| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.6037215713301172, | |
| "eval_steps": 73, | |
| "global_step": 219, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.20124052377670573, | |
| "eval_accuracy": 0.699768501945061, | |
| "eval_loss": 0.5667258501052856, | |
| "eval_runtime": 473.7577, | |
| "eval_samples_per_second": 176.888, | |
| "eval_steps_per_second": 5.528, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.27567195037904896, | |
| "grad_norm": 6.989869594573975, | |
| "learning_rate": 8.23236746999302e-06, | |
| "loss": 0.6204, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.40248104755341146, | |
| "eval_accuracy": 0.711975847831794, | |
| "eval_loss": 0.5560464262962341, | |
| "eval_runtime": 459.6994, | |
| "eval_samples_per_second": 182.297, | |
| "eval_steps_per_second": 5.697, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.5513439007580979, | |
| "grad_norm": 9.542524337768555, | |
| "learning_rate": 4.179279784427625e-06, | |
| "loss": 0.5593, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.6037215713301172, | |
| "eval_accuracy": 0.7077874036419178, | |
| "eval_loss": 0.5531944036483765, | |
| "eval_runtime": 459.974, | |
| "eval_samples_per_second": 182.189, | |
| "eval_steps_per_second": 5.694, | |
| "step": 219 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 362, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 73, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |