| { |
| "best_global_step": 525, |
| "best_metric": 7.128874131012708e-05, |
| "best_model_checkpoint": "./results/checkpoint-525", |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 525, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 1.0, |
| "eval_loss": 0.0002624917251523584, |
| "eval_runtime": 1.7254, |
| "eval_samples_per_second": 348.32, |
| "eval_steps_per_second": 44.047, |
| "step": 175 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 1.0, |
| "eval_loss": 9.458453860133886e-05, |
| "eval_runtime": 0.7317, |
| "eval_samples_per_second": 821.396, |
| "eval_steps_per_second": 103.87, |
| "step": 350 |
| }, |
| { |
| "epoch": 2.857142857142857, |
| "grad_norm": 0.002123623387888074, |
| "learning_rate": 2.4761904761904764e-06, |
| "loss": 0.013978575706481934, |
| "step": 500 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 1.0, |
| "eval_loss": 7.128874131012708e-05, |
| "eval_runtime": 0.7439, |
| "eval_samples_per_second": 807.874, |
| "eval_steps_per_second": 102.16, |
| "step": 525 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 525, |
| "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": 278082186628608.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
