| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 9.375, |
| "eval_steps": 500, |
| "global_step": 150, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.625, |
| "grad_norm": 0.13900995254516602, |
| "learning_rate": 0.009000000000000001, |
| "loss": 3.240981674194336, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.25, |
| "grad_norm": 0.10888686776161194, |
| "learning_rate": 0.0094, |
| "loss": 3.185182571411133, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.875, |
| "grad_norm": 0.10133716464042664, |
| "learning_rate": 0.008733333333333333, |
| "loss": 3.1393909454345703, |
| "step": 30 |
| }, |
| { |
| "epoch": 2.5, |
| "grad_norm": 0.11951159685850143, |
| "learning_rate": 0.008066666666666666, |
| "loss": 3.1178558349609373, |
| "step": 40 |
| }, |
| { |
| "epoch": 3.125, |
| "grad_norm": 0.07364343106746674, |
| "learning_rate": 0.0074, |
| "loss": 3.1153308868408205, |
| "step": 50 |
| }, |
| { |
| "epoch": 3.75, |
| "grad_norm": 0.11443202942609787, |
| "learning_rate": 0.006733333333333333, |
| "loss": 3.111285591125488, |
| "step": 60 |
| }, |
| { |
| "epoch": 4.375, |
| "grad_norm": 0.13409413397312164, |
| "learning_rate": 0.006066666666666667, |
| "loss": 3.107038116455078, |
| "step": 70 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.12714578211307526, |
| "learning_rate": 0.0054, |
| "loss": 3.1068656921386717, |
| "step": 80 |
| }, |
| { |
| "epoch": 5.625, |
| "grad_norm": 0.11183512210845947, |
| "learning_rate": 0.004733333333333333, |
| "loss": 3.1074026107788084, |
| "step": 90 |
| }, |
| { |
| "epoch": 6.25, |
| "grad_norm": 0.10536977648735046, |
| "learning_rate": 0.004066666666666667, |
| "loss": 3.1052799224853516, |
| "step": 100 |
| }, |
| { |
| "epoch": 6.875, |
| "grad_norm": 0.13250383734703064, |
| "learning_rate": 0.0034000000000000002, |
| "loss": 3.108180809020996, |
| "step": 110 |
| }, |
| { |
| "epoch": 7.5, |
| "grad_norm": 0.09257843345403671, |
| "learning_rate": 0.0027333333333333333, |
| "loss": 3.104732322692871, |
| "step": 120 |
| }, |
| { |
| "epoch": 8.125, |
| "grad_norm": 0.12099669873714447, |
| "learning_rate": 0.0020666666666666667, |
| "loss": 3.1070682525634767, |
| "step": 130 |
| }, |
| { |
| "epoch": 8.75, |
| "grad_norm": 0.11566343903541565, |
| "learning_rate": 0.0014000000000000002, |
| "loss": 3.102994918823242, |
| "step": 140 |
| }, |
| { |
| "epoch": 9.375, |
| "grad_norm": 0.12711389362812042, |
| "learning_rate": 0.0007333333333333333, |
| "loss": 3.106877899169922, |
| "step": 150 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 160, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "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": 162155520.0, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
