| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.5065217391304347, |
| "eval_steps": 500, |
| "global_step": 233, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.10869565217391304, |
| "grad_norm": 0.7875521183013916, |
| "learning_rate": 0.00015793991416309012, |
| "loss": 0.2481, |
| "mean_token_accuracy": 0.9385218358039856, |
| "num_tokens": 54418.0, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.21739130434782608, |
| "grad_norm": 0.49858197569847107, |
| "learning_rate": 0.00011502145922746782, |
| "loss": 0.2152, |
| "mean_token_accuracy": 0.9423152530193328, |
| "num_tokens": 109585.0, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.32608695652173914, |
| "grad_norm": 0.7126598954200745, |
| "learning_rate": 7.21030042918455e-05, |
| "loss": 0.1656, |
| "mean_token_accuracy": 0.9530509519577026, |
| "num_tokens": 165165.0, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.43478260869565216, |
| "grad_norm": 0.5112309455871582, |
| "learning_rate": 2.9184549356223178e-05, |
| "loss": 0.1394, |
| "mean_token_accuracy": 0.9604799973964692, |
| "num_tokens": 219074.0, |
| "step": 200 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 233, |
| "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": 1.3743970216378368e+16, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
