| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0032144005143040825, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003214400514304082, | |
| "grad_norm": 2.290867328643799, | |
| "learning_rate": 2e-05, | |
| "loss": 8.2829, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003214400514304082, | |
| "eval_loss": 2.0177955627441406, | |
| "eval_runtime": 60.7868, | |
| "eval_samples_per_second": 21.551, | |
| "eval_steps_per_second": 10.775, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006428801028608164, | |
| "grad_norm": 2.178492784500122, | |
| "learning_rate": 4e-05, | |
| "loss": 7.2637, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0009643201542912247, | |
| "grad_norm": 1.8839120864868164, | |
| "learning_rate": 6e-05, | |
| "loss": 7.954, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0009643201542912247, | |
| "eval_loss": 2.0139377117156982, | |
| "eval_runtime": 59.5833, | |
| "eval_samples_per_second": 21.986, | |
| "eval_steps_per_second": 10.993, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0012857602057216328, | |
| "grad_norm": 2.3659818172454834, | |
| "learning_rate": 8e-05, | |
| "loss": 8.4341, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0016072002571520412, | |
| "grad_norm": 2.5587334632873535, | |
| "learning_rate": 0.0001, | |
| "loss": 9.0658, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0019286403085824494, | |
| "grad_norm": 1.8856533765792847, | |
| "learning_rate": 0.00012, | |
| "loss": 7.571, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0019286403085824494, | |
| "eval_loss": 1.9818049669265747, | |
| "eval_runtime": 59.4312, | |
| "eval_samples_per_second": 22.042, | |
| "eval_steps_per_second": 11.021, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0022500803600128574, | |
| "grad_norm": 1.9607654809951782, | |
| "learning_rate": 0.00014, | |
| "loss": 7.4009, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0025715204114432656, | |
| "grad_norm": 3.441317081451416, | |
| "learning_rate": 0.00016, | |
| "loss": 8.7644, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0028929604628736743, | |
| "grad_norm": 3.002718210220337, | |
| "learning_rate": 0.00018, | |
| "loss": 6.979, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0028929604628736743, | |
| "eval_loss": 1.8745183944702148, | |
| "eval_runtime": 59.6456, | |
| "eval_samples_per_second": 21.963, | |
| "eval_steps_per_second": 10.982, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0032144005143040825, | |
| "grad_norm": 3.2213339805603027, | |
| "learning_rate": 0.0002, | |
| "loss": 7.9439, | |
| "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": 4065247635701760.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |