| { | |
| "best_metric": 2.859468698501587, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.1949317738791423, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003898635477582846, | |
| "grad_norm": 0.3461493253707886, | |
| "learning_rate": 5e-05, | |
| "loss": 2.8801, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003898635477582846, | |
| "eval_loss": 3.456559419631958, | |
| "eval_runtime": 1.7721, | |
| "eval_samples_per_second": 28.215, | |
| "eval_steps_per_second": 7.336, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007797270955165692, | |
| "grad_norm": 0.4024673104286194, | |
| "learning_rate": 0.0001, | |
| "loss": 2.96, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.011695906432748537, | |
| "grad_norm": 0.4904806613922119, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 2.9874, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.015594541910331383, | |
| "grad_norm": 0.4809294641017914, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.8788, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01949317738791423, | |
| "grad_norm": 0.5154537558555603, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.8999, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.023391812865497075, | |
| "grad_norm": 0.544384241104126, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.8836, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02729044834307992, | |
| "grad_norm": 0.5780109167098999, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.8689, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.031189083820662766, | |
| "grad_norm": 0.5785645246505737, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.8486, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03508771929824561, | |
| "grad_norm": 0.619056761264801, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 2.8994, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03898635477582846, | |
| "grad_norm": 0.5879754424095154, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 2.8553, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.042884990253411304, | |
| "grad_norm": 0.7349144220352173, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 2.8687, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04678362573099415, | |
| "grad_norm": 2.103039503097534, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 2.3661, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.050682261208576995, | |
| "grad_norm": 0.9148193597793579, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 2.8528, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.05458089668615984, | |
| "grad_norm": 0.8443722128868103, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.8349, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.05847953216374269, | |
| "grad_norm": 0.6842778921127319, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 2.7925, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06237816764132553, | |
| "grad_norm": 0.5673577785491943, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 2.765, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.06627680311890838, | |
| "grad_norm": 0.4525413513183594, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 2.7274, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.07017543859649122, | |
| "grad_norm": 0.39243853092193604, | |
| "learning_rate": 7.75e-05, | |
| "loss": 2.7372, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07407407407407407, | |
| "grad_norm": 0.4517950713634491, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 2.7865, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.07797270955165692, | |
| "grad_norm": 0.5114383697509766, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 2.8224, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08187134502923976, | |
| "grad_norm": 0.5781399011611938, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 2.7982, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.08576998050682261, | |
| "grad_norm": 0.6390553116798401, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 2.8437, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.08966861598440545, | |
| "grad_norm": 0.7765193581581116, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 2.7538, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0935672514619883, | |
| "grad_norm": 1.0726369619369507, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 2.5752, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.09746588693957114, | |
| "grad_norm": 3.1702678203582764, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 2.8117, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09746588693957114, | |
| "eval_loss": 2.9354588985443115, | |
| "eval_runtime": 1.759, | |
| "eval_samples_per_second": 28.425, | |
| "eval_steps_per_second": 7.39, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10136452241715399, | |
| "grad_norm": 0.28435713052749634, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 2.7583, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.10526315789473684, | |
| "grad_norm": 0.3302833139896393, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 2.7186, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.10916179337231968, | |
| "grad_norm": 0.37060415744781494, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 2.7439, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.11306042884990253, | |
| "grad_norm": 0.37979695200920105, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 2.7777, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.11695906432748537, | |
| "grad_norm": 0.36751940846443176, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 2.719, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.12085769980506822, | |
| "grad_norm": 0.3829987943172455, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 2.7896, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.12475633528265107, | |
| "grad_norm": 0.4021106958389282, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 2.731, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1286549707602339, | |
| "grad_norm": 0.44854679703712463, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 2.7024, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.13255360623781676, | |
| "grad_norm": 0.49962687492370605, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 2.7642, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.1364522417153996, | |
| "grad_norm": 0.5894955992698669, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 2.7013, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.14035087719298245, | |
| "grad_norm": 0.7012891173362732, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 2.7387, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.1442495126705653, | |
| "grad_norm": 1.5239250659942627, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 2.2031, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.14814814814814814, | |
| "grad_norm": 0.5231661796569824, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 2.7886, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.15204678362573099, | |
| "grad_norm": 0.3127061128616333, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 2.6986, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.15594541910331383, | |
| "grad_norm": 0.30186259746551514, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 2.7358, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.15984405458089668, | |
| "grad_norm": 0.32524609565734863, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 2.7544, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.16374269005847952, | |
| "grad_norm": 0.3468033969402313, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 2.8003, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.16764132553606237, | |
| "grad_norm": 0.35150423645973206, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 2.7102, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.17153996101364521, | |
| "grad_norm": 0.36665645241737366, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 2.7094, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.17543859649122806, | |
| "grad_norm": 0.3968718945980072, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 2.6526, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1793372319688109, | |
| "grad_norm": 0.44515466690063477, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 2.725, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.18323586744639375, | |
| "grad_norm": 0.488920658826828, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 2.739, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.1871345029239766, | |
| "grad_norm": 0.6259700059890747, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 2.8396, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.19103313840155944, | |
| "grad_norm": 0.9088934659957886, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 2.5351, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.1949317738791423, | |
| "grad_norm": 4.3960280418396, | |
| "learning_rate": 1e-05, | |
| "loss": 2.3839, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1949317738791423, | |
| "eval_loss": 2.859468698501587, | |
| "eval_runtime": 1.7859, | |
| "eval_samples_per_second": 27.997, | |
| "eval_steps_per_second": 7.279, | |
| "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": 1.059536353886208e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |