| { | |
| "best_metric": 0.5266842842102051, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.05275652862041678, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0010551305724083356, | |
| "grad_norm": 0.4292043447494507, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8965, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010551305724083356, | |
| "eval_loss": 0.9586341381072998, | |
| "eval_runtime": 4.1793, | |
| "eval_samples_per_second": 11.964, | |
| "eval_steps_per_second": 3.111, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0021102611448166712, | |
| "grad_norm": 0.2899351119995117, | |
| "learning_rate": 0.0001, | |
| "loss": 0.639, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0031653917172250064, | |
| "grad_norm": 0.3149925470352173, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 0.6838, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0042205222896333425, | |
| "grad_norm": 0.33221402764320374, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 0.6493, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005275652862041678, | |
| "grad_norm": 0.3607548773288727, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 0.7081, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006330783434450013, | |
| "grad_norm": 0.2802202105522156, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.6299, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0073859140068583485, | |
| "grad_norm": 0.24148952960968018, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.6125, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.008441044579266685, | |
| "grad_norm": 0.24679714441299438, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.6639, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00949617515167502, | |
| "grad_norm": 0.26838093996047974, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.6307, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010551305724083356, | |
| "grad_norm": 0.31573134660720825, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.6763, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01160643629649169, | |
| "grad_norm": 0.3722541630268097, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.6546, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.012661566868900026, | |
| "grad_norm": 0.5633350014686584, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.7466, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.013716697441308361, | |
| "grad_norm": 0.1893165111541748, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.7427, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.014771828013716697, | |
| "grad_norm": 0.32052120566368103, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.5295, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.015826958586125033, | |
| "grad_norm": 0.3322153389453888, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.566, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01688208915853337, | |
| "grad_norm": 0.27850598096847534, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.5434, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.017937219730941704, | |
| "grad_norm": 0.19619186222553253, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.5404, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01899235030335004, | |
| "grad_norm": 0.17680038511753082, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.5334, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.020047480875758375, | |
| "grad_norm": 0.15371857583522797, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.5379, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.021102611448166712, | |
| "grad_norm": 0.17540892958641052, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.539, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.022157742020575046, | |
| "grad_norm": 0.23744337260723114, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.5321, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02321287259298338, | |
| "grad_norm": 0.2669083774089813, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.5554, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.024268003165391717, | |
| "grad_norm": 0.3324032425880432, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.6257, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.02532313373780005, | |
| "grad_norm": 0.358783483505249, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.5674, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02637826431020839, | |
| "grad_norm": 0.6763550639152527, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.7399, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02637826431020839, | |
| "eval_loss": 0.548164963722229, | |
| "eval_runtime": 4.1257, | |
| "eval_samples_per_second": 12.119, | |
| "eval_steps_per_second": 3.151, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.027433394882616723, | |
| "grad_norm": 0.07384027540683746, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.5594, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.02848852545502506, | |
| "grad_norm": 0.08900860697031021, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.4782, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.029543656027433394, | |
| "grad_norm": 0.11665589362382889, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.4881, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03059878659984173, | |
| "grad_norm": 0.13971996307373047, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.4862, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.031653917172250065, | |
| "grad_norm": 0.16317173838615417, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.5448, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0327090477446584, | |
| "grad_norm": 0.17055854201316833, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.4616, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03376417831706674, | |
| "grad_norm": 0.20446307957172394, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.5126, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.03481930888947507, | |
| "grad_norm": 0.19352230429649353, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.5322, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.03587443946188341, | |
| "grad_norm": 0.1872176229953766, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.5782, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.036929570034291745, | |
| "grad_norm": 0.18367165327072144, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.51, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03798470060670008, | |
| "grad_norm": 0.2161339670419693, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.5731, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.03903983117910841, | |
| "grad_norm": 0.29164037108421326, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.559, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.04009496175151675, | |
| "grad_norm": 0.08342503756284714, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.6285, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.04115009232392509, | |
| "grad_norm": 0.07071754336357117, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.5103, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.042205222896333425, | |
| "grad_norm": 0.0784253254532814, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.4681, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.043260353468741755, | |
| "grad_norm": 0.09445218741893768, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.5245, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.04431548404115009, | |
| "grad_norm": 0.1052173376083374, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.4996, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.04537061461355843, | |
| "grad_norm": 0.10680738091468811, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.4858, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.04642574518596676, | |
| "grad_norm": 0.11538807302713394, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.5183, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0474808757583751, | |
| "grad_norm": 0.1201535016298294, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.4874, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.048536006330783435, | |
| "grad_norm": 0.14609256386756897, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.5095, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.04959113690319177, | |
| "grad_norm": 0.15216562151908875, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.4945, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0506462674756001, | |
| "grad_norm": 0.19578099250793457, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.5177, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.05170139804800844, | |
| "grad_norm": 0.2716890871524811, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.577, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.05275652862041678, | |
| "grad_norm": 0.5881212949752808, | |
| "learning_rate": 1e-05, | |
| "loss": 0.692, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05275652862041678, | |
| "eval_loss": 0.5266842842102051, | |
| "eval_runtime": 4.1068, | |
| "eval_samples_per_second": 12.175, | |
| "eval_steps_per_second": 3.165, | |
| "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": 5.2730742643359744e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |