| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 122, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.16494845360824742, |
| "grad_norm": 2.9061486010905555, |
| "learning_rate": 4.99626950870707e-06, |
| "loss": 1.1360912322998047, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.32989690721649484, |
| "grad_norm": 0.6164337792511091, |
| "learning_rate": 4.8668675889776095e-06, |
| "loss": 0.6491106986999512, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.4948453608247423, |
| "grad_norm": 0.35672779855803904, |
| "learning_rate": 4.561925927872421e-06, |
| "loss": 0.5490317344665527, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.6597938144329897, |
| "grad_norm": 0.2943263275586171, |
| "learning_rate": 4.104060653380403e-06, |
| "loss": 0.5126861572265625, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.8247422680412371, |
| "grad_norm": 0.26771084287039937, |
| "learning_rate": 3.527229538316371e-06, |
| "loss": 0.4959553718566895, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.9896907216494846, |
| "grad_norm": 0.2526261108288278, |
| "learning_rate": 2.8742135076578608e-06, |
| "loss": 0.48491363525390624, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.1484536082474226, |
| "grad_norm": 0.26333199686215103, |
| "learning_rate": 2.1934437730492544e-06, |
| "loss": 0.4727530002593994, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.31340206185567, |
| "grad_norm": 0.24714207754984813, |
| "learning_rate": 1.5354099113921614e-06, |
| "loss": 0.4693778038024902, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.4783505154639176, |
| "grad_norm": 0.24110822645306054, |
| "learning_rate": 9.489152839010799e-07, |
| "loss": 0.465252685546875, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.6432989690721649, |
| "grad_norm": 0.23071324603823393, |
| "learning_rate": 4.774575140626317e-07, |
| "loss": 0.4631986141204834, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.8082474226804124, |
| "grad_norm": 0.22609031836413374, |
| "learning_rate": 1.5600246788994938e-07, |
| "loss": 0.4641274929046631, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.97319587628866, |
| "grad_norm": 0.23062918780152833, |
| "learning_rate": 8.390995598676067e-09, |
| "loss": 0.4627840042114258, |
| "step": 120 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 122, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "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": 5.591335448032051e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
