| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0007830735637376704, | |
| "eval_steps": 10, | |
| "global_step": 13, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.02364279798208e-05, | |
| "eval_loss": 5.864229202270508, | |
| "eval_runtime": 643.2876, | |
| "eval_samples_per_second": 10.866, | |
| "eval_steps_per_second": 5.433, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00030118213989910396, | |
| "grad_norm": 1.7193124294281006, | |
| "learning_rate": 5e-05, | |
| "loss": 5.7912, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0006023642797982079, | |
| "grad_norm": 3.2139346599578857, | |
| "learning_rate": 0.0001, | |
| "loss": 5.5145, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0006023642797982079, | |
| "eval_loss": 4.955783843994141, | |
| "eval_runtime": 646.6116, | |
| "eval_samples_per_second": 10.81, | |
| "eval_steps_per_second": 5.405, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3738198614212608.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |