| { | |
| "best_metric": 2.9354588985443115, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.09746588693957114, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "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 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.29768176943104e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |