| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.007313449891440978, | |
| "eval_steps": 2, | |
| "global_step": 4, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0018283624728602445, | |
| "grad_norm": 3.3104889392852783, | |
| "learning_rate": 1e-05, | |
| "loss": 2.7351, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018283624728602445, | |
| "eval_loss": 2.7137372493743896, | |
| "eval_runtime": 73.0686, | |
| "eval_samples_per_second": 12.618, | |
| "eval_steps_per_second": 6.309, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003656724945720489, | |
| "grad_norm": 3.7421786785125732, | |
| "learning_rate": 2e-05, | |
| "loss": 2.7599, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003656724945720489, | |
| "eval_loss": 2.607421398162842, | |
| "eval_runtime": 22.2671, | |
| "eval_samples_per_second": 41.406, | |
| "eval_steps_per_second": 20.703, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005485087418580734, | |
| "grad_norm": 3.3355343341827393, | |
| "learning_rate": 3e-05, | |
| "loss": 2.5934, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007313449891440978, | |
| "grad_norm": 3.516296625137329, | |
| "learning_rate": 4e-05, | |
| "loss": 2.6304, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.007313449891440978, | |
| "eval_loss": 2.4208180904388428, | |
| "eval_runtime": 22.2861, | |
| "eval_samples_per_second": 41.371, | |
| "eval_steps_per_second": 20.686, | |
| "step": 4 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2959302797033472.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |