| { | |
| "best_metric": 9.132105827331543, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.010414632558745036, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00020829265117490073, | |
| "grad_norm": 16.775585174560547, | |
| "learning_rate": 5e-05, | |
| "loss": 11.857, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00020829265117490073, | |
| "eval_loss": 11.821998596191406, | |
| "eval_runtime": 0.4935, | |
| "eval_samples_per_second": 101.322, | |
| "eval_steps_per_second": 26.344, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00041658530234980147, | |
| "grad_norm": 16.417312622070312, | |
| "learning_rate": 0.0001, | |
| "loss": 11.8648, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0006248779535247023, | |
| "grad_norm": 15.215269088745117, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 11.725, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008331706046996029, | |
| "grad_norm": 12.356354713439941, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 11.409, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0010414632558745037, | |
| "grad_norm": 11.116938591003418, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 11.1807, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0012497559070494045, | |
| "grad_norm": 11.471768379211426, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 11.0242, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001458048558224305, | |
| "grad_norm": 10.600059509277344, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 10.8553, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0016663412093992059, | |
| "grad_norm": 12.011614799499512, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 10.8957, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0018746338605741067, | |
| "grad_norm": 11.320947647094727, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 10.7531, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0020829265117490075, | |
| "grad_norm": 10.006556510925293, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 10.5875, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002291219162923908, | |
| "grad_norm": 9.139665603637695, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 10.4485, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.002499511814098809, | |
| "grad_norm": 8.3920259475708, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 10.3098, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0027078044652737096, | |
| "grad_norm": 6.650846004486084, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 10.1004, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00291609711644861, | |
| "grad_norm": 6.051239013671875, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 10.0127, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.003124389767623511, | |
| "grad_norm": 5.502382755279541, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 9.9458, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0033326824187984118, | |
| "grad_norm": 5.097620487213135, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 9.8759, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0035409750699733123, | |
| "grad_norm": 4.649333953857422, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 9.8135, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0037492677211482133, | |
| "grad_norm": 4.2913818359375, | |
| "learning_rate": 7.75e-05, | |
| "loss": 9.7549, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003957560372323114, | |
| "grad_norm": 4.431560516357422, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 9.6946, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.004165853023498015, | |
| "grad_norm": 3.745075225830078, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 9.6538, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004374145674672915, | |
| "grad_norm": 3.8385586738586426, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 9.6214, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.004582438325847816, | |
| "grad_norm": 3.910820484161377, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 9.5972, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.004790730977022717, | |
| "grad_norm": 3.666306495666504, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 9.5416, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.004999023628197618, | |
| "grad_norm": 3.4422073364257812, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 9.4762, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.005207316279372518, | |
| "grad_norm": 3.5492684841156006, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 9.4458, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005207316279372518, | |
| "eval_loss": 9.407609939575195, | |
| "eval_runtime": 0.5038, | |
| "eval_samples_per_second": 99.239, | |
| "eval_steps_per_second": 25.802, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005415608930547419, | |
| "grad_norm": 2.699100971221924, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 9.4023, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.00562390158172232, | |
| "grad_norm": 2.5721964836120605, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 9.3974, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.00583219423289722, | |
| "grad_norm": 2.452620267868042, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 9.3736, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.006040486884072121, | |
| "grad_norm": 2.3704941272735596, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 9.3641, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.006248779535247022, | |
| "grad_norm": 2.2959113121032715, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 9.3428, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0064570721864219225, | |
| "grad_norm": 2.5590760707855225, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 9.3309, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0066653648375968235, | |
| "grad_norm": 2.2302350997924805, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 9.3157, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0068736574887717245, | |
| "grad_norm": 2.2170119285583496, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 9.2802, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.007081950139946625, | |
| "grad_norm": 2.3711395263671875, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 9.2608, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.007290242791121526, | |
| "grad_norm": 2.4080708026885986, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 9.246, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.007498535442296427, | |
| "grad_norm": 2.4190449714660645, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 9.2148, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.007706828093471327, | |
| "grad_norm": 2.703991174697876, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 9.2031, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.007915120744646228, | |
| "grad_norm": 2.100898265838623, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 9.2105, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.008123413395821129, | |
| "grad_norm": 2.0093116760253906, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 9.2042, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.00833170604699603, | |
| "grad_norm": 1.8878018856048584, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 9.198, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.00853999869817093, | |
| "grad_norm": 1.8706705570220947, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 9.2053, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.00874829134934583, | |
| "grad_norm": 1.8576347827911377, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 9.2106, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.008956584000520731, | |
| "grad_norm": 1.8795746564865112, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 9.207, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.009164876651695632, | |
| "grad_norm": 2.854189395904541, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 9.2486, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.009373169302870533, | |
| "grad_norm": 1.8021515607833862, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 9.171, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.009581461954045434, | |
| "grad_norm": 1.9334605932235718, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 9.1662, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.009789754605220335, | |
| "grad_norm": 1.9953815937042236, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 9.1518, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.009998047256395236, | |
| "grad_norm": 2.0963637828826904, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 9.131, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.010206339907570135, | |
| "grad_norm": 2.3475289344787598, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 9.1236, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.010414632558745036, | |
| "grad_norm": 3.048788070678711, | |
| "learning_rate": 1e-05, | |
| "loss": 9.1111, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.010414632558745036, | |
| "eval_loss": 9.132105827331543, | |
| "eval_runtime": 0.5071, | |
| "eval_samples_per_second": 98.598, | |
| "eval_steps_per_second": 25.635, | |
| "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": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 311333514903552.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |