| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.994313566206336, | |
| "eval_steps": 500, | |
| "global_step": 921, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.6255077173030057, | |
| "grad_norm": 2.6197683811187744, | |
| "learning_rate": 9.142236699239957e-06, | |
| "loss": 1.2461, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.994313566206336, | |
| "step": 921, | |
| "total_flos": 6.390476256260915e+16, | |
| "train_loss": 0.8569981246765999, | |
| "train_runtime": 9589.9458, | |
| "train_samples_per_second": 3.079, | |
| "train_steps_per_second": 0.096 | |
| }, | |
| { | |
| "epoch": 2.994313566206336, | |
| "step": 921, | |
| "total_flos": 6.390476256260915e+16, | |
| "train_loss": 0.0, | |
| "train_runtime": 0.0416, | |
| "train_samples_per_second": 52999.962, | |
| "train_steps_per_second": 1658.502 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 69, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.390476256260915e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |