| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9876543209876543, |
| "eval_steps": 100, |
| "global_step": 20, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.24691358024691357, |
| "grad_norm": 2.8213533710551117, |
| "learning_rate": 1.866025403784439e-05, |
| "loss": 1.0711, |
| "mean_token_accuracy": 0.7136330360204468, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.49382716049382713, |
| "grad_norm": 0.9200830078047436, |
| "learning_rate": 1.1736481776669307e-05, |
| "loss": 0.9453, |
| "mean_token_accuracy": 0.7327683591367411, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.7407407407407407, |
| "grad_norm": 0.7482904926497763, |
| "learning_rate": 3.5721239031346067e-06, |
| "loss": 0.8934, |
| "mean_token_accuracy": 0.7430908427007765, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.9876543209876543, |
| "grad_norm": 0.5655985191447793, |
| "learning_rate": 0.0, |
| "loss": 0.8527, |
| "mean_token_accuracy": 0.7547093384596246, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.9876543209876543, |
| "step": 20, |
| "total_flos": 4501058617344.0, |
| "train_loss": 0.9406437873840332, |
| "train_runtime": 76.1726, |
| "train_samples_per_second": 16.896, |
| "train_steps_per_second": 0.263 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 20, |
| "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": false, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4501058617344.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
