| { | |
| "best_metric": 0.06177634373307228, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.0638297872340425, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02127659574468085, | |
| "grad_norm": 464.40740966796875, | |
| "learning_rate": 5e-05, | |
| "loss": 120.0017, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02127659574468085, | |
| "eval_loss": 7.261743545532227, | |
| "eval_runtime": 21.035, | |
| "eval_samples_per_second": 15.07, | |
| "eval_steps_per_second": 1.902, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0425531914893617, | |
| "grad_norm": 478.11968994140625, | |
| "learning_rate": 0.0001, | |
| "loss": 120.8005, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06382978723404255, | |
| "grad_norm": 314.2818298339844, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 87.7523, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0851063829787234, | |
| "grad_norm": 267.66046142578125, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 43.7067, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.10638297872340426, | |
| "grad_norm": 166.4091339111328, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 17.732, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1276595744680851, | |
| "grad_norm": 81.00094604492188, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 4.1092, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.14893617021276595, | |
| "grad_norm": 110.64778900146484, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.5416, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1702127659574468, | |
| "grad_norm": 84.75375366210938, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.248, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.19148936170212766, | |
| "grad_norm": 40.44004440307617, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.3493, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.2127659574468085, | |
| "grad_norm": 143.48594665527344, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 3.2867, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.23404255319148937, | |
| "grad_norm": 55.8441276550293, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.4755, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.2553191489361702, | |
| "grad_norm": 31.11285972595215, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.5003, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2765957446808511, | |
| "grad_norm": 23.737272262573242, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.4429, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2978723404255319, | |
| "grad_norm": 10.330360412597656, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.8425, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3191489361702128, | |
| "grad_norm": 36.87436294555664, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.7142, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3404255319148936, | |
| "grad_norm": 37.09226989746094, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.7574, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.3617021276595745, | |
| "grad_norm": 45.74100875854492, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.8856, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3829787234042553, | |
| "grad_norm": 65.86280059814453, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.0063, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.40425531914893614, | |
| "grad_norm": 31.885648727416992, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.4159, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.425531914893617, | |
| "grad_norm": 26.262710571289062, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.8226, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.44680851063829785, | |
| "grad_norm": 10.645901679992676, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.2902, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.46808510638297873, | |
| "grad_norm": 3.2481682300567627, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.2652, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.48936170212765956, | |
| "grad_norm": 8.560073852539062, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.4973, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5106382978723404, | |
| "grad_norm": 12.47486686706543, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.6121, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5319148936170213, | |
| "grad_norm": 4.415579795837402, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.6636, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5319148936170213, | |
| "eval_loss": 0.08177092671394348, | |
| "eval_runtime": 21.0008, | |
| "eval_samples_per_second": 15.095, | |
| "eval_steps_per_second": 1.905, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5531914893617021, | |
| "grad_norm": 3.5168380737304688, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2512, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.574468085106383, | |
| "grad_norm": 22.19098663330078, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.5594, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.5957446808510638, | |
| "grad_norm": 5.936686038970947, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.1637, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.6170212765957447, | |
| "grad_norm": 16.02676773071289, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.2632, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.6382978723404256, | |
| "grad_norm": 14.360878944396973, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.1993, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6595744680851063, | |
| "grad_norm": 27.750530242919922, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.1324, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.6808510638297872, | |
| "grad_norm": 33.4967041015625, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.0415, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.7021276595744681, | |
| "grad_norm": 13.943852424621582, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.7634, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.723404255319149, | |
| "grad_norm": 16.322202682495117, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.7164, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.7446808510638298, | |
| "grad_norm": 14.58661937713623, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.2368, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.7659574468085106, | |
| "grad_norm": 12.963841438293457, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.2842, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.7872340425531915, | |
| "grad_norm": 26.34542465209961, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.7286, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.8085106382978723, | |
| "grad_norm": 10.058424949645996, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.0142, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.8297872340425532, | |
| "grad_norm": 17.854799270629883, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.9395, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.851063829787234, | |
| "grad_norm": 14.591531753540039, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.6999, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8723404255319149, | |
| "grad_norm": 18.455177307128906, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.9498, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.8936170212765957, | |
| "grad_norm": 25.038835525512695, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.246, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.9148936170212766, | |
| "grad_norm": 14.889090538024902, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.0996, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.9361702127659575, | |
| "grad_norm": 26.219545364379883, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.508, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.9574468085106383, | |
| "grad_norm": 15.979211807250977, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.9828, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.9787234042553191, | |
| "grad_norm": 13.021293640136719, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.4054, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 15.820076942443848, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.9171, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.0212765957446808, | |
| "grad_norm": 27.00518226623535, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.0428, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.0425531914893618, | |
| "grad_norm": 13.826783180236816, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.661, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.0638297872340425, | |
| "grad_norm": 11.46463680267334, | |
| "learning_rate": 0.0, | |
| "loss": 0.7936, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.0638297872340425, | |
| "eval_loss": 0.06177634373307228, | |
| "eval_runtime": 20.9876, | |
| "eval_samples_per_second": 15.104, | |
| "eval_steps_per_second": 1.906, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 5.658021338284032e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |