| { |
| "best_global_step": 6000, |
| "best_metric": 0.13913892209529877, |
| "best_model_checkpoint": "check-point-qwen2.5-bags/checkpoint-6000", |
| "epoch": 1.43818541379517, |
| "eval_steps": 2000, |
| "global_step": 6000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.479415113561455, |
| "eval_entropy": 0.15272226259689922, |
| "eval_loss": 0.15278592705726624, |
| "eval_mean_token_accuracy": 0.9537118973658066, |
| "eval_num_tokens": 32768000.0, |
| "eval_runtime": 24.1335, |
| "eval_samples_per_second": 42.762, |
| "eval_steps_per_second": 10.691, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.95883022712291, |
| "eval_entropy": 0.14324430717054262, |
| "eval_loss": 0.1443789303302765, |
| "eval_mean_token_accuracy": 0.9558175367902416, |
| "eval_num_tokens": 65536000.0, |
| "eval_runtime": 24.6154, |
| "eval_samples_per_second": 41.925, |
| "eval_steps_per_second": 10.481, |
| "step": 4000 |
| }, |
| { |
| "epoch": 1.43818541379517, |
| "eval_entropy": 0.13332727713178294, |
| "eval_loss": 0.13913892209529877, |
| "eval_mean_token_accuracy": 0.9573415898999502, |
| "eval_num_tokens": 98297856.0, |
| "eval_runtime": 25.4619, |
| "eval_samples_per_second": 40.531, |
| "eval_steps_per_second": 10.133, |
| "step": 6000 |
| } |
| ], |
| "logging_steps": 8344, |
| "max_steps": 41720, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 2000, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 7.728220343768187e+17, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
