| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1643509565320877, | |
| "global_step": 11048, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.9950413059216727e-05, | |
| "loss": 14.0627, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.9900826118433453e-05, | |
| "loss": 6.3799, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.9851239177650176e-05, | |
| "loss": 5.31, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.9801652236866898e-05, | |
| "loss": 4.9781, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.9752065296083624e-05, | |
| "loss": 4.7392, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.970247835530035e-05, | |
| "loss": 4.5779, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.9652891414517075e-05, | |
| "loss": 4.4691, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.96033044737338e-05, | |
| "loss": 4.3745, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.9553717532950524e-05, | |
| "loss": 4.2883, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.9504130592167246e-05, | |
| "loss": 4.2342, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.9454543651383972e-05, | |
| "loss": 4.1614, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.9404956710600698e-05, | |
| "loss": 4.1279, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.9355369769817423e-05, | |
| "loss": 4.0802, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.930578282903415e-05, | |
| "loss": 4.0298, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.925619588825087e-05, | |
| "loss": 3.9697, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.9206608947467594e-05, | |
| "loss": 3.9584, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.915702200668432e-05, | |
| "loss": 3.9196, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.9107435065901046e-05, | |
| "loss": 3.9081, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.905784812511777e-05, | |
| "loss": 3.8419, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.9008261184334497e-05, | |
| "loss": 3.8363, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.895867424355122e-05, | |
| "loss": 3.8047, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.8909087302767945e-05, | |
| "loss": 3.7728, | |
| "step": 11000 | |
| } | |
| ], | |
| "max_steps": 201666, | |
| "num_train_epochs": 3, | |
| "total_flos": 1.298603121721344e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |