rate": 1.237734732825678e-05, + "loss": 3.864, + "step": 2297856 + }, + { + "epoch": 1.0, + "learning_rate": 1.2368961380746258e-05, + "loss": 3.8458, + "step": 2298368 + }, + { + "epoch": 1.0, + "learning_rate": 1.2360575433235738e-05, + "loss": 3.8486, + "step": 2298880 + }, + { + "epoch": 1.0, + "learning_rate": 1.2352189485725218e-05, + "loss": 3.8574, + "step": 2299392 + }, + { + "epoch": 1.0, + "learning_rate": 1.2343803538214698e-05, + "loss": 3.8627, + "step": 2299904 + }, + { + "epoch": 1.0, + "learning_rate": 1.2335433969507908e-05, + "loss": 3.8576, + "step": 2300416 + }, + { + "epoch": 1.0, + "learning_rate": 1.232704802199739e-05, + "loss": 3.8564, + "step": 2300928 + }, + { + "epoch": 1.0, + "learning_rate": 1.231866207448687e-05, + "loss": 3.8567, + "step": 2301440 + }, + { + "epoch": 1.0, + "learning_rate": 1.2310276126976348e-05, + "loss": 3.8591, + "step": 2301952 + }, + { + "epoch": 1.0, + "learning_rate": 1.2301890179465828e-05, + "loss": 3.8462, + "step": 2302464 + }, + { + "epoch": 1.0, + "learning_rate": 1.229352061075904e-05, + "loss": 3.8495, + "step": 2302976 + }, + { + "epoch": 1.0, + "learning_rate": 1.2285134663248519e-05, + "loss": 3.8519, + "step": 2303488 + }, + { + "epoch": 1.0, + "learning_rate": 1.2276748715738e-05, + "loss": 3.8493, + "step": 2304000 + }, + { + "epoch": 1.0, + "learning_rate": 1.226836276822748e-05, + "loss": 3.8428, + "step": 2304512 + }, + { + "epoch": 1.01, + "learning_rate": 1.225997682071696e-05, + "loss": 3.8506, + "step": 2305024 + }, + { + "epoch": 1.01, + "learning_rate": 1.2251590873206439e-05, + "loss": 3.8508, + "step": 2305536 + }, + { + "epoch": 1.01, + "learning_rate": 1.224320492569592e-05, + "loss": 3.8625, + "step": 2306048 + }, + { + "epoch": 1.01, + "learning_rate": 1.22348189781854e-05, + "loss": 3.8587, + "step": 2306560 + }, + { + "epoch": 1.01, + "learning_rate": 1.222644940947861e-05, + "loss": 3.8466, + "step": 2307072 + }, + { + "epoch": 1.01, + "learning_rate": 1.2218079840771822e-05, + "loss": 3.8519, + "step": 2307584 + }, + { + "epoch": 1.01, + "learning_rate": 1.2209693893261302e-05, + "loss": 3.8618, + "step": 2308096 + }, + { + "epoch": 1.01, + "learning_rate": 1.2201307945750782e-05, + "loss": 3.8366, + "step": 2308608 + }, + { + "epoch": 1.01, + "learning_rate": 1.2192921998240262e-05, + "loss": 3.8569, + "step": 2309120 + }, + { + "epoch": 1.01, + "learning_rate": 1.2184536050729742e-05, + "loss": 3.8439, + "step": 2309632 + }, + { + "epoch": 1.01, + "learning_rate": 1.2176150103219222e-05, + "loss": 3.8421, + "step": 2310144 + }, + { + "epoch": 1.01, + "learning_rate": 1.2167764155708702e-05, + "loss": 3.8518, + "step": 2310656 + }, + { + "epoch": 1.01, + "learning_rate": 1.2159394587001913e-05, + "loss": 3.8668, + "step": 2311168 + }, + { + "epoch": 1.01, + "learning_rate": 1.2151008639491393e-05, + "loss": 3.8452, + "step": 2311680 + }, + { + "epoch": 1.01, + "learning_rate": 1.2142622691980874e-05, + "loss": 3.8499, + "step": 2312192 + }, + { + "epoch": 1.01, + "learning_rate": 1.2134236744470352e-05, + "loss": 3.8521, + "step": 2312704 + }, + { + "epoch": 1.01, + "learning_rate": 1.2125850796959832e-05, + "loss": 3.8508, + "step": 2313216 + }, + { + "epoch": 1.01, + "learning_rate": 1.2117481228253045e-05, + "loss": 3.8554, + "step": 2313728 + }, + { + "epoch": 1.01, + "learning_rate": 1.2109095280742523e-05, + "loss": 3.8342, + "step": 2314240 + }, + { + "epoch": 1.01, + "learning_rate": 1.2100709333232003e-05, + "loss": 3.8526, + "step": 2314752 + }, + { + "epoch": 1.01, + "learning_rate": 1.2092339764525216e-05, + "loss": 3.8525, + "step": 2315264 + }, + { + "epoch": 1.01, + "learning_rate": 1.2083953817014696e-05, + "loss": 3.8587, + "step": 2315776 + }, + { + "epoch": 1.01, + "learning_rate": 1.2075567869504174e-05, + "loss": 3.8406, + "step": 2316288 + }, + { + "epoch": 1.01, + "learning_rate": 1.2067181921993655e-05, + "loss": 3.8429, + "step": 2316800 + }, + { + "epoch": 1.01, + "learning_rate": 1.2058812353286866e-05, + "loss": 3.8439, + "step": 2317312 + }, + { + "epoch": 1.01, + "learning_rate": 1.2050426405776346e-05, + "loss": 3.8382, + "step": 2317824 + }, + { + "epoch": 1.01, + "learning_rate": 1.2042040458265826e-05, + "loss": 3.8605, + "step": 2318336 + }, + { + "epoch": 1.01, + "learning_rate": 1.2033670889559037e-05, + "loss": 3.8294, + "step": 2318848 + }, + { + "epoch": 1.01, + "learning_rate": 1.2025284942048517e-05, + "loss": 3.8575, + "step": 2319360 + }, + { + "epoch": 1.01, + "learning_rate": 1.2016898994537997e-05, + "loss": 3.8507, + "step": 2319872 + }, + { + "epoch": 1.01, + "learning_rate": 1.2008513047027477e-05, + "loss": 3.8439, + "step": 2320384 + }, + { + "epoch": 1.01, + "learning_rate": 1.2000127099516957e-05, + "loss": 3.861, + "step": 2320896 + }, + { + "epoch": 1.01, + "learning_rate": 1.1991741152006437e-05, + "loss": 3.8396, + "step": 2321408 + }, + { + "epoch": 1.01, + "learning_rate": 1.1983355204495917e-05, + "loss": 3.8372, + "step": 2321920 + }, + { + "epoch": 1.01, + "learning_rate": 1.1974969256985397e-05, + "loss": 3.8404, + "step": 2322432 + }, + { + "epoch": 1.01, + "learning_rate": 1.1966583309474877e-05, + "loss": 3.8622, + "step": 2322944 + }, + { + "epoch": 1.01, + "learning_rate": 1.1958197361964357e-05, + "loss": 3.8437, + "step": 2323456 + }, + { + "epoch": 1.01, + "learning_rate": 1.1949811414453836e-05, + "loss": 3.8434, + "step": 2323968 + }, + { + "epoch": 1.01, + "learning_rate": 1.1941425466943316e-05, + "loss": 3.8355, + "step": 2324480 + }, + { + "epoch": 1.01, + "learning_rate": 1.1933039519432795e-05, + "loss": 3.8444, + "step": 2324992 + }, + { + "epoch": 1.01, + "learning_rate": 1.1924653571922276e-05, + "loss": 3.8545, + "step": 2325504 + }, + { + "epoch": 1.01, + "learning_rate": 1.1916267624411756e-05, + "loss": 3.8599, + "step": 2326016 + }, + { + "epoch": 1.01, + "learning_rate": 1.1907881676901236e-05, + "loss": 3.8473, + "step": 2326528 + }, + { + "epoch": 1.01, + "learning_rate": 1.1899512108194447e-05, + "loss": 3.8585, + "step": 2327040 + }, + { + "epoch": 1.01, + "learning_rate": 1.1891126160683927e-05, + "loss": 3.8645, + "step": 2327552 + }, + { + "epoch": 1.01, + "learning_rate": 1.1882740213173407e-05, + "loss": 3.8511, + "step": 2328064 + }, + { + "epoch": 1.01, + "learning_rate": 1.187437064446662e-05, + "loss": 3.8518, + "step": 2328576 + }, + { + "epoch": 1.01, + "learning_rate": 1.1865984696956098e-05, + "loss": 3.8473, + "step": 2329088 + }, + { + "epoch": 1.01, + "learning_rate": 1.1857598749445578e-05, + "loss": 3.852, + "step": 2329600 + }, + { + "epoch": 1.01, + "learning_rate": 1.1849212801935058e-05, + "loss": 3.845, + "step": 2330112 + }, + { + "epoch": 1.01, + "learning_rate": 1.1840826854424538e-05, + "loss": 3.853, + "step": 2330624 + }, + { + "epoch": 1.01, + "learning_rate": 1.1832440906914018e-05, + "loss": 3.8551, + "step": 2331136 + }, + { + "epoch": 1.01, + "learning_rate": 1.1824054959403497e-05, + "loss": 3.8637, + "step": 2331648 + }, + { + "epoch": 1.01, + "learning_rate": 1.1815669011892977e-05, + "loss": 3.8528, + "step": 2332160 + }, + { + "epoch": 1.01, + "learning_rate": 1.180731582198992e-05, + "loss": 3.8384, + "step": 2332672 + }, + { + "epoch": 1.01, + "learning_rate": 1.17989298744794e-05, + "loss": 3.841, + "step": 2333184 + }, + { + "epoch": 1.01, + "learning_rate": 1.179054392696888e-05, + "loss": 3.8541, + "step": 2333696 + }, + { + "epoch": 1.01, + "learning_rate": 1.1782157979458359e-05, + "loss": 3.8429, + "step": 2334208 + }, + { + "epoch": 1.01, + "learning_rate": 1.177377203194784e-05, + "loss": 3.8543, + "step": 2334720 + }, + { + "epoch": 1.01, + "learning_rate": 1.176538608443732e-05, + "loss": 3.8487, + "step": 2335232 + }, + { + "epoch": 1.02, + "learning_rate": 1.17570001369268e-05, + "loss": 3.844, + "step": 2335744 + }, + { + "epoch": 1.02, + "learning_rate": 1.1748614189416279e-05, + "loss": 3.8411, + "step": 2336256 + }, + { + "epoch": 1.02, + "learning_rate": 1.1740244620709491e-05, + "loss": 3.8491, + "step": 2336768 + }, + { + "epoch": 1.02, + "learning_rate": 1.1731858673198971e-05, + "loss": 3.855, + "step": 2337280 + }, + { + "epoch": 1.02, + "learning_rate": 1.1723489104492184e-05, + "loss": 3.8596, + "step": 2337792 + }, + { + "epoch": 1.02, + "learning_rate": 1.1715103156981662e-05, + "loss": 3.853, + "step": 2338304 + }, + { + "epoch": 1.02, + "learning_rate": 1.1706717209471142e-05, + "loss": 3.8434, + "step": 2338816 + }, + { + "epoch": 1.02, + "learning_rate": 1.1698331261960622e-05, + "loss": 3.8486, + "step": 2339328 + }, + { + "epoch": 1.02, + "learning_rate": 1.1689945314450102e-05, + "loss": 3.8487, + "step": 2339840 + }, + { + "epoch": 1.02, + "learning_rate": 1.1681559366939582e-05, + "loss": 3.8502, + "step": 2340352 + }, + { + "epoch": 1.02, + "learning_rate": 1.1673173419429062e-05, + "loss": 3.8555, + "step": 2340864 + }, + { + "epoch": 1.02, + "learning_rate": 1.1664803850722274e-05, + "loss": 3.8371, + "step": 2341376 + }, + { + "epoch": 1.02, + "learning_rate": 1.1656434282015483e-05, + "loss": 3.8542, + "step": 2341888 + }, + { + "epoch": 1.02, + "learning_rate": 1.1648048334504965e-05, + "loss": 3.8496, + "step": 2342400 + }, + { + "epoch": 1.02, + "learning_rate": 1.1639662386994445e-05, + "loss": 3.8471, + "step": 2342912 + }, + { + "epoch": 1.02, + "learning_rate": 1.1631276439483923e-05, + "loss": 3.8433, + "step": 2343424 + }, + { + "epoch": 1.02, + "learning_rate": 1.1622890491973403e-05, + "loss": 3.8441, + "step": 2343936 + }, + { + "epoch": 1.02, + "learning_rate": 1.1614504544462885e-05, + "loss": 3.8488, + "step": 2344448 + }, + { + "epoch": 1.02, + "learning_rate": 1.1606118596952365e-05, + "loss": 3.8517, + "step": 2344960 + }, + { + "epoch": 1.02, + "learning_rate": 1.1597732649441843e-05, + "loss": 3.8426, + "step": 2345472 + }, + { + "epoch": 1.02, + "learning_rate": 1.1589363080735055e-05, + "loss": 3.8371, + "step": 2345984 + }, + { + "epoch": 1.02, + "learning_rate": 1.1580993512028266e-05, + "loss": 3.8432, + "step": 2346496 + }, + { + "epoch": 1.02, + "learning_rate": 1.1572607564517746e-05, + "loss": 3.8584, + "step": 2347008 + }, + { + "epoch": 1.02, + "learning_rate": 1.1564221617007226e-05, + "loss": 3.8475, + "step": 2347520 + }, + { + "epoch": 1.02, + "learning_rate": 1.1555835669496706e-05, + "loss": 3.8461, + "step": 2348032 + }, + { + "epoch": 1.02, + "learning_rate": 1.1547449721986186e-05, + "loss": 3.8561, + "step": 2348544 + }, + { + "epoch": 1.02, + "learning_rate": 1.1539063774475666e-05, + "loss": 3.8577, + "step": 2349056 + }, + { + "epoch": 1.02, + "learning_rate": 1.1530677826965146e-05, + "loss": 3.8481, + "step": 2349568 + }, + { + "epoch": 1.02, + "learning_rate": 1.1522291879454626e-05, + "loss": 3.8516, + "step": 2350080 + }, + { + "epoch": 1.02, + "learning_rate": 1.1513922310747837e-05, + "loss": 3.8576, + "step": 2350592 + }, + { + "epoch": 1.02, + "learning_rate": 1.1505536363237317e-05, + "loss": 3.8537, + "step": 2351104 + }, + { + "epoch": 1.02, + "learning_rate": 1.1497150415726797e-05, + "loss": 3.84, + "step": 2351616 + }, + { + "epoch": 1.02, + "learning_rate": 1.1488764468216277e-05, + "loss": 3.8486, + "step": 2352128 + }, + { + "epoch": 1.02, + "learning_rate": 1.1480378520705757e-05, + "loss": 3.8447, + "step": 2352640 + }, + { + "epoch": 1.02, + "learning_rate": 1.1471992573195237e-05, + "loss": 3.8474, + "step": 2353152 + }, + { + "epoch": 1.02, + "learning_rate": 1.1463606625684716e-05, + "loss": 3.8457, + "step": 2353664 + }, + { + "epoch": 1.02, + "learning_rate": 1.1455220678174196e-05, + "loss": 3.8419, + "step": 2354176 + }, + { + "epoch": 1.02, + "learning_rate": 1.1446851109467407e-05, + "loss": 3.8453, + "step": 2354688 + }, + { + "epoch": 1.02, + "learning_rate": 1.1438465161956887e-05, + "loss": 3.8485, + "step": 2355200 + }, + { + "epoch": 1.02, + "learning_rate": 1.1430079214446369e-05, + "loss": 3.8483, + "step": 2355712 + }, + { + "epoch": 1.02, + "learning_rate": 1.1421693266935847e-05, + "loss": 3.8589, + "step": 2356224 + }, + { + "epoch": 1.02, + "learning_rate": 1.1413307319425327e-05, + "loss": 3.8571, + "step": 2356736 + }, + { + "epoch": 1.02, + "learning_rate": 1.1404921371914807e-05, + "loss": 3.8406, + "step": 2357248 + }, + { + "epoch": 1.02, + "learning_rate": 1.1396551803208018e-05, + "loss": 3.8548, + "step": 2357760 + }, + { + "epoch": 1.02, + "learning_rate": 1.1388165855697498e-05, + "loss": 3.8554, + "step": 2358272 + }, + { + "epoch": 1.02, + "learning_rate": 1.1379779908186978e-05, + "loss": 3.8561, + "step": 2358784 + }, + { + "epoch": 1.02, + "learning_rate": 1.137139396067646e-05, + "loss": 3.8454, + "step": 2359296 + }, + { + "epoch": 1.02, + "learning_rate": 1.1363008013165938e-05, + "loss": 3.8527, + "step": 2359808 + }, + { + "epoch": 1.02, + "learning_rate": 1.135463844445915e-05, + "loss": 3.858, + "step": 2360320 + }, + { + "epoch": 1.02, + "learning_rate": 1.1346268875752361e-05, + "loss": 3.854, + "step": 2360832 + }, + { + "epoch": 1.02, + "learning_rate": 1.133788292824184e-05, + "loss": 3.8453, + "step": 2361344 + }, + { + "epoch": 1.02, + "learning_rate": 1.132949698073132e-05, + "loss": 3.846, + "step": 2361856 + }, + { + "epoch": 1.02, + "learning_rate": 1.13211110332208e-05, + "loss": 3.8524, + "step": 2362368 + }, + { + "epoch": 1.02, + "learning_rate": 1.131272508571028e-05, + "loss": 3.8468, + "step": 2362880 + }, + { + "epoch": 1.02, + "learning_rate": 1.130433913819976e-05, + "loss": 3.8411, + "step": 2363392 + }, + { + "epoch": 1.02, + "learning_rate": 1.129595319068924e-05, + "loss": 3.8559, + "step": 2363904 + }, + { + "epoch": 1.02, + "learning_rate": 1.128756724317872e-05, + "loss": 3.8466, + "step": 2364416 + }, + { + "epoch": 1.02, + "learning_rate": 1.1279181295668199e-05, + "loss": 3.8592, + "step": 2364928 + }, + { + "epoch": 1.02, + "learning_rate": 1.1270811726961411e-05, + "loss": 3.8406, + "step": 2365440 + }, + { + "epoch": 1.03, + "eval_loss": 3.972705602645874, + "eval_runtime": 292.2576, + "eval_samples_per_second": 1305.667, + "eval_steps_per_second": 40.803, + "step": 2365920 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 9.777656567619186e+17, + "trial_name": null, + "trial_params": null +}