| { |
| "best_metric": 0.9579646012696466, |
| "best_model_checkpoint": "../out/bio/ner-scibert-spanclass/checkpoints/checkpoint-3450", |
| "epoch": 15.265486725663717, |
| "global_step": 3450, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.66, |
| "learning_rate": 9.977876106194692e-06, |
| "loss": 1.1408, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.66, |
| "eval_loss": 0.43231523036956787, |
| "eval_micro_f1": 0.9065265481723156, |
| "eval_runtime": 16.2329, |
| "eval_samples_per_second": 222.758, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.33, |
| "learning_rate": 9.95575221238938e-06, |
| "loss": 0.2911, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.33, |
| "eval_loss": 0.2702934145927429, |
| "eval_micro_f1": 0.9344579641015115, |
| "eval_runtime": 13.695, |
| "eval_samples_per_second": 264.038, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.99, |
| "learning_rate": 9.933628318584071e-06, |
| "loss": 0.1769, |
| "step": 450 |
| }, |
| { |
| "epoch": 1.99, |
| "eval_loss": 0.22861190140247345, |
| "eval_micro_f1": 0.9455199110041632, |
| "eval_runtime": 16.5262, |
| "eval_samples_per_second": 218.804, |
| "step": 450 |
| }, |
| { |
| "epoch": 2.65, |
| "learning_rate": 9.911504424778762e-06, |
| "loss": 0.0951, |
| "step": 600 |
| }, |
| { |
| "epoch": 2.65, |
| "eval_loss": 0.22010141611099243, |
| "eval_micro_f1": 0.9449668136590308, |
| "eval_runtime": 13.6671, |
| "eval_samples_per_second": 264.578, |
| "step": 600 |
| }, |
| { |
| "epoch": 3.32, |
| "learning_rate": 9.889380530973453e-06, |
| "loss": 0.0774, |
| "step": 750 |
| }, |
| { |
| "epoch": 3.32, |
| "eval_loss": 0.22920699417591095, |
| "eval_micro_f1": 0.9457964596767295, |
| "eval_runtime": 8.4285, |
| "eval_samples_per_second": 429.019, |
| "step": 750 |
| }, |
| { |
| "epoch": 3.98, |
| "learning_rate": 9.867256637168142e-06, |
| "loss": 0.0495, |
| "step": 900 |
| }, |
| { |
| "epoch": 3.98, |
| "eval_loss": 0.21396291255950928, |
| "eval_micro_f1": 0.9513274331280555, |
| "eval_runtime": 10.0823, |
| "eval_samples_per_second": 358.649, |
| "step": 900 |
| }, |
| { |
| "epoch": 4.65, |
| "learning_rate": 9.845132743362832e-06, |
| "loss": 0.0309, |
| "step": 1050 |
| }, |
| { |
| "epoch": 4.65, |
| "eval_loss": 0.233700692653656, |
| "eval_micro_f1": 0.9502212384377903, |
| "eval_runtime": 13.8628, |
| "eval_samples_per_second": 260.842, |
| "step": 1050 |
| }, |
| { |
| "epoch": 5.31, |
| "learning_rate": 9.823008849557523e-06, |
| "loss": 0.0256, |
| "step": 1200 |
| }, |
| { |
| "epoch": 5.31, |
| "eval_loss": 0.2532367408275604, |
| "eval_micro_f1": 0.9469026543669947, |
| "eval_runtime": 14.1342, |
| "eval_samples_per_second": 255.834, |
| "step": 1200 |
| }, |
| { |
| "epoch": 5.97, |
| "learning_rate": 9.800884955752214e-06, |
| "loss": 0.0199, |
| "step": 1350 |
| }, |
| { |
| "epoch": 5.97, |
| "eval_loss": 0.2632480263710022, |
| "eval_micro_f1": 0.9460730083492959, |
| "eval_runtime": 13.989, |
| "eval_samples_per_second": 258.488, |
| "step": 1350 |
| }, |
| { |
| "epoch": 6.64, |
| "learning_rate": 9.778761061946903e-06, |
| "loss": 0.0118, |
| "step": 1500 |
| }, |
| { |
| "epoch": 6.64, |
| "eval_loss": 0.27183961868286133, |
| "eval_micro_f1": 0.9460730083492959, |
| "eval_runtime": 16.733, |
| "eval_samples_per_second": 216.099, |
| "step": 1500 |
| }, |
| { |
| "epoch": 7.3, |
| "learning_rate": 9.756637168141593e-06, |
| "loss": 0.0147, |
| "step": 1650 |
| }, |
| { |
| "epoch": 7.3, |
| "eval_loss": 0.2676321268081665, |
| "eval_micro_f1": 0.9502212384377903, |
| "eval_runtime": 15.1239, |
| "eval_samples_per_second": 239.092, |
| "step": 1650 |
| }, |
| { |
| "epoch": 7.96, |
| "learning_rate": 9.734513274336284e-06, |
| "loss": 0.0088, |
| "step": 1800 |
| }, |
| { |
| "epoch": 7.96, |
| "eval_loss": 0.26478642225265503, |
| "eval_micro_f1": 0.9488384950749588, |
| "eval_runtime": 11.1216, |
| "eval_samples_per_second": 325.133, |
| "step": 1800 |
| }, |
| { |
| "epoch": 8.63, |
| "learning_rate": 9.712389380530975e-06, |
| "loss": 0.0062, |
| "step": 1950 |
| }, |
| { |
| "epoch": 8.63, |
| "eval_loss": 0.30603882670402527, |
| "eval_micro_f1": 0.9480088490572599, |
| "eval_runtime": 12.0505, |
| "eval_samples_per_second": 300.071, |
| "step": 1950 |
| }, |
| { |
| "epoch": 9.29, |
| "learning_rate": 9.690265486725664e-06, |
| "loss": 0.0058, |
| "step": 2100 |
| }, |
| { |
| "epoch": 9.29, |
| "eval_loss": 0.3038036823272705, |
| "eval_micro_f1": 0.9477323003846936, |
| "eval_runtime": 15.2086, |
| "eval_samples_per_second": 237.761, |
| "step": 2100 |
| }, |
| { |
| "epoch": 9.96, |
| "learning_rate": 9.668141592920355e-06, |
| "loss": 0.0057, |
| "step": 2250 |
| }, |
| { |
| "epoch": 9.96, |
| "eval_loss": 0.2729575037956238, |
| "eval_micro_f1": 0.9510508844554891, |
| "eval_runtime": 7.7846, |
| "eval_samples_per_second": 464.509, |
| "step": 2250 |
| }, |
| { |
| "epoch": 10.62, |
| "learning_rate": 9.646017699115045e-06, |
| "loss": 0.0052, |
| "step": 2400 |
| }, |
| { |
| "epoch": 10.62, |
| "eval_loss": 0.284730464220047, |
| "eval_micro_f1": 0.9496681410926577, |
| "eval_runtime": 12.2105, |
| "eval_samples_per_second": 296.139, |
| "step": 2400 |
| }, |
| { |
| "epoch": 11.28, |
| "learning_rate": 9.623893805309736e-06, |
| "loss": 0.0032, |
| "step": 2550 |
| }, |
| { |
| "epoch": 11.28, |
| "eval_loss": 0.2924064099788666, |
| "eval_micro_f1": 0.9507743357829229, |
| "eval_runtime": 17.8145, |
| "eval_samples_per_second": 202.981, |
| "step": 2550 |
| }, |
| { |
| "epoch": 11.95, |
| "learning_rate": 9.601769911504427e-06, |
| "loss": 0.0002, |
| "step": 2700 |
| }, |
| { |
| "epoch": 11.95, |
| "eval_loss": 0.30727913975715637, |
| "eval_micro_f1": 0.9499446897652238, |
| "eval_runtime": 7.9256, |
| "eval_samples_per_second": 456.242, |
| "step": 2700 |
| }, |
| { |
| "epoch": 12.61, |
| "learning_rate": 9.579646017699116e-06, |
| "loss": 0.0026, |
| "step": 2850 |
| }, |
| { |
| "epoch": 12.61, |
| "eval_loss": 0.3351140022277832, |
| "eval_micro_f1": 0.9460730083492959, |
| "eval_runtime": 13.6337, |
| "eval_samples_per_second": 265.226, |
| "step": 2850 |
| }, |
| { |
| "epoch": 13.27, |
| "learning_rate": 9.557522123893806e-06, |
| "loss": 0.0028, |
| "step": 3000 |
| }, |
| { |
| "epoch": 13.27, |
| "eval_loss": 0.3179651200771332, |
| "eval_micro_f1": 0.9510508844554891, |
| "eval_runtime": 11.4145, |
| "eval_samples_per_second": 316.79, |
| "step": 3000 |
| }, |
| { |
| "epoch": 13.94, |
| "learning_rate": 9.535398230088495e-06, |
| "loss": 0.0039, |
| "step": 3150 |
| }, |
| { |
| "epoch": 13.94, |
| "eval_loss": 0.3110174536705017, |
| "eval_micro_f1": 0.9507743357829229, |
| "eval_runtime": 17.0074, |
| "eval_samples_per_second": 212.613, |
| "step": 3150 |
| }, |
| { |
| "epoch": 14.6, |
| "learning_rate": 9.513274336283188e-06, |
| "loss": 0.0022, |
| "step": 3300 |
| }, |
| { |
| "epoch": 14.6, |
| "eval_loss": 0.36952659487724304, |
| "eval_micro_f1": 0.9441371676413318, |
| "eval_runtime": 12.5186, |
| "eval_samples_per_second": 288.851, |
| "step": 3300 |
| }, |
| { |
| "epoch": 15.27, |
| "learning_rate": 9.491150442477877e-06, |
| "loss": 0.0013, |
| "step": 3450 |
| }, |
| { |
| "epoch": 15.27, |
| "eval_loss": 0.28838983178138733, |
| "eval_micro_f1": 0.9579646012696466, |
| "eval_runtime": 16.0005, |
| "eval_samples_per_second": 225.993, |
| "step": 3450 |
| } |
| ], |
| "max_steps": 67800, |
| "num_train_epochs": 300, |
| "total_flos": 11961582696110592, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
