| { | |
| "best_metric": 1.1599400043487549, | |
| "best_model_checkpoint": "./beans_outputs/checkpoint-1", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 2, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.125, | |
| "eval_loss": 1.1599400043487549, | |
| "eval_runtime": 0.2079, | |
| "eval_samples_per_second": 38.483, | |
| "eval_steps_per_second": 4.81, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.0, | |
| "eval_loss": 1.1626136302947998, | |
| "eval_runtime": 0.1072, | |
| "eval_samples_per_second": 74.595, | |
| "eval_steps_per_second": 9.324, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 2, | |
| "total_flos": 1239882946412544.0, | |
| "train_loss": 0.96820068359375, | |
| "train_runtime": 21.5994, | |
| "train_samples_per_second": 0.741, | |
| "train_steps_per_second": 0.093 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 2, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 1239882946412544.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |