| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 2.6101141924959217, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.052202283849918436, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0996, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.052202283849918436, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.8719, | |
| "eval_samples_per_second": 57.346, | |
| "eval_steps_per_second": 14.91, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.10440456769983687, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1566068515497553, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.992920667580176e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.20880913539967375, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.971704944519594e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.26101141924959215, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.936419583332062e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3132137030995106, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.887175604818206e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.36541598694942906, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.82412794875295e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.4176182707993475, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.747474986387654e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.4698205546492659, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5220228384991843, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.554359905560886e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5742251223491027, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.438505398589392e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.6264274061990212, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.310258896527278e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.6786296900489397, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.17002391031667e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.7308319738988581, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.018241671106134e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.7830342577487766, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.855389741974244e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.835236541598695, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.8874388254486134, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.498559600784018e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.9396411092985318, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.305704108364301e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.9918433931484503, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.104020832809127e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.0440456769983686, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.894144344319014e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0962479608482871, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.67673499197358e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.1484502446982057, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.452476826029011e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.200652528548124, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.2528548123980423, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.986255778798253e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.3050570962479608, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.745759801411822e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.3050570962479608, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.8708, | |
| "eval_samples_per_second": 57.417, | |
| "eval_steps_per_second": 14.928, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.3572593800978794, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.501344202803414e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.4094616639477977, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.253778004871315e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.461663947797716, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.003840142464886e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.5138662316476346, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.752317012567363e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.566068515497553, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.6182707993474714, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.247682987432637e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.6704730831973897, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.9961598575351155e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.7226753670473083, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.7462219951286867e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.7748776508972268, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.498655797196586e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.8270799347471451, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2542401985881784e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.8792822185970635, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.01374422120175e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.931484502446982, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.9836867862969005, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.547523173970989e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.035889070146819, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.323265008026421e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.088091353996737, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.105855655680986e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.1402936378466557, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8959791671908742e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.1924959216965743, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6942958916356998e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.244698205546493, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.501440399215983e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.2969004893964113, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.3491027732463294, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.144610258025755e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.401305057096248, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.981758328893866e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.4535073409461665, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8299760896833295e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.5057096247960846, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6897411034727218e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.557911908646003, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5614946014106085e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.6101141924959217, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4456400944391146e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.6101141924959217, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.8708, | |
| "eval_samples_per_second": 57.416, | |
| "eval_steps_per_second": 14.928, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 58, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.2616760234606592e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |