| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 125, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.08, |
| "grad_norm": 2.4951331615448, |
| "learning_rate": 0.00019173553719008265, |
| "loss": 2.2136287689208984, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 1.1572011709213257, |
| "learning_rate": 0.00017520661157024794, |
| "loss": 0.41205081939697263, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 0.7024247050285339, |
| "learning_rate": 0.00015867768595041322, |
| "loss": 0.3598937034606934, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 0.5871134400367737, |
| "learning_rate": 0.0001421487603305785, |
| "loss": 0.3458528995513916, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.4141485095024109, |
| "learning_rate": 0.00012561983471074382, |
| "loss": 0.339448070526123, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 0.39055025577545166, |
| "learning_rate": 0.00010909090909090909, |
| "loss": 0.33486232757568357, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.56, |
| "grad_norm": 0.47050267457962036, |
| "learning_rate": 9.256198347107439e-05, |
| "loss": 0.3365666627883911, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 0.27707022428512573, |
| "learning_rate": 7.603305785123968e-05, |
| "loss": 0.33119356632232666, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.72, |
| "grad_norm": 0.29412567615509033, |
| "learning_rate": 5.950413223140496e-05, |
| "loss": 0.3355336904525757, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.311093270778656, |
| "learning_rate": 4.2975206611570254e-05, |
| "loss": 0.33365061283111574, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.88, |
| "grad_norm": 0.22891905903816223, |
| "learning_rate": 2.644628099173554e-05, |
| "loss": 0.33002266883850095, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 0.24521638453006744, |
| "learning_rate": 9.917355371900826e-06, |
| "loss": 0.3309016704559326, |
| "step": 120 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 125, |
| "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": 5111179675582464.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
