| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.00854481756814492, |
| "eval_steps": 25, |
| "global_step": 25, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 1.2600676015019416, |
| "epoch": 0.003417927027257968, |
| "grad_norm": 0.486328125, |
| "learning_rate": 0.00015000000000000001, |
| "loss": 1.3553205490112306, |
| "mean_token_accuracy": 0.7003426559269428, |
| "num_tokens": 50495.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 1.0893292173743248, |
| "epoch": 0.006835854054515936, |
| "grad_norm": 0.53125, |
| "learning_rate": 2.9289321881345254e-05, |
| "loss": 1.1145251274108887, |
| "mean_token_accuracy": 0.7432689998298884, |
| "num_tokens": 99591.0, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.00854481756814492, |
| "eval_entropy": 1.0693371649831533, |
| "eval_loss": 1.040876865386963, |
| "eval_mean_token_accuracy": 0.7473227139562368, |
| "eval_num_tokens": 125580.0, |
| "eval_runtime": 32.1389, |
| "eval_samples_per_second": 7.965, |
| "eval_steps_per_second": 0.996, |
| "step": 25 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 25, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 25, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 8226081949527936.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
