| { | |
| "best_metric": 0.3082202076911926, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.22148394241417496, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004429678848283499, | |
| "grad_norm": 80.3771743774414, | |
| "learning_rate": 5e-05, | |
| "loss": 186.8504, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004429678848283499, | |
| "eval_loss": 11.864986419677734, | |
| "eval_runtime": 126.0276, | |
| "eval_samples_per_second": 12.069, | |
| "eval_steps_per_second": 1.516, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008859357696566999, | |
| "grad_norm": 83.50208282470703, | |
| "learning_rate": 0.0001, | |
| "loss": 191.1957, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.013289036544850499, | |
| "grad_norm": 89.58778381347656, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 186.5678, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.017718715393133997, | |
| "grad_norm": 129.3165740966797, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 170.2373, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0221483942414175, | |
| "grad_norm": 139.35647583007812, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 141.4767, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.026578073089700997, | |
| "grad_norm": 118.65985107421875, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 117.7925, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.031007751937984496, | |
| "grad_norm": 117.44580078125, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 96.8972, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.035437430786267994, | |
| "grad_norm": 115.84791564941406, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 77.6476, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03986710963455149, | |
| "grad_norm": 137.33387756347656, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 54.0985, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.044296788482835, | |
| "grad_norm": 146.39991760253906, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 29.7652, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.048726467331118496, | |
| "grad_norm": 82.59661102294922, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 14.8776, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.053156146179401995, | |
| "grad_norm": 104.44115447998047, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 12.1848, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.05758582502768549, | |
| "grad_norm": 48.7734260559082, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 9.9194, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06201550387596899, | |
| "grad_norm": 46.114593505859375, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 9.2692, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0664451827242525, | |
| "grad_norm": 31.456167221069336, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 8.4696, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07087486157253599, | |
| "grad_norm": 69.29698944091797, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 9.3606, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0753045404208195, | |
| "grad_norm": 41.587501525878906, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 8.9985, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.07973421926910298, | |
| "grad_norm": 32.481868743896484, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 7.2757, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08416389811738649, | |
| "grad_norm": 41.32707214355469, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 6.7443, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.08859357696567, | |
| "grad_norm": 40.19483184814453, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 7.1462, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09302325581395349, | |
| "grad_norm": 83.13573455810547, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 7.713, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.09745293466223699, | |
| "grad_norm": 55.984676361083984, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 5.5221, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.10188261351052048, | |
| "grad_norm": 29.221961975097656, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 5.4771, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.10631229235880399, | |
| "grad_norm": 37.901004791259766, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 5.3382, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.11074197120708748, | |
| "grad_norm": 29.54227066040039, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 4.7856, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11074197120708748, | |
| "eval_loss": 0.4165385067462921, | |
| "eval_runtime": 127.2616, | |
| "eval_samples_per_second": 11.952, | |
| "eval_steps_per_second": 1.501, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11517165005537099, | |
| "grad_norm": 75.84956359863281, | |
| "learning_rate": 5e-05, | |
| "loss": 8.2554, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.11960132890365449, | |
| "grad_norm": 28.34756851196289, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 6.9377, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.12403100775193798, | |
| "grad_norm": 58.43377685546875, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 7.3211, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.12846068660022147, | |
| "grad_norm": 70.48342895507812, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 8.1274, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.132890365448505, | |
| "grad_norm": 36.33397674560547, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 5.5569, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13732004429678848, | |
| "grad_norm": 27.151063919067383, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 5.5113, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.14174972314507198, | |
| "grad_norm": 44.36494064331055, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 5.6198, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1461794019933555, | |
| "grad_norm": 26.758596420288086, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 5.536, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.150609080841639, | |
| "grad_norm": 17.586759567260742, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 5.0683, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.15503875968992248, | |
| "grad_norm": 32.076446533203125, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 5.0719, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.15946843853820597, | |
| "grad_norm": 74.89476013183594, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 4.8337, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.1638981173864895, | |
| "grad_norm": 31.926136016845703, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 3.6355, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.16832779623477298, | |
| "grad_norm": 23.79403305053711, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 4.9566, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.17275747508305647, | |
| "grad_norm": 48.75263977050781, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 6.8026, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.17718715393134, | |
| "grad_norm": 47.51777648925781, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 7.0032, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.18161683277962348, | |
| "grad_norm": 38.380916595458984, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 6.4569, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.18604651162790697, | |
| "grad_norm": 39.794124603271484, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 5.3289, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.19047619047619047, | |
| "grad_norm": 24.938093185424805, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 5.3438, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.19490586932447398, | |
| "grad_norm": 22.430749893188477, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 5.4512, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.19933554817275748, | |
| "grad_norm": 22.097654342651367, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 5.5461, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.20376522702104097, | |
| "grad_norm": 18.900991439819336, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 4.7573, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.2081949058693245, | |
| "grad_norm": 14.95788860321045, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 5.2978, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.21262458471760798, | |
| "grad_norm": 27.965768814086914, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 5.752, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.21705426356589147, | |
| "grad_norm": 39.07429504394531, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 4.222, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.22148394241417496, | |
| "grad_norm": 23.545461654663086, | |
| "learning_rate": 0.0, | |
| "loss": 3.5723, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.22148394241417496, | |
| "eval_loss": 0.3082202076911926, | |
| "eval_runtime": 127.0071, | |
| "eval_samples_per_second": 11.976, | |
| "eval_steps_per_second": 1.504, | |
| "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": 1.0205684108886016e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |