| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.1446540880503147, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6225806451612903, | |
| "eval_loss": 0.2530541718006134, | |
| "eval_runtime": 5.617, | |
| "eval_samples_per_second": 551.892, | |
| "eval_steps_per_second": 11.572, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 1.5723270440251573, | |
| "grad_norm": 0.6070442199707031, | |
| "learning_rate": 1.550763701707098e-05, | |
| "loss": 0.4012, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8338709677419355, | |
| "eval_loss": 0.11427825689315796, | |
| "eval_runtime": 5.5731, | |
| "eval_samples_per_second": 556.244, | |
| "eval_steps_per_second": 11.663, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8858064516129033, | |
| "eval_loss": 0.07237184792757034, | |
| "eval_runtime": 5.3748, | |
| "eval_samples_per_second": 576.761, | |
| "eval_steps_per_second": 12.093, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 3.1446540880503147, | |
| "grad_norm": 0.5394158959388733, | |
| "learning_rate": 1.101527403414196e-05, | |
| "loss": 0.1334, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2226, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 7, | |
| "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": 272409458987400.0, | |
| "train_batch_size": 48, | |
| "trial_name": null, | |
| "trial_params": { | |
| "alpha": 0.6556226970507691, | |
| "num_train_epochs": 7, | |
| "temperature": 4 | |
| } | |
| } | |