| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 7.0, | |
| "eval_steps": 500, | |
| "global_step": 2226, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.0064516129032258064, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.3916, | |
| "eval_samples_per_second": 574.969, | |
| "eval_steps_per_second": 12.056, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 1.5723270440251573, | |
| "grad_norm": 93591.875, | |
| "learning_rate": 1.550763701707098e-05, | |
| "loss": 0.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.0064516129032258064, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.9484, | |
| "eval_samples_per_second": 521.151, | |
| "eval_steps_per_second": 10.927, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.0064516129032258064, | |
| "eval_loss": NaN, | |
| "eval_runtime": 6.1057, | |
| "eval_samples_per_second": 507.718, | |
| "eval_steps_per_second": 10.646, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 3.1446540880503147, | |
| "grad_norm": 409918.25, | |
| "learning_rate": 1.101527403414196e-05, | |
| "loss": 0.0, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.0064516129032258064, | |
| "eval_loss": NaN, | |
| "eval_runtime": 8.0601, | |
| "eval_samples_per_second": 384.61, | |
| "eval_steps_per_second": 8.064, | |
| "step": 1272 | |
| }, | |
| { | |
| "epoch": 4.716981132075472, | |
| "grad_norm": 870723.3125, | |
| "learning_rate": 6.522911051212939e-06, | |
| "loss": 0.0, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.0064516129032258064, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.685, | |
| "eval_samples_per_second": 545.292, | |
| "eval_steps_per_second": 11.434, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.0064516129032258064, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.6061, | |
| "eval_samples_per_second": 552.966, | |
| "eval_steps_per_second": 11.594, | |
| "step": 1908 | |
| }, | |
| { | |
| "epoch": 6.289308176100629, | |
| "grad_norm": 1086472.875, | |
| "learning_rate": 2.0305480682839176e-06, | |
| "loss": 0.0, | |
| "step": 2000 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 520991326672152.0, | |
| "train_batch_size": 48, | |
| "trial_name": null, | |
| "trial_params": { | |
| "alpha": 0.22641126713384185, | |
| "num_train_epochs": 7, | |
| "temperature": 10 | |
| } | |
| } | |