| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.0027824151363383415, |
| "eval_steps": 500, |
| "global_step": 5, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0027824151363383415, |
| "grad_norm": 325.9929922400401, |
| "learning_rate": 2.9289321881345257e-06, |
| "loss": 1.7289, |
| "mean_token_accuracy": 0.607302588224411, |
| "num_tokens": 821289.0, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.0027824151363383415, |
| "eval_loss": 1.5143542289733887, |
| "eval_mean_token_accuracy": 0.6351183690130711, |
| "eval_num_tokens": 821289.0, |
| "eval_runtime": 8.8963, |
| "eval_samples_per_second": 112.406, |
| "eval_steps_per_second": 1.798, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.0027824151363383415, |
| "step": 5, |
| "total_flos": 2076365291520.0, |
| "train_loss": 1.728927230834961, |
| "train_runtime": 84.8476, |
| "train_samples_per_second": 7.543, |
| "train_steps_per_second": 0.059 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 5, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2076365291520.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
