| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.2891629458874556e-05, | |
| "eval_steps": 3, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.7630543152958186e-05, | |
| "grad_norm": 4.367908477783203, | |
| "learning_rate": 2e-05, | |
| "loss": 2.4166, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.7630543152958186e-05, | |
| "eval_loss": 2.4869089126586914, | |
| "eval_runtime": 2092.2381, | |
| "eval_samples_per_second": 11.415, | |
| "eval_steps_per_second": 5.707, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.526108630591637e-05, | |
| "grad_norm": 4.961367130279541, | |
| "learning_rate": 4e-05, | |
| "loss": 2.4042, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 5.2891629458874556e-05, | |
| "grad_norm": 3.3946964740753174, | |
| "learning_rate": 6e-05, | |
| "loss": 2.0628, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 5.2891629458874556e-05, | |
| "eval_loss": 2.404568672180176, | |
| "eval_runtime": 2091.7971, | |
| "eval_samples_per_second": 11.417, | |
| "eval_steps_per_second": 5.708, | |
| "step": 3 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1180126329962496.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |