| { | |
| "best_metric": 0.0032391464337706566, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.1052631578947367, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.042105263157894736, | |
| "grad_norm": 14.870198249816895, | |
| "learning_rate": 5e-05, | |
| "loss": 10.7091, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.042105263157894736, | |
| "eval_loss": 11.368334770202637, | |
| "eval_runtime": 3.0396, | |
| "eval_samples_per_second": 16.45, | |
| "eval_steps_per_second": 4.277, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08421052631578947, | |
| "grad_norm": 15.38886833190918, | |
| "learning_rate": 0.0001, | |
| "loss": 11.2438, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.12631578947368421, | |
| "grad_norm": 15.02553939819336, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 10.5051, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.16842105263157894, | |
| "grad_norm": 20.028017044067383, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 6.9958, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 18.299043655395508, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 3.438, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.25263157894736843, | |
| "grad_norm": 10.302573204040527, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.0462, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.29473684210526313, | |
| "grad_norm": 6.063451766967773, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.8572, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3368421052631579, | |
| "grad_norm": 4.465893745422363, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.489, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.37894736842105264, | |
| "grad_norm": 3.456413507461548, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.2984, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 7.26656436920166, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.2787, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4631578947368421, | |
| "grad_norm": 6.0136260986328125, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.2192, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.5052631578947369, | |
| "grad_norm": 4.878045558929443, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.2523, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5473684210526316, | |
| "grad_norm": 1.8895072937011719, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.1674, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5894736842105263, | |
| "grad_norm": 5.177565097808838, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.2135, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.631578947368421, | |
| "grad_norm": 5.553564071655273, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.1999, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6736842105263158, | |
| "grad_norm": 0.6585373282432556, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.1176, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.7157894736842105, | |
| "grad_norm": 1.6070789098739624, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.097, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.7578947368421053, | |
| "grad_norm": 0.6574999690055847, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.0865, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 4.730718612670898, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.1293, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 2.033341646194458, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.0685, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8842105263157894, | |
| "grad_norm": 0.9938953518867493, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.0426, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.9263157894736842, | |
| "grad_norm": 1.2293890714645386, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.0598, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.968421052631579, | |
| "grad_norm": 0.6777116656303406, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.025, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.0105263157894737, | |
| "grad_norm": 4.29020357131958, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.0789, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.0526315789473684, | |
| "grad_norm": 0.1184600442647934, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.0023, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0526315789473684, | |
| "eval_loss": 0.07134973257780075, | |
| "eval_runtime": 3.0239, | |
| "eval_samples_per_second": 16.535, | |
| "eval_steps_per_second": 4.299, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0947368421052632, | |
| "grad_norm": 0.2849907875061035, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0064, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.1368421052631579, | |
| "grad_norm": 1.011404275894165, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.0255, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.1789473684210527, | |
| "grad_norm": 2.2019524574279785, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.0276, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.2210526315789474, | |
| "grad_norm": 0.5445430278778076, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.0445, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.263157894736842, | |
| "grad_norm": 3.8727214336395264, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.0576, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.305263157894737, | |
| "grad_norm": 0.2200043797492981, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.0027, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.3473684210526315, | |
| "grad_norm": 0.5764152407646179, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.0121, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.3894736842105262, | |
| "grad_norm": 0.3320938050746918, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.0102, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.431578947368421, | |
| "grad_norm": 0.5339176654815674, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.0041, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.4736842105263157, | |
| "grad_norm": 0.9797345995903015, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.0105, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.5157894736842106, | |
| "grad_norm": 0.7296271324157715, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.0068, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.5578947368421052, | |
| "grad_norm": 0.605354368686676, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.0074, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.6698538661003113, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.012, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.6421052631578947, | |
| "grad_norm": 5.393788814544678, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.0142, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.6842105263157894, | |
| "grad_norm": 1.3299963474273682, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.0109, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.7263157894736842, | |
| "grad_norm": 0.04660975560545921, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.0008, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.768421052631579, | |
| "grad_norm": 0.1902923732995987, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.0011, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.8105263157894735, | |
| "grad_norm": 1.5841089487075806, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.012, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.8526315789473684, | |
| "grad_norm": 3.1886465549468994, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.0083, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.8947368421052633, | |
| "grad_norm": 0.28632158041000366, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.0005, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.936842105263158, | |
| "grad_norm": 0.23157168924808502, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.002, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.9789473684210526, | |
| "grad_norm": 0.08383818715810776, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.0012, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.0210526315789474, | |
| "grad_norm": 0.062229812145233154, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.0006, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.0631578947368423, | |
| "grad_norm": 0.14913830161094666, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.001, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.1052631578947367, | |
| "grad_norm": 0.00795549713075161, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0002, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.1052631578947367, | |
| "eval_loss": 0.0032391464337706566, | |
| "eval_runtime": 2.9882, | |
| "eval_samples_per_second": 16.732, | |
| "eval_steps_per_second": 4.35, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |