| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.042973785990545764, | |
| "global_step": 10000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.0004211081201405e-05, | |
| "loss": 3.9197, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.0016844250917146e-05, | |
| "loss": 3.9108, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.003789928748371e-05, | |
| "loss": 3.8655, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.006737582146571e-05, | |
| "loss": 3.8602, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.010527333566261e-05, | |
| "loss": 3.8478, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.0151591165118474e-05, | |
| "loss": 3.8608, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.020632849713237e-05, | |
| "loss": 3.8431, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.0269484371273996e-05, | |
| "loss": 3.8447, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.034105767939918e-05, | |
| "loss": 3.8422, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.0421047165670686e-05, | |
| "loss": 3.8019, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.050945142657905e-05, | |
| "loss": 3.8109, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.0606268910968035e-05, | |
| "loss": 3.8192, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.071149792006154e-05, | |
| "loss": 3.8037, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.082513660749298e-05, | |
| "loss": 3.8074, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.0947182979338874e-05, | |
| "loss": 3.801, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.1077634894152375e-05, | |
| "loss": 3.786, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.121649006300163e-05, | |
| "loss": 3.7799, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.136374604951046e-05, | |
| "loss": 3.7721, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.1519400269899535e-05, | |
| "loss": 3.7829, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.1683449993033545e-05, | |
| "loss": 3.7922, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.185589234046783e-05, | |
| "loss": 3.7686, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.203672428649923e-05, | |
| "loss": 3.7742, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.2225942658219505e-05, | |
| "loss": 3.753, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.242354413557057e-05, | |
| "loss": 3.7663, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.262952525140289e-05, | |
| "loss": 3.7589, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.2843882391536666e-05, | |
| "loss": 3.7652, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.306661179482435e-05, | |
| "loss": 3.7618, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.329770955321802e-05, | |
| "loss": 3.7441, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.3537171611836355e-05, | |
| "loss": 3.7364, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.3784993769037384e-05, | |
| "loss": 3.7501, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.404117167649071e-05, | |
| "loss": 3.7363, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.43057008392547e-05, | |
| "loss": 3.7279, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.457857661585541e-05, | |
| "loss": 3.7158, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.485979421836779e-05, | |
| "loss": 3.74, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.514934871249906e-05, | |
| "loss": 3.7441, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.544723501767687e-05, | |
| "loss": 3.7141, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.575344790713656e-05, | |
| "loss": 3.7264, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.6067982008014406e-05, | |
| "loss": 3.7221, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.639083180144098e-05, | |
| "loss": 3.7363, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.672199162263839e-05, | |
| "loss": 3.73, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.706145566101981e-05, | |
| "loss": 3.7205, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.740921796029065e-05, | |
| "loss": 3.7192, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.776527241855393e-05, | |
| "loss": 3.7095, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.812961278841707e-05, | |
| "loss": 3.7311, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.85022326771014e-05, | |
| "loss": 3.7031, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.888312554655438e-05, | |
| "loss": 3.6934, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.92722847135643e-05, | |
| "loss": 3.7218, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.9669703349877704e-05, | |
| "loss": 3.711, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 5.0075374482318863e-05, | |
| "loss": 3.7002, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 5.0489290992912625e-05, | |
| "loss": 3.698, | |
| "step": 10000 | |
| } | |
| ], | |
| "max_steps": 500000, | |
| "num_train_epochs": 3, | |
| "total_flos": 1.593829982208e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |