| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00010412147505422994, | |
| "eval_steps": 3, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.470715835140998e-05, | |
| "grad_norm": 7.366649627685547, | |
| "learning_rate": 2e-05, | |
| "loss": 6.754, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.470715835140998e-05, | |
| "eval_loss": 1.3082431554794312, | |
| "eval_runtime": 323.5438, | |
| "eval_samples_per_second": 37.497, | |
| "eval_steps_per_second": 18.749, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.941431670281996e-05, | |
| "grad_norm": 2.6472208499908447, | |
| "learning_rate": 4e-05, | |
| "loss": 5.6375, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00010412147505422994, | |
| "grad_norm": 2.7043254375457764, | |
| "learning_rate": 6e-05, | |
| "loss": 4.9946, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00010412147505422994, | |
| "eval_loss": 1.3049659729003906, | |
| "eval_runtime": 320.7522, | |
| "eval_samples_per_second": 37.824, | |
| "eval_steps_per_second": 18.912, | |
| "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": 342798394982400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |