| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.03453187723917642, |
| "eval_steps": 50, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.006906375447835283, |
| "grad_norm": 0.6163769960403442, |
| "learning_rate": 4.0909090909090915e-06, |
| "loss": 1.232158088684082, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.013812750895670566, |
| "grad_norm": 0.45759695768356323, |
| "learning_rate": 8.636363636363637e-06, |
| "loss": 1.2015103340148925, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.02071912634350585, |
| "grad_norm": 0.2702416777610779, |
| "learning_rate": 1.3181818181818183e-05, |
| "loss": 1.0803868293762207, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.027625501791341132, |
| "grad_norm": 0.31841039657592773, |
| "learning_rate": 1.772727272727273e-05, |
| "loss": 0.9162900924682618, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.03453187723917642, |
| "grad_norm": 0.406064510345459, |
| "learning_rate": 1.9999374148910363e-05, |
| "loss": 0.912994384765625, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.03453187723917642, |
| "eval_loss": 0.8581966757774353, |
| "eval_runtime": 1039.6495, |
| "eval_samples_per_second": 0.455, |
| "eval_steps_per_second": 0.455, |
| "step": 50 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 1448, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 50, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 9.325311885873648e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
