| { | |
| "best_metric": 0.06123066693544388, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.23689665383476458, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004737933076695291, | |
| "grad_norm": 52.389259338378906, | |
| "learning_rate": 5e-05, | |
| "loss": 7.4525, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004737933076695291, | |
| "eval_loss": 7.695676326751709, | |
| "eval_runtime": 93.9033, | |
| "eval_samples_per_second": 15.143, | |
| "eval_steps_per_second": 1.896, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009475866153390583, | |
| "grad_norm": 49.32695770263672, | |
| "learning_rate": 0.0001, | |
| "loss": 7.5853, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.014213799230085875, | |
| "grad_norm": 47.50961685180664, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 7.6199, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.018951732306781165, | |
| "grad_norm": 74.07343292236328, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 6.9211, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.023689665383476458, | |
| "grad_norm": 86.87323760986328, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 5.265, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02842759846017175, | |
| "grad_norm": 58.85215377807617, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.5893, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03316553153686704, | |
| "grad_norm": 56.270606994628906, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.7787, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03790346461356233, | |
| "grad_norm": 50.2116813659668, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.8891, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.042641397690257626, | |
| "grad_norm": 46.09134292602539, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.3797, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.047379330766952915, | |
| "grad_norm": 34.20993423461914, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.832, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05211726384364821, | |
| "grad_norm": 33.35684585571289, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.5466, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0568551969203435, | |
| "grad_norm": 33.218482971191406, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.4529, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.061593129997038795, | |
| "grad_norm": 27.902225494384766, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.4454, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06633106307373408, | |
| "grad_norm": 17.487951278686523, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.314, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.07106899615042937, | |
| "grad_norm": 12.388195991516113, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.2289, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07580692922712466, | |
| "grad_norm": 21.05245018005371, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.2368, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.08054486230381996, | |
| "grad_norm": 24.567829132080078, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.2338, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.08528279538051525, | |
| "grad_norm": 9.504969596862793, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.153, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.09002072845721054, | |
| "grad_norm": 10.618803024291992, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.1224, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.09475866153390583, | |
| "grad_norm": 9.873135566711426, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.1164, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09949659461060112, | |
| "grad_norm": 10.154685974121094, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.1337, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.10423452768729642, | |
| "grad_norm": 9.861929893493652, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.0837, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.10897246076399171, | |
| "grad_norm": 10.900649070739746, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.099, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.113710393840687, | |
| "grad_norm": 6.15477991104126, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.0936, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.11844832691738229, | |
| "grad_norm": 8.439327239990234, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.0795, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11844832691738229, | |
| "eval_loss": 0.1033322736620903, | |
| "eval_runtime": 93.9327, | |
| "eval_samples_per_second": 15.139, | |
| "eval_steps_per_second": 1.895, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.12318625999407759, | |
| "grad_norm": 8.260644912719727, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0799, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.12792419307077288, | |
| "grad_norm": 19.179166793823242, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.1616, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.13266212614746817, | |
| "grad_norm": 16.56215476989746, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.122, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.13740005922416346, | |
| "grad_norm": 8.13351058959961, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.1073, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.14213799230085875, | |
| "grad_norm": 6.613006591796875, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0833, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.14687592537755403, | |
| "grad_norm": 5.962475299835205, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.0568, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.15161385845424932, | |
| "grad_norm": 12.22464370727539, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.083, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1563517915309446, | |
| "grad_norm": 8.224514961242676, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.0595, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.16108972460763993, | |
| "grad_norm": 8.671944618225098, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0695, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.16582765768433522, | |
| "grad_norm": 7.786879539489746, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0842, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.1705655907610305, | |
| "grad_norm": 6.3661651611328125, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0665, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.1753035238377258, | |
| "grad_norm": 5.761310577392578, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.0637, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.18004145691442108, | |
| "grad_norm": 6.241346836090088, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0949, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.18477938999111637, | |
| "grad_norm": 5.52647066116333, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.0901, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.18951732306781166, | |
| "grad_norm": 4.935317516326904, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0837, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.19425525614450695, | |
| "grad_norm": 6.299217700958252, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0788, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.19899318922120224, | |
| "grad_norm": 5.384281158447266, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0628, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.20373112229789755, | |
| "grad_norm": 5.419621467590332, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.0601, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.20846905537459284, | |
| "grad_norm": 5.761849403381348, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0755, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.21320698845128813, | |
| "grad_norm": 3.9190921783447266, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.0361, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.21794492152798342, | |
| "grad_norm": 4.561317443847656, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0649, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.2226828546046787, | |
| "grad_norm": 4.831967830657959, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0485, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.227420787681374, | |
| "grad_norm": 6.556378364562988, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0835, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.2321587207580693, | |
| "grad_norm": 3.2636804580688477, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.0443, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.23689665383476458, | |
| "grad_norm": 9.330513954162598, | |
| "learning_rate": 0.0, | |
| "loss": 0.0776, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.23689665383476458, | |
| "eval_loss": 0.06123066693544388, | |
| "eval_runtime": 93.9167, | |
| "eval_samples_per_second": 15.141, | |
| "eval_steps_per_second": 1.895, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0937288838086656e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |