| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.029925187032418952, | |
| "eval_steps": 9, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0033250207813798837, | |
| "eval_loss": 2.4745399951934814, | |
| "eval_runtime": 35.0849, | |
| "eval_samples_per_second": 14.451, | |
| "eval_steps_per_second": 1.824, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00997506234413965, | |
| "grad_norm": 1.8293392658233643, | |
| "learning_rate": 1.5e-05, | |
| "loss": 2.4184, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0199501246882793, | |
| "grad_norm": 2.3942174911499023, | |
| "learning_rate": 3e-05, | |
| "loss": 2.4593, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.029925187032418952, | |
| "grad_norm": 1.915959358215332, | |
| "learning_rate": 4.5e-05, | |
| "loss": 2.2337, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.029925187032418952, | |
| "eval_loss": 2.385331153869629, | |
| "eval_runtime": 35.4941, | |
| "eval_samples_per_second": 14.284, | |
| "eval_steps_per_second": 1.803, | |
| "step": 9 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.3353971104088064e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |