| { |
| "best_metric": 0.8840346336364746, |
| "best_model_checkpoint": "./beans_outputs/checkpoint-17", |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 17, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.5882352941176471, |
| "grad_norm": 1.354477882385254, |
| "learning_rate": 8.23529411764706e-06, |
| "loss": 0.9983, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8646616541353384, |
| "eval_loss": 0.8840346336364746, |
| "eval_runtime": 4.3311, |
| "eval_samples_per_second": 30.708, |
| "eval_steps_per_second": 0.693, |
| "step": 17 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 17, |
| "total_flos": 8.012743541191066e+16, |
| "train_loss": 0.9630123587215648, |
| "train_runtime": 54.0236, |
| "train_samples_per_second": 19.14, |
| "train_steps_per_second": 0.315 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 17, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "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": 8.012743541191066e+16, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
