| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 5000, | |
| "global_step": 250, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 6.934624875983995, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 2.103, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 5.1807618349506, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 1.8909, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 6.5954086545418065, | |
| "learning_rate": 9.987820251299121e-06, | |
| "loss": 1.824, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 5.007940234065442, | |
| "learning_rate": 9.890738003669029e-06, | |
| "loss": 1.7976, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 5.547938420021615, | |
| "learning_rate": 9.698463103929542e-06, | |
| "loss": 1.7517, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 4.827027410050357, | |
| "learning_rate": 9.414737964294636e-06, | |
| "loss": 1.7713, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 5.056786497937932, | |
| "learning_rate": 9.045084971874738e-06, | |
| "loss": 1.7739, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 5.121984543351305, | |
| "learning_rate": 8.596699001693257e-06, | |
| "loss": 1.7582, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 4.91114831213652, | |
| "learning_rate": 8.078307376628292e-06, | |
| "loss": 1.7622, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 4.683991285272623, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 1.7483, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 4.763566929439094, | |
| "learning_rate": 6.873032967079562e-06, | |
| "loss": 1.7125, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 4.55699687365493, | |
| "learning_rate": 6.209609477998339e-06, | |
| "loss": 1.7158, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 4.305275765374834, | |
| "learning_rate": 5.522642316338268e-06, | |
| "loss": 1.5306, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 5.193573230531262, | |
| "learning_rate": 4.825502516487497e-06, | |
| "loss": 1.216, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 4.796622072535023, | |
| "learning_rate": 4.131759111665349e-06, | |
| "loss": 1.2646, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 4.58108869642696, | |
| "learning_rate": 3.4549150281252635e-06, | |
| "loss": 1.1715, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.3599999999999999, | |
| "grad_norm": 4.310210417447434, | |
| "learning_rate": 2.8081442660546126e-06, | |
| "loss": 1.1951, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 4.192869112702819, | |
| "learning_rate": 2.204035482646267e-06, | |
| "loss": 1.183, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 4.875360102559976, | |
| "learning_rate": 1.6543469682057105e-06, | |
| "loss": 1.1787, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 4.580700158257907, | |
| "learning_rate": 1.1697777844051105e-06, | |
| "loss": 1.215, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.6800000000000002, | |
| "grad_norm": 4.199474615753831, | |
| "learning_rate": 7.597595192178702e-07, | |
| "loss": 1.1823, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 4.8247220195933735, | |
| "learning_rate": 4.322727117869951e-07, | |
| "loss": 1.1846, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.8399999999999999, | |
| "grad_norm": 4.565950530430589, | |
| "learning_rate": 1.9369152030840553e-07, | |
| "loss": 1.1522, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 4.630965250705156, | |
| "learning_rate": 4.865965629214819e-08, | |
| "loss": 1.0957, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 4.304531672963748, | |
| "learning_rate": 0.0, | |
| "loss": 1.1635, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 250, | |
| "total_flos": 6359176904704.0, | |
| "train_loss": 1.4936893577575683, | |
| "train_runtime": 530.0247, | |
| "train_samples_per_second": 3.77, | |
| "train_steps_per_second": 0.472 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 5000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6359176904704.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |