| { |
| "best_global_step": 1, |
| "best_metric": 0.22503923, |
| "best_model_checkpoint": "/app/outputs/sft-qwen3/v3-20260317-133746/checkpoint-1", |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 1, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.15579837330600022, |
| "learning_rate": 1e-05, |
| "loss": 0.3281792104244232, |
| "step": 1, |
| "token_acc": 0.922295852928602 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.22503922879695892, |
| "eval_runtime": 3.6435, |
| "eval_samples_per_second": 0.549, |
| "eval_steps_per_second": 0.274, |
| "eval_token_acc": 0.9450915901512037, |
| "step": 1 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.22503922879695892, |
| "eval_runtime": 2.0475, |
| "eval_samples_per_second": 0.977, |
| "eval_steps_per_second": 0.488, |
| "eval_token_acc": 0.9450915901512037, |
| "step": 1 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 1, |
| "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": 10981327503360.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
