| { |
| "best_global_step": 75, |
| "best_metric": 1.0301096439361572, |
| "best_model_checkpoint": "./peft-training-1765506126/checkpoint-75", |
| "epoch": 0.5, |
| "eval_steps": 25, |
| "global_step": 75, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.16666666666666666, |
| "grad_norm": 0.5185418128967285, |
| "learning_rate": 0.0001953953953953954, |
| "loss": 1.6287, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.16666666666666666, |
| "eval_loss": 1.1943494081497192, |
| "eval_runtime": 7.8779, |
| "eval_samples_per_second": 9.52, |
| "eval_steps_per_second": 1.269, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.3333333333333333, |
| "grad_norm": 0.4658413231372833, |
| "learning_rate": 0.0001903903903903904, |
| "loss": 1.2089, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.3333333333333333, |
| "eval_loss": 1.0838648080825806, |
| "eval_runtime": 7.9179, |
| "eval_samples_per_second": 9.472, |
| "eval_steps_per_second": 1.263, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 0.5783963799476624, |
| "learning_rate": 0.0001853853853853854, |
| "loss": 1.1048, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.5, |
| "eval_loss": 1.0301096439361572, |
| "eval_runtime": 8.0045, |
| "eval_samples_per_second": 9.37, |
| "eval_steps_per_second": 1.249, |
| "step": 75 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 1000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 7, |
| "save_steps": 25, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2012544618178560.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
