| { | |
| "best_metric": 0.22627143561840057, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.6802721088435374, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013605442176870748, | |
| "grad_norm": 93.97410583496094, | |
| "learning_rate": 5e-05, | |
| "loss": 8.5273, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013605442176870748, | |
| "eval_loss": 11.231951713562012, | |
| "eval_runtime": 12.5298, | |
| "eval_samples_per_second": 39.506, | |
| "eval_steps_per_second": 4.948, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.027210884353741496, | |
| "grad_norm": 95.9598617553711, | |
| "learning_rate": 0.0001, | |
| "loss": 8.538, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04081632653061224, | |
| "grad_norm": 63.501033782958984, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 6.6595, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05442176870748299, | |
| "grad_norm": 46.91209411621094, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.7585, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06802721088435375, | |
| "grad_norm": 10.052841186523438, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.6885, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08163265306122448, | |
| "grad_norm": 118.25402069091797, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 7.0601, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09523809523809523, | |
| "grad_norm": 120.69783782958984, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 6.7704, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.10884353741496598, | |
| "grad_norm": 115.61042022705078, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 5.5917, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.12244897959183673, | |
| "grad_norm": 107.16246032714844, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 3.2736, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1360544217687075, | |
| "grad_norm": 61.53949737548828, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.0701, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14965986394557823, | |
| "grad_norm": 61.477577209472656, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.2541, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.16326530612244897, | |
| "grad_norm": 42.21637725830078, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.6663, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.17687074829931973, | |
| "grad_norm": 110.94076538085938, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.6277, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.19047619047619047, | |
| "grad_norm": 148.243896484375, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.711, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.20408163265306123, | |
| "grad_norm": 89.7364501953125, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.2819, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.21768707482993196, | |
| "grad_norm": 3.0155715942382812, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.0097, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.23129251700680273, | |
| "grad_norm": 0.006209846585988998, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.0001, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.24489795918367346, | |
| "grad_norm": 48.33979415893555, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.0066, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2585034013605442, | |
| "grad_norm": 91.27472686767578, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.7072, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.272108843537415, | |
| "grad_norm": 80.66976165771484, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.2061, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 72.21331787109375, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.6214, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.29931972789115646, | |
| "grad_norm": 37.6623420715332, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.7571, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3129251700680272, | |
| "grad_norm": 27.254451751708984, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.5842, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.32653061224489793, | |
| "grad_norm": 25.075157165527344, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.4047, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3401360544217687, | |
| "grad_norm": 12.705240249633789, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.2204, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3401360544217687, | |
| "eval_loss": 0.2315373420715332, | |
| "eval_runtime": 12.5079, | |
| "eval_samples_per_second": 39.575, | |
| "eval_steps_per_second": 4.957, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.35374149659863946, | |
| "grad_norm": 10.045724868774414, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0646, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3673469387755102, | |
| "grad_norm": 17.253311157226562, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.1257, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "grad_norm": 16.977933883666992, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.1158, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3945578231292517, | |
| "grad_norm": 8.944509506225586, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0538, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.40816326530612246, | |
| "grad_norm": 3.2423906326293945, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0169, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4217687074829932, | |
| "grad_norm": 47.8316535949707, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.5456, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.43537414965986393, | |
| "grad_norm": 66.37613677978516, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.5475, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4489795918367347, | |
| "grad_norm": 39.44430923461914, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.5115, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.46258503401360546, | |
| "grad_norm": 17.030851364135742, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.3512, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.47619047619047616, | |
| "grad_norm": 14.662363052368164, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.3138, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4897959183673469, | |
| "grad_norm": 14.485307693481445, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.2473, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5034013605442177, | |
| "grad_norm": 12.0574312210083, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.2097, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5170068027210885, | |
| "grad_norm": 1.3240798711776733, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0633, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5306122448979592, | |
| "grad_norm": 0.8655800819396973, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.003, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.54421768707483, | |
| "grad_norm": 0.7527680993080139, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0025, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5578231292517006, | |
| "grad_norm": 0.4660660922527313, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0016, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 0.297651469707489, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0011, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5850340136054422, | |
| "grad_norm": 6.011413097381592, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.0826, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5986394557823129, | |
| "grad_norm": 18.873197555541992, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.2667, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6122448979591837, | |
| "grad_norm": 16.203052520751953, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.2395, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6258503401360545, | |
| "grad_norm": 17.224546432495117, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.2585, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6394557823129252, | |
| "grad_norm": 16.941646575927734, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.2371, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6530612244897959, | |
| "grad_norm": 12.933724403381348, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.1872, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 18.311908721923828, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.2395, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6802721088435374, | |
| "grad_norm": 14.999979019165039, | |
| "learning_rate": 0.0, | |
| "loss": 0.2348, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6802721088435374, | |
| "eval_loss": 0.22627143561840057, | |
| "eval_runtime": 12.4896, | |
| "eval_samples_per_second": 39.633, | |
| "eval_steps_per_second": 4.964, | |
| "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": 1.059536353886208e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |