| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.09854644000985464, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009854644000985464, | |
| "grad_norm": 0.23810631036758423, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 0.2963, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009854644000985464, | |
| "eval_loss": NaN, | |
| "eval_runtime": 39.8095, | |
| "eval_samples_per_second": 42.929, | |
| "eval_steps_per_second": 10.751, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001970928800197093, | |
| "grad_norm": 0.5004399418830872, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.3224, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0029563932002956393, | |
| "grad_norm": 0.31753167510032654, | |
| "learning_rate": 1.5e-06, | |
| "loss": 0.4478, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003941857600394186, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 14.4189, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004927322000492732, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005912786400591279, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006898250800689825, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5e-06, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.007883715200788372, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.008869179600886918, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5e-06, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.009854644000985464, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-06, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01084010840108401, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.99847706754774e-06, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.011825572801182557, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.993910125649561e-06, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.012811037201281104, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.986304738420684e-06, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01379650160137965, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.975670171853926e-06, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.014781966001478197, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.962019382530521e-06, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.015767430401576743, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.9453690018345144e-06, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01675289480167529, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.925739315689991e-06, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.017738359201773836, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.903154239845798e-06, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.018723823601872382, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8776412907378845e-06, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01970928800197093, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.849231551964771e-06, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.020694752402069475, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.817959636416969e-06, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02168021680216802, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.783863644106502e-06, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.022665681202266568, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.746985115747918e-06, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.023651145602365115, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.707368982147318e-06, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02463661000246366, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.665063509461098e-06, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.025622074402562207, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.620120240391065e-06, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.026607538802660754, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.572593931387604e-06, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0275930032027593, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.522542485937369e-06, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.028578467602857847, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.470026884016805e-06, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.029563932002956393, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.415111107797445e-06, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03054939640305494, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.357862063693486e-06, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.031534860803153486, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2983495008466285e-06, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.032520325203252036, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.236645926147493e-06, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.03350578960335058, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.172826515897146e-06, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.03449125400344913, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.106969024216348e-06, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03547671840354767, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.039153688314146e-06, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.03646218280364622, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.969463130731183e-06, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.037447647203744765, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.897982258676867e-06, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.038433111603843315, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.824798160583012e-06, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.03941857600394186, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04040404040404041, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6736789069647273e-06, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.04138950480413895, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.595927866972694e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0423749692042375, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.516841607689501e-06, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.04336043360433604, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.436516483539781e-06, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.04434589800443459, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3550503583141726e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.045331362404533136, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.272542485937369e-06, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.046316826804631686, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.189093389542498e-06, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.04730229120473023, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.1048047389991693e-06, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.04828775560482878, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.019779227044398e-06, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.04927322000492732, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9341204441673267e-06, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04927322000492732, | |
| "eval_loss": NaN, | |
| "eval_runtime": 38.4642, | |
| "eval_samples_per_second": 44.431, | |
| "eval_steps_per_second": 11.127, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05025868440502587, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.847932752400164e-06, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.051244148805124415, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.761321158169134e-06, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.052229613205222965, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6743911843603134e-06, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.05321507760532151, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.587248741756253e-06, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.05420054200542006, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.0551860064055186, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4127512582437486e-06, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.05617147080561715, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.325608815639687e-06, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.057156935205715693, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.238678841830867e-06, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.05814239960581424, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1520672475998374e-06, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.059127864005912786, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0658795558326745e-06, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.060113328406011336, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9802207729556023e-06, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.06109879280610988, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.895195261000831e-06, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.06208425720620843, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8109066104575023e-06, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.06306972160630697, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7274575140626318e-06, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.06405518600640552, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6449496416858285e-06, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.06504065040650407, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.56348351646022e-06, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.06602611480660261, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4831583923105e-06, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.06701157920670116, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4040721330273063e-06, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.0679970436067997, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3263210930352737e-06, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.06898250800689826, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2500000000000007e-06, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0699679724069968, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1752018394169882e-06, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.07095343680709534, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1020177413231334e-06, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.07193890120719389, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0305368692688175e-06, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.07292436560729244, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.608463116858544e-07, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.07390983000739099, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.930309757836517e-07, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.07489529440748953, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.271734841028553e-07, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.07588075880758807, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.633540738525066e-07, | |
| "loss": 0.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.07686622320768663, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.016504991533727e-07, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.07785168760778517, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.421379363065142e-07, | |
| "loss": 0.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.07883715200788372, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.848888922025553e-07, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.07982261640798226, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.299731159831953e-07, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.08080808080808081, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.774575140626317e-07, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.08179354520817936, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.27406068612396e-07, | |
| "loss": 0.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.0827790096082779, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.798797596089351e-07, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.08376447400837644, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3493649053890325e-07, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.084749938408475, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9263101785268253e-07, | |
| "loss": 0.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.08573540280857354, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.53014884252083e-07, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.08672086720867209, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1613635589349756e-07, | |
| "loss": 0.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.08770633160877063, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8204036358303173e-07, | |
| "loss": 0.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.08869179600886919, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.507684480352292e-07, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.08967726040896773, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.223587092621162e-07, | |
| "loss": 0.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.09066272480906627, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.684576015420277e-08, | |
| "loss": 0.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.09164818920916482, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.426068431000883e-08, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.09263365360926337, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.463099816548578e-08, | |
| "loss": 0.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.09361911800936192, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.798061746947995e-08, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.09460458240946046, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4329828146074096e-08, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.095590046809559, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3695261579316776e-08, | |
| "loss": 0.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.09657551120965756, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.089874350439507e-09, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.0975609756097561, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5229324522605949e-09, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.09854644000985464, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.09854644000985464, | |
| "eval_loss": NaN, | |
| "eval_runtime": 38.4999, | |
| "eval_samples_per_second": 44.39, | |
| "eval_steps_per_second": 11.117, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9958181280153600.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |