abhinavp's picture
Training in progress, epoch 0, checkpoint
5fdd460 verified
{
"best_metric": 3.968932628631592,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/re-irr-sv-agr/transformer/1/checkpoints/checkpoint-228960",
"epoch": 0.025000606015738065,
"eval_steps": 10,
"global_step": 228960,
"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": 11.0276,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 6.8021,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 6.1657,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 5.9659,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 5.8071,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 5.7018,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 5.5962,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 5.5359,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 5.4402,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 5.3993,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 5.338,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 5.3128,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 5.2656,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989099906116697e-05,
"loss": 5.2117,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988261311365645e-05,
"loss": 5.1781,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.987422716614593e-05,
"loss": 5.1281,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 5.1052,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 5.0833,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.054,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.0234,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.0129,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.982391148108281e-05,
"loss": 4.9818,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 4.9619,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 4.9277,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 4.9254,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790384069844466e-05,
"loss": 4.8956,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9781998122333946e-05,
"loss": 4.8836,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 4.8629,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 4.8362,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756856658606115e-05,
"loss": 4.8213,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748470711095595e-05,
"loss": 4.804,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740101142388804e-05,
"loss": 4.7957,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731715194878284e-05,
"loss": 4.7803,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.97233456261715e-05,
"loss": 4.7726,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.971495967866098e-05,
"loss": 4.7597,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 4.7466,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969818778363994e-05,
"loss": 4.7344,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968980183612942e-05,
"loss": 4.6997,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.96814158886189e-05,
"loss": 4.6981,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967302994110837e-05,
"loss": 4.6868,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966464399359785e-05,
"loss": 4.6695,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 4.6729,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 4.6665,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963950252987002e-05,
"loss": 4.6459,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.96311165823595e-05,
"loss": 4.6451,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 4.6382,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 4.63,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 4.627,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959758917112116e-05,
"loss": 4.6066,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.95892359812181e-05,
"loss": 4.5942,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958085003370758e-05,
"loss": 4.5962,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957246408619706e-05,
"loss": 4.5816,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956407813868654e-05,
"loss": 4.5817,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.9555692191176016e-05,
"loss": 4.5545,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.9547306243665496e-05,
"loss": 4.5682,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.9538920296154976e-05,
"loss": 4.5432,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530534348644456e-05,
"loss": 4.5632,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.9522148401133936e-05,
"loss": 4.5377,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951376245362342e-05,
"loss": 4.5358,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950539288491663e-05,
"loss": 4.5275,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949700693740611e-05,
"loss": 4.5215,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948862098989559e-05,
"loss": 4.5078,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.948023504238507e-05,
"loss": 4.5121,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947186547367828e-05,
"loss": 4.4892,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946347952616776e-05,
"loss": 4.4831,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945510995746097e-05,
"loss": 4.4971,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944672400995045e-05,
"loss": 4.4867,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.943833806243993e-05,
"loss": 4.4762,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942995211492941e-05,
"loss": 4.46,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942156616741889e-05,
"loss": 4.4617,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.941318021990837e-05,
"loss": 4.4688,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404794272397856e-05,
"loss": 4.4631,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396408324887336e-05,
"loss": 4.4559,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388038756180545e-05,
"loss": 4.4538,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379652808670025e-05,
"loss": 4.4554,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371266861159505e-05,
"loss": 4.4489,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362897292452714e-05,
"loss": 4.4262,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.9354511344942194e-05,
"loss": 4.4268,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.9346125397431674e-05,
"loss": 4.4253,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.9337739449921154e-05,
"loss": 4.4178,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.9329353502410634e-05,
"loss": 4.418,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.9320967554900114e-05,
"loss": 4.41,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.9312581607389594e-05,
"loss": 4.4266,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930421203868281e-05,
"loss": 4.4016,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929582609117229e-05,
"loss": 4.3882,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.928744014366177e-05,
"loss": 4.3984,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927905419615125e-05,
"loss": 4.3951,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927066824864073e-05,
"loss": 4.3988,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.92622823011302e-05,
"loss": 4.3806,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925391273242342e-05,
"loss": 4.3827,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.92455267849129e-05,
"loss": 4.3806,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923714083740238e-05,
"loss": 4.3755,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922875488989185e-05,
"loss": 4.3623,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922036894238133e-05,
"loss": 4.3662,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921198299487081e-05,
"loss": 4.3675,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920361342616403e-05,
"loss": 4.3758,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919522747865351e-05,
"loss": 4.3542,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918684153114299e-05,
"loss": 4.3475,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917845558363247e-05,
"loss": 4.3471,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.917006963612195e-05,
"loss": 4.3435,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.916168368861143e-05,
"loss": 4.3529,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.915329774110091e-05,
"loss": 4.3364,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914491179359039e-05,
"loss": 4.3334,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136542224883596e-05,
"loss": 4.326,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.9128156277373076e-05,
"loss": 4.3348,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.9119770329862556e-05,
"loss": 4.3036,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.9111384382352036e-05,
"loss": 4.323,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.9103014813645245e-05,
"loss": 4.3156,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.909462886613473e-05,
"loss": 4.3238,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908624291862421e-05,
"loss": 4.3105,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907785697111369e-05,
"loss": 4.3161,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.906947102360317e-05,
"loss": 4.3038,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906108507609265e-05,
"loss": 4.3052,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905271550738586e-05,
"loss": 4.3091,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904432955987534e-05,
"loss": 4.2915,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903594361236482e-05,
"loss": 4.3073,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.90275576648543e-05,
"loss": 4.3058,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.901920447495124e-05,
"loss": 4.2974,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.901081852744072e-05,
"loss": 4.2871,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.90024325799302e-05,
"loss": 4.2855,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994046632419686e-05,
"loss": 4.2885,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985660684909166e-05,
"loss": 4.2847,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977274737398646e-05,
"loss": 4.2868,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968888789888125e-05,
"loss": 4.2754,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960502842377605e-05,
"loss": 4.2814,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952116894867085e-05,
"loss": 4.2659,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943730947356565e-05,
"loss": 4.2692,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.893534499984604e-05,
"loss": 4.2571,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.8926975431139254e-05,
"loss": 4.2602,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.8918589483628734e-05,
"loss": 4.2501,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.8910203536118214e-05,
"loss": 4.2717,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890181758860769e-05,
"loss": 4.277,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889343164109717e-05,
"loss": 4.262,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888504569358665e-05,
"loss": 4.241,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.8876659746076134e-05,
"loss": 4.2613,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.8868273798565614e-05,
"loss": 4.254,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885990422985882e-05,
"loss": 4.252,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.885153466115204e-05,
"loss": 4.2432,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884314871364151e-05,
"loss": 4.2515,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883476276613099e-05,
"loss": 4.2453,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882637681862047e-05,
"loss": 4.2394,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881799087110995e-05,
"loss": 4.2385,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.880960492359943e-05,
"loss": 4.2408,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880121897608891e-05,
"loss": 4.2284,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879284940738212e-05,
"loss": 4.2302,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.87844634598716e-05,
"loss": 4.242,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877607751236109e-05,
"loss": 4.2287,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876769156485057e-05,
"loss": 4.2271,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875930561734005e-05,
"loss": 4.2376,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875091966982953e-05,
"loss": 4.2191,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.213301658630371,
"eval_runtime": 302.9256,
"eval_samples_per_second": 1259.686,
"eval_steps_per_second": 39.366,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.874253372231901e-05,
"loss": 4.2016,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.873414777480849e-05,
"loss": 4.2101,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.87257782061017e-05,
"loss": 4.2246,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.871739225859118e-05,
"loss": 4.2134,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.8709022689884386e-05,
"loss": 4.2197,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.8700636742373866e-05,
"loss": 4.1985,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.8692250794863346e-05,
"loss": 4.2098,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.8683864847352826e-05,
"loss": 4.1902,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.867549527864604e-05,
"loss": 4.2064,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.866710933113552e-05,
"loss": 4.191,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.8658723383625e-05,
"loss": 4.2063,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865033743611448e-05,
"loss": 4.2009,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.864196786740769e-05,
"loss": 4.1943,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.863358191989717e-05,
"loss": 4.1819,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862519597238665e-05,
"loss": 4.1752,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.861681002487613e-05,
"loss": 4.1746,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.860842407736561e-05,
"loss": 4.1841,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860003812985509e-05,
"loss": 4.1819,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.859165218234457e-05,
"loss": 4.1756,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858326623483405e-05,
"loss": 4.1951,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.857488028732352e-05,
"loss": 4.1855,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.856649433981301e-05,
"loss": 4.1781,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.855810839230249e-05,
"loss": 4.1701,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.85497388235957e-05,
"loss": 4.1876,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.8541369254888915e-05,
"loss": 4.1607,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.8532983307378395e-05,
"loss": 4.1742,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.8524597359867875e-05,
"loss": 4.1702,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.851621141235735e-05,
"loss": 4.1639,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.850782546484683e-05,
"loss": 4.1553,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.849943951733631e-05,
"loss": 4.156,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.8491069948629524e-05,
"loss": 4.16,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.8482684001119e-05,
"loss": 4.1598,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847429805360848e-05,
"loss": 4.1607,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.8465912106097964e-05,
"loss": 4.1572,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.8457526158587444e-05,
"loss": 4.158,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.8449140211076924e-05,
"loss": 4.1525,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.844077064237013e-05,
"loss": 4.1348,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843238469485961e-05,
"loss": 4.1438,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842399874734909e-05,
"loss": 4.1361,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.841561279983857e-05,
"loss": 4.1326,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840724323113178e-05,
"loss": 4.1418,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.839885728362126e-05,
"loss": 4.1454,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839047133611074e-05,
"loss": 4.1332,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.838208538860022e-05,
"loss": 4.1331,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.83736994410897e-05,
"loss": 4.1352,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836531349357918e-05,
"loss": 4.1371,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.835692754606866e-05,
"loss": 4.1388,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834855797736188e-05,
"loss": 4.1281,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834017202985136e-05,
"loss": 4.1244,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.833178608234084e-05,
"loss": 4.1276,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.832340013483032e-05,
"loss": 4.1209,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.83150141873198e-05,
"loss": 4.1246,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.830662823980928e-05,
"loss": 4.113,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.8298258671102486e-05,
"loss": 4.1272,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.8289872723591966e-05,
"loss": 4.1018,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.8281486776081446e-05,
"loss": 4.1269,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273100828570926e-05,
"loss": 4.1136,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.8264731259864135e-05,
"loss": 4.1104,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.8256345312353615e-05,
"loss": 4.1199,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.8247959364843095e-05,
"loss": 4.1072,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823957341733258e-05,
"loss": 4.1012,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.823118746982206e-05,
"loss": 4.1162,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.822281790111527e-05,
"loss": 4.0891,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.821443195360475e-05,
"loss": 4.0907,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.820604600609423e-05,
"loss": 4.1058,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.819766005858371e-05,
"loss": 4.1042,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.8189274111073184e-05,
"loss": 4.0976,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.81809045423664e-05,
"loss": 4.0871,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817251859485588e-05,
"loss": 4.0881,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.816413264734535e-05,
"loss": 4.0958,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.815574669983483e-05,
"loss": 4.1038,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.814737713112805e-05,
"loss": 4.0949,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.8138991183617535e-05,
"loss": 4.0997,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.813060523610701e-05,
"loss": 4.0988,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.812221928859649e-05,
"loss": 4.0986,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.8113849719889704e-05,
"loss": 4.0787,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.8105463772379184e-05,
"loss": 4.0823,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.809707782486866e-05,
"loss": 4.091,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.808869187735814e-05,
"loss": 4.0796,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808030592984762e-05,
"loss": 4.0852,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.80719199823371e-05,
"loss": 4.0764,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806353403482658e-05,
"loss": 4.0978,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.8055164466119786e-05,
"loss": 4.0785,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804677851860927e-05,
"loss": 4.0674,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803839257109875e-05,
"loss": 4.077,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.803000662358823e-05,
"loss": 4.0801,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.802162067607771e-05,
"loss": 4.086,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801325110737092e-05,
"loss": 4.0693,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.80048651598604e-05,
"loss": 4.071,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.799647921234988e-05,
"loss": 4.0798,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.798809326483936e-05,
"loss": 4.0675,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.797972369613257e-05,
"loss": 4.0626,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797133774862205e-05,
"loss": 4.0671,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.796295180111153e-05,
"loss": 4.0738,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.795458223240474e-05,
"loss": 4.0757,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.794619628489423e-05,
"loss": 4.0707,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.793781033738371e-05,
"loss": 4.0542,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792942438987319e-05,
"loss": 4.0593,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792103844236267e-05,
"loss": 4.0612,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.791265249485215e-05,
"loss": 4.0646,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.790426654734163e-05,
"loss": 4.0621,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.7895880599831107e-05,
"loss": 4.0569,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.7887511031124316e-05,
"loss": 4.0485,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.7879125083613796e-05,
"loss": 4.0647,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.7870739136103276e-05,
"loss": 4.0309,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.7862353188592756e-05,
"loss": 4.0551,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.7853983619885965e-05,
"loss": 4.0468,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.7845597672375445e-05,
"loss": 4.0594,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.7837211724864925e-05,
"loss": 4.0448,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.782882577735441e-05,
"loss": 4.0547,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.782043982984389e-05,
"loss": 4.0435,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.781205388233337e-05,
"loss": 4.0453,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.7803667934822844e-05,
"loss": 4.0537,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.7795281987312324e-05,
"loss": 4.0405,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.778691241860554e-05,
"loss": 4.0521,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.777852647109502e-05,
"loss": 4.0577,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777015690238823e-05,
"loss": 4.0484,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.776177095487771e-05,
"loss": 4.0387,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775338500736719e-05,
"loss": 4.0424,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.774499905985666e-05,
"loss": 4.0466,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773661311234615e-05,
"loss": 4.0323,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.772822716483563e-05,
"loss": 4.0498,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.771984121732511e-05,
"loss": 4.0325,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771145526981459e-05,
"loss": 4.0428,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.77030857011078e-05,
"loss": 4.0346,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.769469975359728e-05,
"loss": 4.0329,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.768631380608676e-05,
"loss": 4.0214,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.767792785857624e-05,
"loss": 4.0261,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766955828986945e-05,
"loss": 4.0211,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766117234235893e-05,
"loss": 4.0412,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765278639484841e-05,
"loss": 4.05,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764440044733789e-05,
"loss": 4.0343,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.7636030878631096e-05,
"loss": 4.0163,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762764493112058e-05,
"loss": 4.0375,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761925898361006e-05,
"loss": 4.0276,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.761087303609954e-05,
"loss": 4.0291,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.760250346739275e-05,
"loss": 4.0258,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.759411751988223e-05,
"loss": 4.0283,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758573157237171e-05,
"loss": 4.0232,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.757734562486119e-05,
"loss": 4.0278,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.75689760561544e-05,
"loss": 4.0229,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.756059010864388e-05,
"loss": 4.0267,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.755220416113336e-05,
"loss": 4.0216,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.754383459242657e-05,
"loss": 4.0131,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.753544864491605e-05,
"loss": 4.0323,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.7527062697405536e-05,
"loss": 4.0237,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.7518676749895016e-05,
"loss": 4.0147,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.7510290802384496e-05,
"loss": 4.0302,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.7501904854873976e-05,
"loss": 4.0124,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.044633388519287,
"eval_runtime": 303.5157,
"eval_samples_per_second": 1257.236,
"eval_steps_per_second": 39.29,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.7493518907363456e-05,
"loss": 3.9987,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.7485132959852936e-05,
"loss": 4.0053,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.7476747012342416e-05,
"loss": 4.0223,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.7468361064831896e-05,
"loss": 4.015,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.7459975117321376e-05,
"loss": 4.0205,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.745158916981085e-05,
"loss": 4.0009,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.744320322230033e-05,
"loss": 4.0141,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.743481727478981e-05,
"loss": 3.9902,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.742643132727929e-05,
"loss": 4.0163,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.741804537976877e-05,
"loss": 3.9977,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.740965943225825e-05,
"loss": 4.0133,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.7401289863551465e-05,
"loss": 4.0083,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.739292029484468e-05,
"loss": 4.0045,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.7384534347334154e-05,
"loss": 3.9928,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.7376148399823634e-05,
"loss": 3.9908,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.7367762452313114e-05,
"loss": 3.9899,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.7359376504802594e-05,
"loss": 3.9968,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.7350990557292074e-05,
"loss": 3.9979,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.7342604609781554e-05,
"loss": 3.9954,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.7334218662271034e-05,
"loss": 4.0103,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732584909356424e-05,
"loss": 4.0039,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.731746314605372e-05,
"loss": 4.002,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.73090771985432e-05,
"loss": 3.9945,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.730069125103269e-05,
"loss": 4.0042,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.72923216823259e-05,
"loss": 3.9859,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.728393573481538e-05,
"loss": 3.9976,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.727554978730486e-05,
"loss": 3.9951,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.726716383979434e-05,
"loss": 3.991,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.725879427108755e-05,
"loss": 3.9811,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.725040832357703e-05,
"loss": 3.9831,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.724202237606651e-05,
"loss": 3.9863,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.7233652807359716e-05,
"loss": 3.993,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.7225266859849196e-05,
"loss": 3.9949,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.7216880912338676e-05,
"loss": 3.9861,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.7208494964828156e-05,
"loss": 3.9864,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.720010901731764e-05,
"loss": 3.9841,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.719172306980712e-05,
"loss": 3.9707,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.71833371222966e-05,
"loss": 3.9815,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.717496755358981e-05,
"loss": 3.9721,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.716658160607929e-05,
"loss": 3.9721,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.715819565856877e-05,
"loss": 3.9747,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.714980971105825e-05,
"loss": 3.985,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714144014235146e-05,
"loss": 3.9736,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.713305419484094e-05,
"loss": 3.9707,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.712466824733042e-05,
"loss": 3.9831,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.71162822998199e-05,
"loss": 3.976,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.710791273111311e-05,
"loss": 3.9837,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.709952678360259e-05,
"loss": 3.9686,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.709114083609208e-05,
"loss": 3.9639,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.708275488858156e-05,
"loss": 3.9759,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.7074385319874766e-05,
"loss": 3.9663,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.7065999372364246e-05,
"loss": 3.971,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.7057613424853726e-05,
"loss": 3.9608,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.7049227477343206e-05,
"loss": 3.9683,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.7040857908636415e-05,
"loss": 3.9546,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.7032471961125895e-05,
"loss": 3.97,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.7024086013615375e-05,
"loss": 3.9619,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.7015700066104855e-05,
"loss": 3.9615,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.7007314118594335e-05,
"loss": 3.9718,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.6998928171083814e-05,
"loss": 3.9549,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.6990542223573294e-05,
"loss": 3.9521,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.698217265486651e-05,
"loss": 3.9728,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.6973786707355983e-05,
"loss": 3.9432,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.6965400759845463e-05,
"loss": 3.9417,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.6957014812334943e-05,
"loss": 3.9574,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694864524362816e-05,
"loss": 3.9643,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694025929611763e-05,
"loss": 3.954,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693187334860711e-05,
"loss": 3.9437,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692348740109659e-05,
"loss": 3.9486,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.691511783238981e-05,
"loss": 3.9495,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.690673188487928e-05,
"loss": 3.9618,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.689834593736877e-05,
"loss": 3.9534,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.688995998985825e-05,
"loss": 3.9569,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.688159042115146e-05,
"loss": 3.957,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.687320447364094e-05,
"loss": 3.9616,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.686481852613042e-05,
"loss": 3.9404,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.68564325786199e-05,
"loss": 3.9445,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.6848063009913106e-05,
"loss": 3.9534,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.6839677062402586e-05,
"loss": 3.9407,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.6831291114892066e-05,
"loss": 3.9487,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.6822905167381546e-05,
"loss": 3.9405,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.6814535598674755e-05,
"loss": 3.9593,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.6806149651164235e-05,
"loss": 3.9446,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.679776370365372e-05,
"loss": 3.9344,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.67893777561432e-05,
"loss": 3.9389,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.678100818743641e-05,
"loss": 3.9453,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.677262223992589e-05,
"loss": 3.956,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.676423629241537e-05,
"loss": 3.9362,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675585034490485e-05,
"loss": 3.9409,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.674748077619806e-05,
"loss": 3.9386,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.673909482868754e-05,
"loss": 3.9461,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.673070888117702e-05,
"loss": 3.9331,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.67223229336665e-05,
"loss": 3.9328,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.671395336495971e-05,
"loss": 3.9463,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.6705583796252925e-05,
"loss": 3.9448,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.6697197848742405e-05,
"loss": 3.9434,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.6688811901231885e-05,
"loss": 3.9267,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.6680425953721365e-05,
"loss": 3.9319,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.6672040006210844e-05,
"loss": 3.9332,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.6663654058700324e-05,
"loss": 3.9371,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.6655268111189804e-05,
"loss": 3.9376,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.6646882163679284e-05,
"loss": 3.9295,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.6638512594972493e-05,
"loss": 3.9247,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.6630126647461973e-05,
"loss": 3.9379,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.662174069995145e-05,
"loss": 3.9098,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.661335475244093e-05,
"loss": 3.9277,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.660498518373414e-05,
"loss": 3.922,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.659659923622363e-05,
"loss": 3.9368,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.658821328871311e-05,
"loss": 3.9245,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.657982734120259e-05,
"loss": 3.9274,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.657144139369207e-05,
"loss": 3.921,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.656305544618155e-05,
"loss": 3.9244,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.655466949867103e-05,
"loss": 3.9325,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.654628355116051e-05,
"loss": 3.9241,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.653791398245372e-05,
"loss": 3.9321,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.65295280349432e-05,
"loss": 3.9348,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.652115846623641e-05,
"loss": 3.9321,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.651277251872589e-05,
"loss": 3.9209,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.650438657121537e-05,
"loss": 3.9183,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649600062370485e-05,
"loss": 3.9301,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648761467619433e-05,
"loss": 3.9128,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.647922872868381e-05,
"loss": 3.9303,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.6470842781173294e-05,
"loss": 3.9159,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.646245683366277e-05,
"loss": 3.9243,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.645408726495598e-05,
"loss": 3.92,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.644570131744546e-05,
"loss": 3.9193,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.643731536993494e-05,
"loss": 3.9029,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.6428929422424416e-05,
"loss": 3.9149,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.642055985371763e-05,
"loss": 3.9097,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.641217390620711e-05,
"loss": 3.921,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.640378795869659e-05,
"loss": 3.9331,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.6395402011186065e-05,
"loss": 3.9279,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.638703244247928e-05,
"loss": 3.896,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.637864649496876e-05,
"loss": 3.927,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.637026054745824e-05,
"loss": 3.9157,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636187459994772e-05,
"loss": 3.9172,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.6353505031240936e-05,
"loss": 3.9062,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.6345119083730416e-05,
"loss": 3.9186,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.633673313621989e-05,
"loss": 3.9113,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632834718870937e-05,
"loss": 3.9166,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.631996124119885e-05,
"loss": 3.9147,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.631157529368833e-05,
"loss": 3.9161,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.630318934617781e-05,
"loss": 3.9137,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.629481977747102e-05,
"loss": 3.9069,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.62864338299605e-05,
"loss": 3.9184,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.6278047882449985e-05,
"loss": 3.915,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.6269661934939465e-05,
"loss": 3.9069,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.6261275987428945e-05,
"loss": 3.9205,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.6252890039918425e-05,
"loss": 3.9042,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 3.968932628631592,
"eval_runtime": 308.6955,
"eval_samples_per_second": 1236.14,
"eval_steps_per_second": 38.63,
"step": 228960
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 1.5444074027470234e+17,
"trial_name": null,
"trial_params": null
}