| { | |
| "best_metric": 0.1280977874994278, | |
| "best_model_checkpoint": "saved_model/checkpoint-7574", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 7574, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.9867969368893584e-05, | |
| "loss": 0.2264, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.9735938737787167e-05, | |
| "loss": 0.1508, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.9603908106680753e-05, | |
| "loss": 0.131, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.9471877475574335e-05, | |
| "loss": 0.1143, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.9339846844467918e-05, | |
| "loss": 0.1038, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.92078162133615e-05, | |
| "loss": 0.1031, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.9075785582255083e-05, | |
| "loss": 0.0996, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1.8943754951148666e-05, | |
| "loss": 0.0957, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 1.881172432004225e-05, | |
| "loss": 0.0929, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.8679693688935834e-05, | |
| "loss": 0.0875, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.8547663057829417e-05, | |
| "loss": 0.0888, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.8415632426723e-05, | |
| "loss": 0.0779, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1.8283601795616582e-05, | |
| "loss": 0.0768, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.8151571164510168e-05, | |
| "loss": 0.0733, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1.801954053340375e-05, | |
| "loss": 0.0749, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9679495642989173, | |
| "eval_loss": 0.1280977874994278, | |
| "eval_macro_f1": 0.9678598089097803, | |
| "eval_runtime": 110.0803, | |
| "eval_samples_per_second": 275.217, | |
| "eval_steps_per_second": 8.603, | |
| "step": 7574 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 75740, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 3.188485013274624e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |