| { | |
| "best_metric": 0.8431416153907776, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.3157894736842106, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02631578947368421, | |
| "grad_norm": 35.830352783203125, | |
| "learning_rate": 1e-05, | |
| "loss": 5.5742, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02631578947368421, | |
| "eval_loss": 1.6754724979400635, | |
| "eval_runtime": 4.6369, | |
| "eval_samples_per_second": 13.802, | |
| "eval_steps_per_second": 3.451, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05263157894736842, | |
| "grad_norm": 45.00202560424805, | |
| "learning_rate": 2e-05, | |
| "loss": 6.0369, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.07894736842105263, | |
| "grad_norm": 46.17910385131836, | |
| "learning_rate": 3e-05, | |
| "loss": 6.0642, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.10526315789473684, | |
| "grad_norm": 49.760963439941406, | |
| "learning_rate": 4e-05, | |
| "loss": 5.5496, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.13157894736842105, | |
| "grad_norm": 39.75947189331055, | |
| "learning_rate": 5e-05, | |
| "loss": 5.168, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.15789473684210525, | |
| "grad_norm": 41.92656707763672, | |
| "learning_rate": 6e-05, | |
| "loss": 4.7943, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.18421052631578946, | |
| "grad_norm": 27.3580322265625, | |
| "learning_rate": 7e-05, | |
| "loss": 3.9595, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 34.04036331176758, | |
| "learning_rate": 8e-05, | |
| "loss": 4.0193, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.23684210526315788, | |
| "grad_norm": 39.38542556762695, | |
| "learning_rate": 9e-05, | |
| "loss": 4.7816, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.2631578947368421, | |
| "grad_norm": 42.04862976074219, | |
| "learning_rate": 0.0001, | |
| "loss": 4.7192, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2894736842105263, | |
| "grad_norm": 16.514020919799805, | |
| "learning_rate": 9.997718922447667e-05, | |
| "loss": 3.6934, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3157894736842105, | |
| "grad_norm": 14.977937698364258, | |
| "learning_rate": 9.990877771116589e-05, | |
| "loss": 4.0051, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.34210526315789475, | |
| "grad_norm": 16.822614669799805, | |
| "learning_rate": 9.979482788085454e-05, | |
| "loss": 3.3175, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.3684210526315789, | |
| "grad_norm": 17.509784698486328, | |
| "learning_rate": 9.96354437049027e-05, | |
| "loss": 3.4816, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.39473684210526316, | |
| "grad_norm": 15.930502891540527, | |
| "learning_rate": 9.943077061037671e-05, | |
| "loss": 3.2727, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 20.140819549560547, | |
| "learning_rate": 9.918099534735718e-05, | |
| "loss": 3.531, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.4473684210526316, | |
| "grad_norm": 21.51377296447754, | |
| "learning_rate": 9.888634581854234e-05, | |
| "loss": 3.2109, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.47368421052631576, | |
| "grad_norm": 21.92951202392578, | |
| "learning_rate": 9.85470908713026e-05, | |
| "loss": 3.6691, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 10.309015274047852, | |
| "learning_rate": 9.816354005237583e-05, | |
| "loss": 3.3325, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "grad_norm": 14.019783973693848, | |
| "learning_rate": 9.773604332542729e-05, | |
| "loss": 3.8225, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5526315789473685, | |
| "grad_norm": 12.386563301086426, | |
| "learning_rate": 9.726499075173201e-05, | |
| "loss": 3.4366, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.5789473684210527, | |
| "grad_norm": 13.775650978088379, | |
| "learning_rate": 9.675081213427076e-05, | |
| "loss": 3.6102, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.6052631578947368, | |
| "grad_norm": 13.588586807250977, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.7363, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.631578947368421, | |
| "grad_norm": 13.898175239562988, | |
| "learning_rate": 9.559499229960451e-05, | |
| "loss": 3.2825, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.6578947368421053, | |
| "grad_norm": 15.590497970581055, | |
| "learning_rate": 9.495440568827129e-05, | |
| "loss": 3.2594, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6842105263157895, | |
| "grad_norm": 18.052392959594727, | |
| "learning_rate": 9.42728012826605e-05, | |
| "loss": 3.4811, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.7105263157894737, | |
| "grad_norm": 20.789844512939453, | |
| "learning_rate": 9.355080099977578e-05, | |
| "loss": 4.004, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.7368421052631579, | |
| "grad_norm": 11.545269012451172, | |
| "learning_rate": 9.278906361507238e-05, | |
| "loss": 3.407, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.7631578947368421, | |
| "grad_norm": 11.368681907653809, | |
| "learning_rate": 9.19882841613699e-05, | |
| "loss": 3.212, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.7894736842105263, | |
| "grad_norm": 12.940420150756836, | |
| "learning_rate": 9.114919329468282e-05, | |
| "loss": 3.4642, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.8157894736842105, | |
| "grad_norm": 11.59272575378418, | |
| "learning_rate": 9.02725566275473e-05, | |
| "loss": 3.3124, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 17.267396926879883, | |
| "learning_rate": 8.935917403045251e-05, | |
| "loss": 3.5721, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.868421052631579, | |
| "grad_norm": 14.882741928100586, | |
| "learning_rate": 8.840987890201403e-05, | |
| "loss": 3.7928, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.8947368421052632, | |
| "grad_norm": 14.032687187194824, | |
| "learning_rate": 8.742553740855506e-05, | |
| "loss": 3.2582, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.9210526315789473, | |
| "grad_norm": 13.775826454162598, | |
| "learning_rate": 8.640704769378942e-05, | |
| "loss": 3.4732, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.9473684210526315, | |
| "grad_norm": 17.22196388244629, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.6359, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.9736842105263158, | |
| "grad_norm": 14.44973373413086, | |
| "learning_rate": 8.427137111675199e-05, | |
| "loss": 3.5035, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 17.80911636352539, | |
| "learning_rate": 8.315613291203976e-05, | |
| "loss": 3.3937, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.0263157894736843, | |
| "grad_norm": 8.416217803955078, | |
| "learning_rate": 8.201064202312441e-05, | |
| "loss": 2.8219, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.0526315789473684, | |
| "grad_norm": 8.224820137023926, | |
| "learning_rate": 8.083594363142717e-05, | |
| "loss": 1.9419, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.0789473684210527, | |
| "grad_norm": 8.183276176452637, | |
| "learning_rate": 7.963310956820085e-05, | |
| "loss": 1.795, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.1052631578947367, | |
| "grad_norm": 8.23655891418457, | |
| "learning_rate": 7.840323733655778e-05, | |
| "loss": 1.6889, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.131578947368421, | |
| "grad_norm": 11.236390113830566, | |
| "learning_rate": 7.714744911007394e-05, | |
| "loss": 1.6847, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.1578947368421053, | |
| "grad_norm": 10.796011924743652, | |
| "learning_rate": 7.586689070888284e-05, | |
| "loss": 1.4455, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.1842105263157894, | |
| "grad_norm": 10.806239128112793, | |
| "learning_rate": 7.456273055419388e-05, | |
| "loss": 1.1321, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.2105263157894737, | |
| "grad_norm": 11.67683219909668, | |
| "learning_rate": 7.323615860218843e-05, | |
| "loss": 1.0502, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.236842105263158, | |
| "grad_norm": 15.044631958007812, | |
| "learning_rate": 7.188838525826702e-05, | |
| "loss": 1.189, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.263157894736842, | |
| "grad_norm": 13.156881332397461, | |
| "learning_rate": 7.052064027263786e-05, | |
| "loss": 2.1428, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.2894736842105263, | |
| "grad_norm": 11.645526885986328, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.6295, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.3157894736842106, | |
| "grad_norm": 10.376519203186035, | |
| "learning_rate": 6.773024435212678e-05, | |
| "loss": 1.609, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.3157894736842106, | |
| "eval_loss": 0.8431416153907776, | |
| "eval_runtime": 4.7683, | |
| "eval_samples_per_second": 13.422, | |
| "eval_steps_per_second": 3.355, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 114, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.123694981323162e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |