| { | |
| "best_metric": 1.0777992010116577, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.3401360544217687, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006802721088435374, | |
| "grad_norm": 248.7234344482422, | |
| "learning_rate": 5e-05, | |
| "loss": 5.5476, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006802721088435374, | |
| "eval_loss": 5.460923194885254, | |
| "eval_runtime": 48.3168, | |
| "eval_samples_per_second": 20.49, | |
| "eval_steps_per_second": 2.566, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013605442176870748, | |
| "grad_norm": 249.16697692871094, | |
| "learning_rate": 0.0001, | |
| "loss": 5.0478, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02040816326530612, | |
| "grad_norm": 199.95889282226562, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 3.945, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.027210884353741496, | |
| "grad_norm": 97.236083984375, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.6199, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.034013605442176874, | |
| "grad_norm": 132.86361694335938, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.0852, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04081632653061224, | |
| "grad_norm": 105.98623657226562, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.48, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.047619047619047616, | |
| "grad_norm": 146.3207244873047, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.3469, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05442176870748299, | |
| "grad_norm": 261.4817810058594, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.4178, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.061224489795918366, | |
| "grad_norm": 359.5050354003906, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.511, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06802721088435375, | |
| "grad_norm": 54.73991775512695, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.2544, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07482993197278912, | |
| "grad_norm": 77.96929931640625, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.3443, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.08163265306122448, | |
| "grad_norm": 157.8025665283203, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.2625, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08843537414965986, | |
| "grad_norm": 95.96159362792969, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.4238, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.09523809523809523, | |
| "grad_norm": 101.90237426757812, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.3396, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.10204081632653061, | |
| "grad_norm": 76.30518341064453, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.2345, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.10884353741496598, | |
| "grad_norm": 166.89657592773438, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.3707, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.11564625850340136, | |
| "grad_norm": 97.20339965820312, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.3398, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.12244897959183673, | |
| "grad_norm": 57.96915054321289, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.2716, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1292517006802721, | |
| "grad_norm": 46.3163948059082, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.1885, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.1360544217687075, | |
| "grad_norm": 43.7919921875, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.1528, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14285714285714285, | |
| "grad_norm": 79.05441284179688, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.1924, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.14965986394557823, | |
| "grad_norm": 55.5147819519043, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.158, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.1564625850340136, | |
| "grad_norm": 81.28190612792969, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.2168, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.16326530612244897, | |
| "grad_norm": 50.6247673034668, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.1891, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.17006802721088435, | |
| "grad_norm": 46.605167388916016, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.1467, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.17006802721088435, | |
| "eval_loss": 1.3848936557769775, | |
| "eval_runtime": 48.2965, | |
| "eval_samples_per_second": 20.498, | |
| "eval_steps_per_second": 2.567, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.17687074829931973, | |
| "grad_norm": 263.2676696777344, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5215, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1836734693877551, | |
| "grad_norm": 136.86534118652344, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.2886, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.19047619047619047, | |
| "grad_norm": 68.25189208984375, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.2215, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.19727891156462585, | |
| "grad_norm": 53.51959228515625, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.2119, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.20408163265306123, | |
| "grad_norm": 81.20413208007812, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.2189, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2108843537414966, | |
| "grad_norm": 87.15968322753906, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.1506, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.21768707482993196, | |
| "grad_norm": 78.61097717285156, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.1764, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.22448979591836735, | |
| "grad_norm": 69.10588836669922, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.1398, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.23129251700680273, | |
| "grad_norm": 22.39168930053711, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.0795, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.23809523809523808, | |
| "grad_norm": 42.56079864501953, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.1041, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.24489795918367346, | |
| "grad_norm": 59.99042510986328, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.1952, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.25170068027210885, | |
| "grad_norm": 25.075746536254883, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.1129, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.2585034013605442, | |
| "grad_norm": 16.67337989807129, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.1065, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.2653061224489796, | |
| "grad_norm": 21.959392547607422, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.0687, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.272108843537415, | |
| "grad_norm": 21.31378173828125, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.0832, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2789115646258503, | |
| "grad_norm": 21.72305679321289, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.0934, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 14.651026725769043, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.0633, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2925170068027211, | |
| "grad_norm": 24.642000198364258, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.0877, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.29931972789115646, | |
| "grad_norm": 80.92622375488281, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.1321, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.30612244897959184, | |
| "grad_norm": 28.691543579101562, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.0745, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3129251700680272, | |
| "grad_norm": 29.16392707824707, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.0768, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.3197278911564626, | |
| "grad_norm": 18.52094841003418, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.0671, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.32653061224489793, | |
| "grad_norm": 27.642658233642578, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.101, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 26.79389190673828, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.1145, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.3401360544217687, | |
| "grad_norm": 35.00909423828125, | |
| "learning_rate": 0.0, | |
| "loss": 1.1167, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3401360544217687, | |
| "eval_loss": 1.0777992010116577, | |
| "eval_runtime": 48.3094, | |
| "eval_samples_per_second": 20.493, | |
| "eval_steps_per_second": 2.567, | |
| "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": 5.889646573062717e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |