| { |
| "best_global_step": 84, |
| "best_metric": 1.3734480142593384, |
| "best_model_checkpoint": "./final_intent_model/checkpoint-84", |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 84, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.7142857142857143, |
| "grad_norm": 6.867106914520264, |
| "learning_rate": 1.5476190476190476e-05, |
| "loss": 2.1539, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.9462890625, |
| "eval_runtime": 0.1331, |
| "eval_samples_per_second": 420.644, |
| "eval_steps_per_second": 52.581, |
| "step": 28 |
| }, |
| { |
| "epoch": 1.4285714285714286, |
| "grad_norm": 6.846766471862793, |
| "learning_rate": 1.0714285714285714e-05, |
| "loss": 1.9324, |
| "step": 40 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 1.5284249782562256, |
| "eval_runtime": 0.2241, |
| "eval_samples_per_second": 249.932, |
| "eval_steps_per_second": 31.241, |
| "step": 56 |
| }, |
| { |
| "epoch": 2.142857142857143, |
| "grad_norm": 9.248769760131836, |
| "learning_rate": 5.9523809523809525e-06, |
| "loss": 1.6384, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.857142857142857, |
| "grad_norm": 8.236637115478516, |
| "learning_rate": 1.1904761904761906e-06, |
| "loss": 1.469, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 1.3734480142593384, |
| "eval_runtime": 0.1798, |
| "eval_samples_per_second": 311.39, |
| "eval_steps_per_second": 38.924, |
| "step": 84 |
| } |
| ], |
| "logging_steps": 20, |
| "max_steps": 84, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "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": 43416052669440.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
