| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 91, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.11049723756906077, |
| "grad_norm": 11.2506103515625, |
| "learning_rate": 7.2e-07, |
| "loss": 1.8026, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.22099447513812154, |
| "grad_norm": 6.07244873046875, |
| "learning_rate": 7.758770483143634e-07, |
| "loss": 1.617, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.3314917127071823, |
| "grad_norm": 4.1009345054626465, |
| "learning_rate": 6.962176052436018e-07, |
| "loss": 1.3842, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.4419889502762431, |
| "grad_norm": 3.1159005165100098, |
| "learning_rate": 5.725544262725014e-07, |
| "loss": 1.1844, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.5524861878453039, |
| "grad_norm": 2.9044346809387207, |
| "learning_rate": 4.232579315641903e-07, |
| "loss": 1.1189, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.6629834254143646, |
| "grad_norm": 2.5874500274658203, |
| "learning_rate": 2.705064231766716e-07, |
| "loss": 1.0706, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.7734806629834254, |
| "grad_norm": 2.463254690170288, |
| "learning_rate": 1.3699145257237458e-07, |
| "loss": 1.0409, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.8839779005524862, |
| "grad_norm": 2.43276309967041, |
| "learning_rate": 4.254694387063513e-08, |
| "loss": 1.0466, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.994475138121547, |
| "grad_norm": 2.4817826747894287, |
| "learning_rate": 1.2028235328831903e-09, |
| "loss": 1.0427, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 91, |
| "total_flos": 368013566017536.0, |
| "train_loss": 1.2484562665551573, |
| "train_runtime": 9550.5077, |
| "train_samples_per_second": 0.303, |
| "train_steps_per_second": 0.01 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 91, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 368013566017536.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
