| { |
| "best_global_step": 74, |
| "best_metric": 0.9931506849315068, |
| "best_model_checkpoint": "./conceptnet-intent-classifier/checkpoint-74", |
| "epoch": 5.0, |
| "eval_steps": 500, |
| "global_step": 185, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8972602739726028, |
| "eval_loss": 0.388628214597702, |
| "eval_runtime": 0.168, |
| "eval_samples_per_second": 869.095, |
| "eval_steps_per_second": 29.764, |
| "step": 37 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9931506849315068, |
| "eval_loss": 0.05768229067325592, |
| "eval_runtime": 0.1184, |
| "eval_samples_per_second": 1232.64, |
| "eval_steps_per_second": 42.214, |
| "step": 74 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9863013698630136, |
| "eval_loss": 0.0521763451397419, |
| "eval_runtime": 0.1295, |
| "eval_samples_per_second": 1127.358, |
| "eval_steps_per_second": 38.608, |
| "step": 111 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9863013698630136, |
| "eval_loss": 0.04882890358567238, |
| "eval_runtime": 0.1156, |
| "eval_samples_per_second": 1262.665, |
| "eval_steps_per_second": 43.242, |
| "step": 148 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9863013698630136, |
| "eval_loss": 0.0471014566719532, |
| "eval_runtime": 0.1148, |
| "eval_samples_per_second": 1271.363, |
| "eval_steps_per_second": 43.54, |
| "step": 185 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 185, |
| "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": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 14828598312192.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
