| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9946714031971581, | |
| "eval_steps": 100, | |
| "global_step": 35, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2841918294849023, | |
| "grad_norm": 7.636162757873535, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.5668, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5683836589698046, | |
| "grad_norm": 4.247854709625244, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3333, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8525754884547069, | |
| "grad_norm": 3.775770425796509, | |
| "learning_rate": 1.2500000000000006e-05, | |
| "loss": 1.2611, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.9946714031971581, | |
| "step": 35, | |
| "total_flos": 1.0171584618692608e+16, | |
| "train_loss": 1.3742423057556152, | |
| "train_runtime": 1847.7373, | |
| "train_samples_per_second": 4.871, | |
| "train_steps_per_second": 0.019 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 35, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0171584618692608e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |