| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 5.0, |
| "eval_steps": 500, |
| "global_step": 515, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.41088836479966884, |
| "las": 90.11845774060063, |
| "step": 103, |
| "uas": 92.5142522244126 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.35711488044150524, |
| "las": 91.45576926492267, |
| "step": 206, |
| "uas": 93.5105759497043 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.3521741897424805, |
| "las": 92.34198234677748, |
| "step": 309, |
| "uas": 94.16413589784574 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.38171229114599314, |
| "las": 92.63679471468912, |
| "step": 412, |
| "uas": 94.42165272523843 |
| }, |
| { |
| "epoch": 4.854368932038835, |
| "grad_norm": 0.9455211162567139, |
| "learning_rate": 5.825242718446602e-06, |
| "loss": 0.3874, |
| "step": 500 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 515, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "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": 1.126545536687616e+16, |
| "train_batch_size": 128, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
