| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006876790830945559, | |
| "eval_steps": 3, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002292263610315186, | |
| "grad_norm": 7.612102508544922, | |
| "learning_rate": 2e-05, | |
| "loss": 2.6658, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002292263610315186, | |
| "eval_loss": 0.6854150891304016, | |
| "eval_runtime": 11.0145, | |
| "eval_samples_per_second": 16.705, | |
| "eval_steps_per_second": 8.353, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004584527220630372, | |
| "grad_norm": 8.802815437316895, | |
| "learning_rate": 4e-05, | |
| "loss": 2.8533, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006876790830945559, | |
| "grad_norm": 6.691609859466553, | |
| "learning_rate": 6e-05, | |
| "loss": 2.8252, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006876790830945559, | |
| "eval_loss": 0.6701761484146118, | |
| "eval_runtime": 10.4102, | |
| "eval_samples_per_second": 17.675, | |
| "eval_steps_per_second": 8.838, | |
| "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": 1051603079528448.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |