| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 1000, | |
| "global_step": 2758, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00036258158085569254, | |
| "grad_norm": 6.934128284454346, | |
| "learning_rate": 0.0, | |
| "loss": 3.917, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.36258158085569253, | |
| "grad_norm": 6.089656352996826, | |
| "learning_rate": 1.2072507552870091e-05, | |
| "loss": 3.1519, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.36258158085569253, | |
| "eval_cosine_accuracy": 0.9487853646278381, | |
| "eval_loss": 0.5210903286933899, | |
| "eval_runtime": 35.26, | |
| "eval_samples_per_second": 269.682, | |
| "eval_steps_per_second": 1.078, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.7251631617113851, | |
| "grad_norm": 7.9518561363220215, | |
| "learning_rate": 1.896056806164073e-05, | |
| "loss": 1.9693, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.7251631617113851, | |
| "eval_cosine_accuracy": 0.9558312892913818, | |
| "eval_loss": 0.46612653136253357, | |
| "eval_runtime": 34.6788, | |
| "eval_samples_per_second": 274.202, | |
| "eval_steps_per_second": 1.096, | |
| "step": 2000 | |
| } | |
| ], | |
| "logging_steps": 1000, | |
| "max_steps": 8274, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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 | |
| } | |