| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.984126984126984, | |
| "global_step": 9400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 5e-05, | |
| "loss": 2.1043, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.7206703910614525e-05, | |
| "loss": 1.4607, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.4413407821229054e-05, | |
| "loss": 1.331, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 4.1620111731843576e-05, | |
| "loss": 1.2417, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 3.8826815642458106e-05, | |
| "loss": 1.1599, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 3.603351955307263e-05, | |
| "loss": 1.1286, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.324022346368715e-05, | |
| "loss": 0.978, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 3.0446927374301676e-05, | |
| "loss": 0.9336, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 2.7653631284916205e-05, | |
| "loss": 0.9469, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 2.4860335195530728e-05, | |
| "loss": 0.9089, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 2.206703910614525e-05, | |
| "loss": 0.8395, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 1.9273743016759776e-05, | |
| "loss": 0.8046, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 1.64804469273743e-05, | |
| "loss": 0.7157, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 1.3687150837988827e-05, | |
| "loss": 0.6048, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 1.0893854748603351e-05, | |
| "loss": 0.618, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 8.100558659217877e-06, | |
| "loss": 0.6173, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 5.307262569832402e-06, | |
| "loss": 0.6185, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 2.5139664804469276e-06, | |
| "loss": 0.5967, | |
| "step": 9000 | |
| } | |
| ], | |
| "max_steps": 9450, | |
| "num_train_epochs": 3, | |
| "total_flos": 2.1134250039809664e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |