| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.716981132075472, | |
| "eval_steps": 500, | |
| "global_step": 1500, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5980645161290322, | |
| "eval_loss": 0.2370469570159912, | |
| "eval_runtime": 5.131, | |
| "eval_samples_per_second": 604.169, | |
| "eval_steps_per_second": 12.668, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 1.5723270440251573, | |
| "grad_norm": 0.5828151106834412, | |
| "learning_rate": 1.4758909853249476e-05, | |
| "loss": 0.3737, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8264516129032258, | |
| "eval_loss": 0.11328593641519547, | |
| "eval_runtime": 5.5375, | |
| "eval_samples_per_second": 559.823, | |
| "eval_steps_per_second": 11.738, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8780645161290322, | |
| "eval_loss": 0.0755920559167862, | |
| "eval_runtime": 5.1832, | |
| "eval_samples_per_second": 598.091, | |
| "eval_steps_per_second": 12.541, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 3.1446540880503147, | |
| "grad_norm": 0.5158044099807739, | |
| "learning_rate": 9.517819706498952e-06, | |
| "loss": 0.1316, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8916129032258064, | |
| "eval_loss": 0.0598440058529377, | |
| "eval_runtime": 5.2058, | |
| "eval_samples_per_second": 595.488, | |
| "eval_steps_per_second": 12.486, | |
| "step": 1272 | |
| }, | |
| { | |
| "epoch": 4.716981132075472, | |
| "grad_norm": 0.3741317093372345, | |
| "learning_rate": 4.276729559748428e-06, | |
| "loss": 0.0865, | |
| "step": 1500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1908, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 391368939443328.0, | |
| "train_batch_size": 48, | |
| "trial_name": null, | |
| "trial_params": { | |
| "alpha": 0.4750594581069757, | |
| "num_train_epochs": 6, | |
| "temperature": 5 | |
| } | |
| } | |