| { | |
| "best_metric": 0.03835269808769226, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.2222222222222223, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.044444444444444446, | |
| "grad_norm": 19.489383697509766, | |
| "learning_rate": 5e-05, | |
| "loss": 9.8289, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.044444444444444446, | |
| "eval_loss": 13.514202117919922, | |
| "eval_runtime": 8.4499, | |
| "eval_samples_per_second": 5.917, | |
| "eval_steps_per_second": 1.538, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08888888888888889, | |
| "grad_norm": 25.218671798706055, | |
| "learning_rate": 0.0001, | |
| "loss": 12.676, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.13333333333333333, | |
| "grad_norm": 32.122947692871094, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 14.0526, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.17777777777777778, | |
| "grad_norm": 36.05207824707031, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 12.1873, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 19.450180053710938, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 7.6919, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.26666666666666666, | |
| "grad_norm": 56.321868896484375, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 5.76, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3111111111111111, | |
| "grad_norm": 71.17435455322266, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 6.9863, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 32.751712799072266, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 5.7548, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 63.81245040893555, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 5.644, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 29.754924774169922, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 4.8104, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4888888888888889, | |
| "grad_norm": 59.040863037109375, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 3.1751, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 78.91889953613281, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 4.5459, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5777777777777777, | |
| "grad_norm": 19.41783905029297, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 3.8003, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.6222222222222222, | |
| "grad_norm": 19.681726455688477, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 3.1133, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 17.745349884033203, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 2.8088, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 9.727351188659668, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 2.107, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.7555555555555555, | |
| "grad_norm": 10.590718269348145, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.7782, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 11.196682929992676, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.6216, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.8444444444444444, | |
| "grad_norm": 8.443291664123535, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.2221, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 14.523398399353027, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.7676, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.9333333333333333, | |
| "grad_norm": 11.742149353027344, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.2736, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.9777777777777777, | |
| "grad_norm": 4.969881534576416, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.4277, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.0222222222222221, | |
| "grad_norm": 14.083453178405762, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.9514, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 6.694072723388672, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.4019, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.1111111111111112, | |
| "grad_norm": 5.454488754272461, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.3627, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.1111111111111112, | |
| "eval_loss": 0.4674427807331085, | |
| "eval_runtime": 8.5285, | |
| "eval_samples_per_second": 5.863, | |
| "eval_steps_per_second": 1.524, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.1555555555555554, | |
| "grad_norm": 12.888225555419922, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.6015, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 13.187077522277832, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.4939, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.2444444444444445, | |
| "grad_norm": 2.669879674911499, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.0848, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.2888888888888888, | |
| "grad_norm": 6.082226753234863, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.1901, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 6.845930099487305, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.1438, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.3777777777777778, | |
| "grad_norm": 3.527693748474121, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.0763, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.4222222222222223, | |
| "grad_norm": 3.684480905532837, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.0606, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.4666666666666668, | |
| "grad_norm": 3.098820686340332, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.0797, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.511111111111111, | |
| "grad_norm": 2.297424554824829, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.0386, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.5555555555555556, | |
| "grad_norm": 4.277784824371338, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.0329, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 2.5591373443603516, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.0492, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.6444444444444444, | |
| "grad_norm": 2.6662991046905518, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.0238, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.6888888888888889, | |
| "grad_norm": 1.7695767879486084, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.0106, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.7333333333333334, | |
| "grad_norm": 0.13798579573631287, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.0019, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 8.660087585449219, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.1515, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.8222222222222222, | |
| "grad_norm": 1.4062175750732422, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.014, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.8666666666666667, | |
| "grad_norm": 1.929388403892517, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.0195, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.911111111111111, | |
| "grad_norm": 1.239054799079895, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.0084, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.9555555555555557, | |
| "grad_norm": 1.154092788696289, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.0081, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.7374815940856934, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.0199, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.0444444444444443, | |
| "grad_norm": 1.071720004081726, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.0101, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.088888888888889, | |
| "grad_norm": 0.10346444696187973, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.0012, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 0.33200082182884216, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.0021, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.1777777777777776, | |
| "grad_norm": 0.09029132127761841, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.0008, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": 0.11896515637636185, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0007, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "eval_loss": 0.03835269808769226, | |
| "eval_runtime": 8.515, | |
| "eval_samples_per_second": 5.872, | |
| "eval_steps_per_second": 1.527, | |
| "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": 1.1457518287265464e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |