| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.001840577658218887, | |
| "eval_steps": 10, | |
| "global_step": 13, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00014158289678606824, | |
| "eval_loss": 7.729015827178955, | |
| "eval_runtime": 834.0188, | |
| "eval_samples_per_second": 3.566, | |
| "eval_steps_per_second": 1.783, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007079144839303412, | |
| "grad_norm": 3.9896390438079834, | |
| "learning_rate": 5e-05, | |
| "loss": 7.5715, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0014158289678606825, | |
| "grad_norm": 7.42996883392334, | |
| "learning_rate": 0.0001, | |
| "loss": 7.7081, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0014158289678606825, | |
| "eval_loss": 6.551854133605957, | |
| "eval_runtime": 1047.0566, | |
| "eval_samples_per_second": 2.84, | |
| "eval_steps_per_second": 1.42, | |
| "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": 2404433522589696.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |