| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 1000, | |
| "global_step": 2529, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00039541320680110717, | |
| "grad_norm": 6.574801445007324, | |
| "learning_rate": 0.0, | |
| "loss": 4.3129, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.39541320680110714, | |
| "grad_norm": 6.2015180587768555, | |
| "learning_rate": 9.871541501976284e-06, | |
| "loss": 3.298, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.39541320680110714, | |
| "eval_cosine_accuracy": 0.9471027255058289, | |
| "eval_loss": 0.5520303249359131, | |
| "eval_runtime": 36.3857, | |
| "eval_samples_per_second": 261.339, | |
| "eval_steps_per_second": 1.044, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.7908264136022143, | |
| "grad_norm": 8.382867813110352, | |
| "learning_rate": 1.9752964426877474e-05, | |
| "loss": 1.9673, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.7908264136022143, | |
| "eval_cosine_accuracy": 0.953938364982605, | |
| "eval_loss": 0.4995275139808655, | |
| "eval_runtime": 34.9654, | |
| "eval_samples_per_second": 271.955, | |
| "eval_steps_per_second": 1.087, | |
| "step": 2000 | |
| } | |
| ], | |
| "logging_steps": 1000, | |
| "max_steps": 20232, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 8, | |
| "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": 0.0, | |
| "train_batch_size": 256, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |