| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006278449223041909, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006278449223041908, | |
| "grad_norm": 64.84742736816406, | |
| "learning_rate": 2e-05, | |
| "loss": 11.0677, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006278449223041908, | |
| "eval_loss": 3.482679843902588, | |
| "eval_runtime": 8.9058, | |
| "eval_samples_per_second": 75.344, | |
| "eval_steps_per_second": 37.728, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012556898446083817, | |
| "grad_norm": 68.0997314453125, | |
| "learning_rate": 4e-05, | |
| "loss": 15.5951, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0018835347669125726, | |
| "grad_norm": 73.67550659179688, | |
| "learning_rate": 6e-05, | |
| "loss": 12.6231, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0018835347669125726, | |
| "eval_loss": 3.4707937240600586, | |
| "eval_runtime": 8.0731, | |
| "eval_samples_per_second": 83.115, | |
| "eval_steps_per_second": 41.62, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0025113796892167633, | |
| "grad_norm": 132.30996704101562, | |
| "learning_rate": 8e-05, | |
| "loss": 10.6845, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0031392246115209545, | |
| "grad_norm": 54.27143859863281, | |
| "learning_rate": 0.0001, | |
| "loss": 15.3449, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003767069533825145, | |
| "grad_norm": 61.677696228027344, | |
| "learning_rate": 0.00012, | |
| "loss": 13.3455, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003767069533825145, | |
| "eval_loss": 3.372068166732788, | |
| "eval_runtime": 8.1125, | |
| "eval_samples_per_second": 82.712, | |
| "eval_steps_per_second": 41.418, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004394914456129336, | |
| "grad_norm": 76.38861083984375, | |
| "learning_rate": 0.00014, | |
| "loss": 17.475, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005022759378433527, | |
| "grad_norm": 82.15962219238281, | |
| "learning_rate": 0.00016, | |
| "loss": 14.0928, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005650604300737718, | |
| "grad_norm": 68.57530212402344, | |
| "learning_rate": 0.00018, | |
| "loss": 10.6811, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005650604300737718, | |
| "eval_loss": 3.0674076080322266, | |
| "eval_runtime": 8.1104, | |
| "eval_samples_per_second": 82.734, | |
| "eval_steps_per_second": 41.429, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006278449223041909, | |
| "grad_norm": 58.21860122680664, | |
| "learning_rate": 0.0002, | |
| "loss": 10.5424, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 87728565780480.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |