| { |
| "best_metric": 0.12369738519191742, |
| "best_model_checkpoint": "moments-2_lr0.00001_beta0.9/checkpoint-450", |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 450, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_f1": 0.0, |
| "eval_loss": 0.2882869839668274, |
| "eval_runtime": 3.0943, |
| "eval_samples_per_second": 96.951, |
| "eval_steps_per_second": 12.28, |
| "step": 225 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_f1": 0.6666666666666666, |
| "eval_loss": 0.12369738519191742, |
| "eval_runtime": 3.0482, |
| "eval_samples_per_second": 98.42, |
| "eval_steps_per_second": 12.467, |
| "step": 450 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 4500, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 20, |
| "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": 1151443063495956.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
