| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 45.0, | |
| "eval_steps": 500, | |
| "global_step": 45, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 1.8389599323272705, | |
| "learning_rate": 4.9309248009941914e-05, | |
| "loss": 3.453, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 0.037354476749897, | |
| "learning_rate": 3.8062464117898724e-05, | |
| "loss": 0.077, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "grad_norm": 0.00799699779599905, | |
| "learning_rate": 1.9163865903602374e-05, | |
| "loss": 0.0004, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "grad_norm": 0.003759935265406966, | |
| "learning_rate": 3.6839958911476957e-06, | |
| "loss": 0.0001, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "step": 45, | |
| "total_flos": 1851009220214784.0, | |
| "train_loss": 0.7845717103155847, | |
| "train_runtime": 154.7444, | |
| "train_samples_per_second": 2.326, | |
| "train_steps_per_second": 0.291 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 45, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 45, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1851009220214784.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |