| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9990884229717412, | |
| "eval_steps": 500, | |
| "global_step": 137, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07292616226071102, | |
| "grad_norm": 2.03125, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 1.4613, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14585232452142205, | |
| "grad_norm": 1.21875, | |
| "learning_rate": 4.970701059450872e-05, | |
| "loss": 1.2568, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2187784867821331, | |
| "grad_norm": 0.9140625, | |
| "learning_rate": 4.79413289650907e-05, | |
| "loss": 1.2099, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2917046490428441, | |
| "grad_norm": 0.91015625, | |
| "learning_rate": 4.468715765333664e-05, | |
| "loss": 1.1924, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3646308113035551, | |
| "grad_norm": 0.81640625, | |
| "learning_rate": 4.015563527416595e-05, | |
| "loss": 1.1706, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4375569735642662, | |
| "grad_norm": 0.8046875, | |
| "learning_rate": 3.46407781122034e-05, | |
| "loss": 1.1576, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5104831358249772, | |
| "grad_norm": 0.80859375, | |
| "learning_rate": 2.8500403624215734e-05, | |
| "loss": 1.14, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.5834092980856882, | |
| "grad_norm": 0.79296875, | |
| "learning_rate": 2.2132914365039993e-05, | |
| "loss": 1.1243, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.6563354603463992, | |
| "grad_norm": 0.73828125, | |
| "learning_rate": 1.5951448652822047e-05, | |
| "loss": 1.1189, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.7292616226071102, | |
| "grad_norm": 0.6953125, | |
| "learning_rate": 1.035707514179513e-05, | |
| "loss": 1.122, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8021877848678214, | |
| "grad_norm": 0.68359375, | |
| "learning_rate": 5.712770504451426e-06, | |
| "loss": 1.1159, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.8751139471285324, | |
| "grad_norm": 0.69921875, | |
| "learning_rate": 2.3198686149022013e-06, | |
| "loss": 1.1201, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.9480401093892434, | |
| "grad_norm": 0.76953125, | |
| "learning_rate": 3.9850926816357157e-07, | |
| "loss": 1.1217, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.9990884229717412, | |
| "step": 137, | |
| "total_flos": 8.085894968356372e+17, | |
| "train_loss": 1.1745838492456144, | |
| "train_runtime": 5870.8803, | |
| "train_samples_per_second": 2.987, | |
| "train_steps_per_second": 0.023 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 137, | |
| "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": 8.085894968356372e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |