| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 157, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9936305732484076, | |
| "eval_runtime": 318.4788, | |
| "eval_samples_per_second": 3.14, | |
| "eval_steps_per_second": 0.1, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.9872611464968153, | |
| "eval_runtime": 318.9727, | |
| "eval_samples_per_second": 3.135, | |
| "eval_steps_per_second": 0.1, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 2.980891719745223, | |
| "eval_runtime": 318.115, | |
| "eval_samples_per_second": 3.144, | |
| "eval_steps_per_second": 0.101, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_runtime": 319.048, | |
| "eval_samples_per_second": 3.134, | |
| "eval_steps_per_second": 0.1, | |
| "step": 157 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 195, | |
| "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": 1.1594102734848e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |