| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.041911148365465216, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0016764459346186086, | |
| "grad_norm": 41.98318099975586, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 7.7669, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016764459346186086, | |
| "eval_loss": 8.831981658935547, | |
| "eval_runtime": 25.9299, | |
| "eval_samples_per_second": 19.398, | |
| "eval_steps_per_second": 9.719, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003352891869237217, | |
| "grad_norm": 50.515586853027344, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 11.2237, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005029337803855826, | |
| "grad_norm": 52.518070220947266, | |
| "learning_rate": 0.0001, | |
| "loss": 8.3685, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006705783738474434, | |
| "grad_norm": 28.536165237426758, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 5.3907, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008382229673093043, | |
| "grad_norm": 28.03000259399414, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 4.1955, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010058675607711651, | |
| "grad_norm": 24.324188232421875, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.3303, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01173512154233026, | |
| "grad_norm": 25.27045440673828, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 2.5867, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.013411567476948869, | |
| "grad_norm": 18.81125259399414, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 1.4315, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.015088013411567477, | |
| "grad_norm": 14.121123313903809, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.0803, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.016764459346186086, | |
| "grad_norm": 15.772384643554688, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 1.0693, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.018440905280804692, | |
| "grad_norm": 17.11600685119629, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.8722, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.020117351215423303, | |
| "grad_norm": 13.86662769317627, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.7378, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02179379715004191, | |
| "grad_norm": 13.181978225708008, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 0.6078, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.02347024308466052, | |
| "grad_norm": 8.900806427001953, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 0.3962, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.025146689019279127, | |
| "grad_norm": 12.434109687805176, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.5659, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.026823134953897737, | |
| "grad_norm": 10.655670166015625, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 0.6674, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.028499580888516344, | |
| "grad_norm": 7.57264518737793, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 0.2832, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.030176026823134954, | |
| "grad_norm": 8.742619514465332, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.437, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03185247275775356, | |
| "grad_norm": 5.534316539764404, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.1241, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03352891869237217, | |
| "grad_norm": 5.564460277557373, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 0.2132, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03520536462699078, | |
| "grad_norm": 3.952474594116211, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.1064, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.036881810561609385, | |
| "grad_norm": 4.8364129066467285, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 0.1232, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.038558256496227995, | |
| "grad_norm": 7.046288013458252, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 0.1325, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.040234702430846606, | |
| "grad_norm": 9.619534492492676, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.3749, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.041911148365465216, | |
| "grad_norm": 8.914854049682617, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 0.1327, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.041911148365465216, | |
| "eval_loss": 0.24791227281093597, | |
| "eval_runtime": 25.7908, | |
| "eval_samples_per_second": 19.503, | |
| "eval_steps_per_second": 9.771, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9934148626022400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |