| { | |
| "best_metric": 1.3029065132141113, | |
| "best_model_checkpoint": "/content/pubmedbert-abstract-cord19/checkpoint-100000", | |
| "epoch": 3.0, | |
| "global_step": 102084, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 2.496e-05, | |
| "loss": 1.3774, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 1.3211560249328613, | |
| "eval_runtime": 169.3169, | |
| "eval_samples_per_second": 86.258, | |
| "eval_steps_per_second": 10.785, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.9945000000000004e-05, | |
| "loss": 1.3937, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 1.4059454202651978, | |
| "eval_runtime": 169.3069, | |
| "eval_samples_per_second": 86.263, | |
| "eval_steps_per_second": 10.785, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.7291603318709e-05, | |
| "loss": 1.6812, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 1.6174367666244507, | |
| "eval_runtime": 168.9751, | |
| "eval_samples_per_second": 86.433, | |
| "eval_steps_per_second": 10.806, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.457723382998132e-05, | |
| "loss": 1.4712, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 1.4382678270339966, | |
| "eval_runtime": 168.9508, | |
| "eval_samples_per_second": 86.445, | |
| "eval_steps_per_second": 10.808, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 4.186340732374788e-05, | |
| "loss": 1.4293, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 1.4356446266174316, | |
| "eval_runtime": 168.8828, | |
| "eval_samples_per_second": 86.48, | |
| "eval_steps_per_second": 10.812, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3.914849485252596e-05, | |
| "loss": 1.4155, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 1.4283361434936523, | |
| "eval_runtime": 169.0831, | |
| "eval_samples_per_second": 86.378, | |
| "eval_steps_per_second": 10.799, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.6435754311281005e-05, | |
| "loss": 1.3963, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "eval_loss": 1.4134665727615356, | |
| "eval_runtime": 169.088, | |
| "eval_samples_per_second": 86.375, | |
| "eval_steps_per_second": 10.799, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 3.372138482255332e-05, | |
| "loss": 1.3718, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "eval_loss": 1.3948187828063965, | |
| "eval_runtime": 169.0271, | |
| "eval_samples_per_second": 86.406, | |
| "eval_steps_per_second": 10.803, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 3.1006472351331396e-05, | |
| "loss": 1.369, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "eval_loss": 1.3961154222488403, | |
| "eval_runtime": 169.0308, | |
| "eval_samples_per_second": 86.404, | |
| "eval_steps_per_second": 10.803, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 2.8292645845097955e-05, | |
| "loss": 1.354, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_loss": 1.378829836845398, | |
| "eval_runtime": 169.1643, | |
| "eval_samples_per_second": 86.336, | |
| "eval_steps_per_second": 10.794, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 2.5579362321358764e-05, | |
| "loss": 1.3399, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "eval_loss": 1.3865987062454224, | |
| "eval_runtime": 169.0688, | |
| "eval_samples_per_second": 86.385, | |
| "eval_steps_per_second": 10.8, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 2.2866078797619567e-05, | |
| "loss": 1.3289, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "eval_loss": 1.362976312637329, | |
| "eval_runtime": 169.1136, | |
| "eval_samples_per_second": 86.362, | |
| "eval_steps_per_second": 10.797, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 2.0151709308891882e-05, | |
| "loss": 1.3155, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "eval_loss": 1.3609150648117065, | |
| "eval_runtime": 169.0556, | |
| "eval_samples_per_second": 86.392, | |
| "eval_steps_per_second": 10.801, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 1.743788280265844e-05, | |
| "loss": 1.2976, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "eval_loss": 1.3489034175872803, | |
| "eval_runtime": 169.1114, | |
| "eval_samples_per_second": 86.363, | |
| "eval_steps_per_second": 10.798, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 1.4724599278919249e-05, | |
| "loss": 1.2783, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "eval_loss": 1.3333380222320557, | |
| "eval_runtime": 169.0576, | |
| "eval_samples_per_second": 86.391, | |
| "eval_steps_per_second": 10.801, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 1.2009686807697321e-05, | |
| "loss": 1.2696, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "eval_loss": 1.3259785175323486, | |
| "eval_runtime": 168.9798, | |
| "eval_samples_per_second": 86.43, | |
| "eval_steps_per_second": 10.806, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 9.29586030146388e-06, | |
| "loss": 1.2607, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "eval_loss": 1.3232313394546509, | |
| "eval_runtime": 168.7484, | |
| "eval_samples_per_second": 86.549, | |
| "eval_steps_per_second": 10.821, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 6.582033795230443e-06, | |
| "loss": 1.2547, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "eval_loss": 1.3033902645111084, | |
| "eval_runtime": 168.7446, | |
| "eval_samples_per_second": 86.551, | |
| "eval_steps_per_second": 10.821, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 3.867664306502758e-06, | |
| "loss": 1.2495, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "eval_loss": 1.3035175800323486, | |
| "eval_runtime": 168.7573, | |
| "eval_samples_per_second": 86.544, | |
| "eval_steps_per_second": 10.82, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 1.1538378002693194e-06, | |
| "loss": 1.2404, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "eval_loss": 1.3029065132141113, | |
| "eval_runtime": 168.8016, | |
| "eval_samples_per_second": 86.522, | |
| "eval_steps_per_second": 10.817, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 102084, | |
| "total_flos": 1.04954332801725e+17, | |
| "train_loss": 1.35220570928797, | |
| "train_runtime": 32542.0864, | |
| "train_samples_per_second": 25.095, | |
| "train_steps_per_second": 3.137 | |
| } | |
| ], | |
| "max_steps": 102084, | |
| "num_train_epochs": 3, | |
| "total_flos": 1.04954332801725e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |