| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.061068702290076333, | |
| "eval_steps": 6, | |
| "global_step": 24, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002544529262086514, | |
| "grad_norm": 2.992696523666382, | |
| "learning_rate": 2e-05, | |
| "loss": 1.1826, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002544529262086514, | |
| "eval_loss": 1.6133360862731934, | |
| "eval_runtime": 7.5869, | |
| "eval_samples_per_second": 21.88, | |
| "eval_steps_per_second": 10.94, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005089058524173028, | |
| "grad_norm": 3.473165512084961, | |
| "learning_rate": 4e-05, | |
| "loss": 1.4445, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007633587786259542, | |
| "grad_norm": 2.82555890083313, | |
| "learning_rate": 6e-05, | |
| "loss": 1.175, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010178117048346057, | |
| "grad_norm": 2.444389581680298, | |
| "learning_rate": 8e-05, | |
| "loss": 0.8444, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01272264631043257, | |
| "grad_norm": 2.6523401737213135, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0504, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015267175572519083, | |
| "grad_norm": 2.7490906715393066, | |
| "learning_rate": 0.00012, | |
| "loss": 1.0024, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.015267175572519083, | |
| "eval_loss": 0.9683742523193359, | |
| "eval_runtime": 7.6156, | |
| "eval_samples_per_second": 21.797, | |
| "eval_steps_per_second": 10.899, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.017811704834605598, | |
| "grad_norm": 2.5362422466278076, | |
| "learning_rate": 0.00014, | |
| "loss": 0.8316, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.020356234096692113, | |
| "grad_norm": 2.6198008060455322, | |
| "learning_rate": 0.00016, | |
| "loss": 0.6159, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.022900763358778626, | |
| "grad_norm": 2.256551742553711, | |
| "learning_rate": 0.00018, | |
| "loss": 0.4382, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02544529262086514, | |
| "grad_norm": 2.475969076156616, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3562, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.027989821882951654, | |
| "grad_norm": 3.510289192199707, | |
| "learning_rate": 0.00019749279121818235, | |
| "loss": 0.3165, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.030534351145038167, | |
| "grad_norm": 1.8848199844360352, | |
| "learning_rate": 0.0001900968867902419, | |
| "loss": 0.2195, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.030534351145038167, | |
| "eval_loss": 0.1976952999830246, | |
| "eval_runtime": 7.5845, | |
| "eval_samples_per_second": 21.887, | |
| "eval_steps_per_second": 10.943, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03307888040712468, | |
| "grad_norm": 1.0237454175949097, | |
| "learning_rate": 0.000178183148246803, | |
| "loss": 0.0876, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.035623409669211195, | |
| "grad_norm": 2.4736454486846924, | |
| "learning_rate": 0.00016234898018587337, | |
| "loss": 0.2691, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03816793893129771, | |
| "grad_norm": 3.9042718410491943, | |
| "learning_rate": 0.00014338837391175582, | |
| "loss": 0.2463, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04071246819338423, | |
| "grad_norm": 2.2620346546173096, | |
| "learning_rate": 0.00012225209339563145, | |
| "loss": 0.2234, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.043256997455470736, | |
| "grad_norm": 2.5762858390808105, | |
| "learning_rate": 0.0001, | |
| "loss": 0.4415, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04580152671755725, | |
| "grad_norm": 1.2997937202453613, | |
| "learning_rate": 7.774790660436858e-05, | |
| "loss": 0.1092, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04580152671755725, | |
| "eval_loss": 0.16112367808818817, | |
| "eval_runtime": 7.6895, | |
| "eval_samples_per_second": 21.588, | |
| "eval_steps_per_second": 10.794, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04834605597964377, | |
| "grad_norm": 0.7907422780990601, | |
| "learning_rate": 5.6611626088244194e-05, | |
| "loss": 0.0608, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05089058524173028, | |
| "grad_norm": 1.1940962076187134, | |
| "learning_rate": 3.7651019814126654e-05, | |
| "loss": 0.2102, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05343511450381679, | |
| "grad_norm": 1.0911586284637451, | |
| "learning_rate": 2.181685175319702e-05, | |
| "loss": 0.098, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05597964376590331, | |
| "grad_norm": 2.3480300903320312, | |
| "learning_rate": 9.903113209758096e-06, | |
| "loss": 0.32, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.058524173027989825, | |
| "grad_norm": 0.9640387296676636, | |
| "learning_rate": 2.5072087818176382e-06, | |
| "loss": 0.1036, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.061068702290076333, | |
| "grad_norm": 1.2761191129684448, | |
| "learning_rate": 0.0, | |
| "loss": 0.128, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.061068702290076333, | |
| "eval_loss": 0.16466298699378967, | |
| "eval_runtime": 7.5305, | |
| "eval_samples_per_second": 22.044, | |
| "eval_steps_per_second": 11.022, | |
| "step": 24 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 24, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 6, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1200233593700352.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |