| { | |
| "best_metric": 0.5474712252616882, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 2.849122807017544, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.056140350877192984, | |
| "grad_norm": 48.57777404785156, | |
| "learning_rate": 5e-05, | |
| "loss": 6.6579, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.056140350877192984, | |
| "eval_loss": 6.74901008605957, | |
| "eval_runtime": 1.0992, | |
| "eval_samples_per_second": 45.488, | |
| "eval_steps_per_second": 11.827, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11228070175438597, | |
| "grad_norm": 47.00796890258789, | |
| "learning_rate": 0.0001, | |
| "loss": 6.7391, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.16842105263157894, | |
| "grad_norm": 33.626976013183594, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 3.6924, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.22456140350877193, | |
| "grad_norm": 11.591245651245117, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.1897, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.2807017543859649, | |
| "grad_norm": 6.829763889312744, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 0.6814, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3368421052631579, | |
| "grad_norm": 20.96088409423828, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.8488, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3929824561403509, | |
| "grad_norm": 2.328688621520996, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.5832, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.44912280701754387, | |
| "grad_norm": 1.939924716949463, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.575, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5052631578947369, | |
| "grad_norm": 1.6199500560760498, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.585, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5614035087719298, | |
| "grad_norm": 0.6787525415420532, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.5614, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6175438596491228, | |
| "grad_norm": 0.8290811777114868, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.5661, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.6736842105263158, | |
| "grad_norm": 0.20235224068164825, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.5513, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.7298245614035088, | |
| "grad_norm": 0.148473858833313, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.5504, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.7859649122807018, | |
| "grad_norm": 0.22677071392536163, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.5454, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 0.26962289214134216, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.5485, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.8982456140350877, | |
| "grad_norm": 0.17206503450870514, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.5437, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.9543859649122807, | |
| "grad_norm": 0.3968896269798279, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.5546, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.0315789473684212, | |
| "grad_norm": 0.46319472789764404, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.8464, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.087719298245614, | |
| "grad_norm": 0.3382393717765808, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.5309, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.143859649122807, | |
| "grad_norm": 0.4685853123664856, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.543, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 0.6385741829872131, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.5374, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.256140350877193, | |
| "grad_norm": 0.9591385722160339, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.5331, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.312280701754386, | |
| "grad_norm": 1.3898637294769287, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.5215, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.368421052631579, | |
| "grad_norm": 2.8904006481170654, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.5049, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.424561403508772, | |
| "grad_norm": 3.769226312637329, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.5675, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.424561403508772, | |
| "eval_loss": 0.5474712252616882, | |
| "eval_runtime": 1.0993, | |
| "eval_samples_per_second": 45.485, | |
| "eval_steps_per_second": 11.826, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.4807017543859649, | |
| "grad_norm": 1.2373392581939697, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.484, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.5368421052631578, | |
| "grad_norm": 1.2246801853179932, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.5089, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.592982456140351, | |
| "grad_norm": 5.694296836853027, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.5521, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.6491228070175439, | |
| "grad_norm": 4.855273723602295, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.5784, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.7052631578947368, | |
| "grad_norm": 1.6988043785095215, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.5402, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.76140350877193, | |
| "grad_norm": 0.37333518266677856, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.5372, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.8175438596491227, | |
| "grad_norm": 0.3897054195404053, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.5294, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.8736842105263158, | |
| "grad_norm": 0.3769664466381073, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.5232, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.9298245614035088, | |
| "grad_norm": 0.3648321330547333, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.5266, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.007017543859649, | |
| "grad_norm": 0.6096442937850952, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.8266, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.0631578947368423, | |
| "grad_norm": 0.630775511264801, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.5151, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.119298245614035, | |
| "grad_norm": 0.6183218359947205, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.51, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.175438596491228, | |
| "grad_norm": 0.7393589019775391, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.499, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.231578947368421, | |
| "grad_norm": 1.0172677040100098, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.4687, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.287719298245614, | |
| "grad_norm": 1.1205629110336304, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.4881, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.343859649122807, | |
| "grad_norm": 1.283227801322937, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.4856, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 2.2868361473083496, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.4732, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.456140350877193, | |
| "grad_norm": 2.0381109714508057, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.448, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.512280701754386, | |
| "grad_norm": 2.1232497692108154, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.4969, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.568421052631579, | |
| "grad_norm": 2.6984243392944336, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.4528, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.624561403508772, | |
| "grad_norm": 2.359876871109009, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.474, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.680701754385965, | |
| "grad_norm": 2.875005006790161, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.3875, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.736842105263158, | |
| "grad_norm": 1.8744059801101685, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.3585, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.7929824561403507, | |
| "grad_norm": 3.156296730041504, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.4208, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.849122807017544, | |
| "grad_norm": 2.5855393409729004, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3564, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.849122807017544, | |
| "eval_loss": 0.5512737035751343, | |
| "eval_runtime": 1.0976, | |
| "eval_samples_per_second": 45.555, | |
| "eval_steps_per_second": 11.844, | |
| "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": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.62480894509056e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |