| { | |
| "best_metric": 0.28254151344299316, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.32679738562091504, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006535947712418301, | |
| "grad_norm": 81.04505920410156, | |
| "learning_rate": 5e-05, | |
| "loss": 11.1064, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006535947712418301, | |
| "eval_loss": 10.93410873413086, | |
| "eval_runtime": 3.9389, | |
| "eval_samples_per_second": 12.694, | |
| "eval_steps_per_second": 3.3, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013071895424836602, | |
| "grad_norm": 84.43704986572266, | |
| "learning_rate": 0.0001, | |
| "loss": 10.7929, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0196078431372549, | |
| "grad_norm": 51.297943115234375, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 6.2038, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.026143790849673203, | |
| "grad_norm": 38.199363708496094, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.0512, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.032679738562091505, | |
| "grad_norm": 25.375030517578125, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.3986, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0392156862745098, | |
| "grad_norm": 25.622278213500977, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.3294, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0457516339869281, | |
| "grad_norm": 11.487774848937988, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.5629, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05228758169934641, | |
| "grad_norm": 14.262380599975586, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.9633, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.058823529411764705, | |
| "grad_norm": 12.048569679260254, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.7031, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06535947712418301, | |
| "grad_norm": 13.704314231872559, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.5484, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0718954248366013, | |
| "grad_norm": 9.657209396362305, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.4793, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0784313725490196, | |
| "grad_norm": 5.514215469360352, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.4715, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08496732026143791, | |
| "grad_norm": 4.0377116203308105, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.422, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0915032679738562, | |
| "grad_norm": 7.226027965545654, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.4152, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.09803921568627451, | |
| "grad_norm": 5.052182674407959, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.4001, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.10457516339869281, | |
| "grad_norm": 2.393721103668213, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.3588, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1111111111111111, | |
| "grad_norm": 5.823914051055908, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.4459, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.11764705882352941, | |
| "grad_norm": 3.734591245651245, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.3655, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.12418300653594772, | |
| "grad_norm": 4.15626859664917, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.4, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.13071895424836602, | |
| "grad_norm": 3.9641897678375244, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.4168, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.13725490196078433, | |
| "grad_norm": 3.6173903942108154, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.4026, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1437908496732026, | |
| "grad_norm": 2.8172080516815186, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.361, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.1503267973856209, | |
| "grad_norm": 4.506333827972412, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.4224, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1568627450980392, | |
| "grad_norm": 2.879072904586792, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.4037, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.16339869281045752, | |
| "grad_norm": 2.7367208003997803, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.4145, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.16339869281045752, | |
| "eval_loss": 0.28254151344299316, | |
| "eval_runtime": 4.0024, | |
| "eval_samples_per_second": 12.492, | |
| "eval_steps_per_second": 3.248, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.16993464052287582, | |
| "grad_norm": 1.602662205696106, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.3057, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.17647058823529413, | |
| "grad_norm": 1.589160680770874, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.319, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1830065359477124, | |
| "grad_norm": 2.4900217056274414, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.241, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.1895424836601307, | |
| "grad_norm": 1.270291805267334, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.2711, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.19607843137254902, | |
| "grad_norm": 2.1127798557281494, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.2638, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.20261437908496732, | |
| "grad_norm": 2.7198941707611084, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.3523, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.20915032679738563, | |
| "grad_norm": 3.0281879901885986, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.4, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.21568627450980393, | |
| "grad_norm": 2.0487160682678223, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.3356, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 2.616393804550171, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.3093, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.22875816993464052, | |
| "grad_norm": 2.027432918548584, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.2994, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": 1.4597184658050537, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.2981, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.24183006535947713, | |
| "grad_norm": 0.7803646326065063, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.3038, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.24836601307189543, | |
| "grad_norm": 1.935690999031067, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.3237, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.2549019607843137, | |
| "grad_norm": 2.474318265914917, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.2763, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.26143790849673204, | |
| "grad_norm": 2.2222399711608887, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.2458, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2679738562091503, | |
| "grad_norm": 2.2565555572509766, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.2784, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.27450980392156865, | |
| "grad_norm": 1.7884281873703003, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.3071, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.28104575163398693, | |
| "grad_norm": 1.1541043519973755, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.2965, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.2875816993464052, | |
| "grad_norm": 1.7841823101043701, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.2844, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.29411764705882354, | |
| "grad_norm": 3.4865846633911133, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.3227, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3006535947712418, | |
| "grad_norm": 2.5097360610961914, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.3135, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.30718954248366015, | |
| "grad_norm": 1.5082900524139404, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.2822, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3137254901960784, | |
| "grad_norm": 1.5687335729599, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.3099, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3202614379084967, | |
| "grad_norm": 0.6072501540184021, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.2671, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.32679738562091504, | |
| "grad_norm": 0.7342411279678345, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3171, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.32679738562091504, | |
| "eval_loss": 0.29997187852859497, | |
| "eval_runtime": 4.0194, | |
| "eval_samples_per_second": 12.44, | |
| "eval_steps_per_second": 3.234, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 6.174479344467968e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |