| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1572052401746725, | |
| "eval_steps": 9, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.017467248908296942, | |
| "eval_loss": 2.185687303543091, | |
| "eval_runtime": 8.5055, | |
| "eval_samples_per_second": 11.404, | |
| "eval_steps_per_second": 1.528, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05240174672489083, | |
| "grad_norm": 3.7532355785369873, | |
| "learning_rate": 3e-05, | |
| "loss": 2.1745, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.10480349344978165, | |
| "grad_norm": 3.853607177734375, | |
| "learning_rate": 6e-05, | |
| "loss": 2.0202, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1572052401746725, | |
| "grad_norm": 2.7308859825134277, | |
| "learning_rate": 9e-05, | |
| "loss": 1.2437, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1572052401746725, | |
| "eval_loss": 0.7501007318496704, | |
| "eval_runtime": 8.6626, | |
| "eval_samples_per_second": 11.198, | |
| "eval_steps_per_second": 1.501, | |
| "step": 9 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 1.5255898586873856e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |