| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 1057, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0946073793755913, | |
| "grad_norm": 1.295289158821106, | |
| "learning_rate": 0.0009700409965310628, | |
| "loss": 2.3794, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.1892147587511826, | |
| "grad_norm": 0.7961627244949341, | |
| "learning_rate": 0.0009385052034058657, | |
| "loss": 0.5368, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.28382213812677387, | |
| "grad_norm": 0.8890175223350525, | |
| "learning_rate": 0.0009069694102806686, | |
| "loss": 0.3488, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.3784295175023652, | |
| "grad_norm": 0.5166388154029846, | |
| "learning_rate": 0.0008754336171554715, | |
| "loss": 0.2712, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.47303689687795647, | |
| "grad_norm": 0.3027492165565491, | |
| "learning_rate": 0.0008438978240302744, | |
| "loss": 0.2219, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.5676442762535477, | |
| "grad_norm": 0.8666072487831116, | |
| "learning_rate": 0.0008123620309050773, | |
| "loss": 0.1906, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.6622516556291391, | |
| "grad_norm": 0.5293228030204773, | |
| "learning_rate": 0.0007808262377798802, | |
| "loss": 0.17, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.7568590350047304, | |
| "grad_norm": 0.33755800127983093, | |
| "learning_rate": 0.0007492904446546831, | |
| "loss": 0.1506, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.8514664143803217, | |
| "grad_norm": 0.3760841190814972, | |
| "learning_rate": 0.000717754651529486, | |
| "loss": 0.142, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.9460737937559129, | |
| "grad_norm": 0.3145512044429779, | |
| "learning_rate": 0.0006862188584042889, | |
| "loss": 0.1256, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 3171, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 67458613248000.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |