| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 5, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 2.919967442750931, |
| "epoch": 0.47058823529411764, |
| "grad_norm": 0.7388926148414612, |
| "learning_rate": 5e-05, |
| "loss": 3.528480052947998, |
| "mean_token_accuracy": 0.39445167779922485, |
| "num_tokens": 1330.0, |
| "step": 2 |
| }, |
| { |
| "entropy": 2.921311140060425, |
| "epoch": 0.9411764705882353, |
| "grad_norm": 0.7427535653114319, |
| "learning_rate": 2.5e-05, |
| "loss": 3.505293607711792, |
| "mean_token_accuracy": 0.3824109882116318, |
| "num_tokens": 2602.0, |
| "step": 4 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_entropy": 2.845902681350708, |
| "eval_loss": 3.5877914428710938, |
| "eval_mean_token_accuracy": 0.38056680560112, |
| "eval_num_tokens": 2814.0, |
| "eval_runtime": 0.8041, |
| "eval_samples_per_second": 3.731, |
| "eval_steps_per_second": 1.244, |
| "step": 5 |
| } |
| ], |
| "logging_steps": 2, |
| "max_steps": 5, |
| "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": 1824259739904.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
