| { | |
| "best_global_step": 7352, | |
| "best_metric": 0.947425127029419, | |
| "best_model_checkpoint": "/kaggle/working/checkpoint-7352", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 7352, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 36.47157669067383, | |
| "learning_rate": 8.432529699118777e-06, | |
| "loss": 8.9556, | |
| "step": 3676 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_runtime": 58.0349, | |
| "eval_samples_per_second": 0.0, | |
| "eval_steps_per_second": 0.0, | |
| "eval_validation_eval_cosine_accuracy": 0.9409878849983215, | |
| "step": 3676 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 17.716238021850586, | |
| "learning_rate": 3.0211621605838098e-06, | |
| "loss": 5.7553, | |
| "step": 7352 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_runtime": 58.536, | |
| "eval_samples_per_second": 0.0, | |
| "eval_steps_per_second": 0.0, | |
| "eval_validation_eval_cosine_accuracy": 0.947425127029419, | |
| "step": 7352 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 11028, | |
| "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": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |