| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 1000, | |
| "global_step": 2165, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00046189376443418013, | |
| "grad_norm": 7.368561744689941, | |
| "learning_rate": 0.0, | |
| "loss": 3.6183, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.4618937644341801, | |
| "eval_cosine_accuracy": 0.9518148303031921, | |
| "eval_loss": 1.2476075887680054, | |
| "eval_runtime": 21.6936, | |
| "eval_samples_per_second": 438.147, | |
| "eval_steps_per_second": 1.752, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.9237875288683602, | |
| "eval_cosine_accuracy": 0.9532877206802368, | |
| "eval_loss": 1.1978851556777954, | |
| "eval_runtime": 21.447, | |
| "eval_samples_per_second": 443.185, | |
| "eval_steps_per_second": 1.772, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 18.16141128540039, | |
| "learning_rate": 1.7780970953505083e-05, | |
| "loss": 2.4107, | |
| "step": 2165 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 10825, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "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 | |
| } | |