| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0028929604628736743, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003214400514304082, | |
| "grad_norm": 2.2572340965270996, | |
| "learning_rate": 2e-05, | |
| "loss": 8.2829, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003214400514304082, | |
| "eval_loss": 2.0177955627441406, | |
| "eval_runtime": 60.9708, | |
| "eval_samples_per_second": 21.486, | |
| "eval_steps_per_second": 10.743, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006428801028608164, | |
| "grad_norm": 2.169924736022949, | |
| "learning_rate": 4e-05, | |
| "loss": 7.2637, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0009643201542912247, | |
| "grad_norm": 1.8544375896453857, | |
| "learning_rate": 6e-05, | |
| "loss": 7.9408, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0009643201542912247, | |
| "eval_loss": 2.0139975547790527, | |
| "eval_runtime": 59.6992, | |
| "eval_samples_per_second": 21.943, | |
| "eval_steps_per_second": 10.972, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0012857602057216328, | |
| "grad_norm": 2.2169251441955566, | |
| "learning_rate": 8e-05, | |
| "loss": 8.4545, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0016072002571520412, | |
| "grad_norm": 2.4655027389526367, | |
| "learning_rate": 0.0001, | |
| "loss": 9.0766, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0019286403085824494, | |
| "grad_norm": 1.885632038116455, | |
| "learning_rate": 0.00012, | |
| "loss": 7.623, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0019286403085824494, | |
| "eval_loss": 1.981154441833496, | |
| "eval_runtime": 59.8218, | |
| "eval_samples_per_second": 21.898, | |
| "eval_steps_per_second": 10.949, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0022500803600128574, | |
| "grad_norm": 1.9592024087905884, | |
| "learning_rate": 0.00014, | |
| "loss": 7.3957, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0025715204114432656, | |
| "grad_norm": 3.445594310760498, | |
| "learning_rate": 0.00016, | |
| "loss": 8.7616, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0028929604628736743, | |
| "grad_norm": 2.8671069145202637, | |
| "learning_rate": 0.00018, | |
| "loss": 6.9782, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0028929604628736743, | |
| "eval_loss": 1.8752474784851074, | |
| "eval_runtime": 59.7402, | |
| "eval_samples_per_second": 21.928, | |
| "eval_steps_per_second": 10.964, | |
| "step": 9 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3637326831943680.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |