| { |
| "best_metric": 0.0637156292796135, |
| "best_model_checkpoint": "training_output/reranker_focal_meta_answer/checkpoint-15132", |
| "epoch": 12.0, |
| "global_step": 15132, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.4, |
| "learning_rate": 4.960348929421095e-05, |
| "loss": 0.0291, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.79, |
| "learning_rate": 4.920697858842189e-05, |
| "loss": 0.0124, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.07028326392173767, |
| "eval_runtime": 70.3628, |
| "eval_samples_per_second": 561.22, |
| "step": 1261 |
| }, |
| { |
| "epoch": 1.19, |
| "learning_rate": 4.881046788263283e-05, |
| "loss": 0.0106, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.59, |
| "learning_rate": 4.841395717684378e-05, |
| "loss": 0.01, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.98, |
| "learning_rate": 4.8017446471054725e-05, |
| "loss": 0.0097, |
| "step": 2500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.06599269062280655, |
| "eval_runtime": 70.3845, |
| "eval_samples_per_second": 561.047, |
| "step": 2522 |
| }, |
| { |
| "epoch": 2.38, |
| "learning_rate": 4.7620935765265664e-05, |
| "loss": 0.0088, |
| "step": 3000 |
| }, |
| { |
| "epoch": 2.78, |
| "learning_rate": 4.722442505947661e-05, |
| "loss": 0.009, |
| "step": 3500 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.0710427388548851, |
| "eval_runtime": 70.4108, |
| "eval_samples_per_second": 560.838, |
| "step": 3783 |
| }, |
| { |
| "epoch": 3.17, |
| "learning_rate": 4.682791435368755e-05, |
| "loss": 0.0085, |
| "step": 4000 |
| }, |
| { |
| "epoch": 3.57, |
| "learning_rate": 4.6431403647898495e-05, |
| "loss": 0.008, |
| "step": 4500 |
| }, |
| { |
| "epoch": 3.97, |
| "learning_rate": 4.6034892942109434e-05, |
| "loss": 0.0078, |
| "step": 5000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.07019173353910446, |
| "eval_runtime": 70.4591, |
| "eval_samples_per_second": 560.452, |
| "step": 5044 |
| }, |
| { |
| "epoch": 4.36, |
| "learning_rate": 4.563838223632038e-05, |
| "loss": 0.007, |
| "step": 5500 |
| }, |
| { |
| "epoch": 4.76, |
| "learning_rate": 4.5241871530531326e-05, |
| "loss": 0.0071, |
| "step": 6000 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 0.06962954998016357, |
| "eval_runtime": 70.4328, |
| "eval_samples_per_second": 560.662, |
| "step": 6305 |
| }, |
| { |
| "epoch": 5.15, |
| "learning_rate": 4.484536082474227e-05, |
| "loss": 0.0066, |
| "step": 6500 |
| }, |
| { |
| "epoch": 5.55, |
| "learning_rate": 4.444885011895321e-05, |
| "loss": 0.0062, |
| "step": 7000 |
| }, |
| { |
| "epoch": 5.95, |
| "learning_rate": 4.405233941316416e-05, |
| "loss": 0.0063, |
| "step": 7500 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 0.07188139855861664, |
| "eval_runtime": 70.4837, |
| "eval_samples_per_second": 560.257, |
| "step": 7566 |
| }, |
| { |
| "epoch": 6.34, |
| "learning_rate": 4.36558287073751e-05, |
| "loss": 0.0056, |
| "step": 8000 |
| }, |
| { |
| "epoch": 6.74, |
| "learning_rate": 4.325931800158605e-05, |
| "loss": 0.0054, |
| "step": 8500 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_loss": 0.06544803828001022, |
| "eval_runtime": 70.4941, |
| "eval_samples_per_second": 560.175, |
| "step": 8827 |
| }, |
| { |
| "epoch": 7.14, |
| "learning_rate": 4.286280729579699e-05, |
| "loss": 0.0053, |
| "step": 9000 |
| }, |
| { |
| "epoch": 7.53, |
| "learning_rate": 4.2466296590007934e-05, |
| "loss": 0.0048, |
| "step": 9500 |
| }, |
| { |
| "epoch": 7.93, |
| "learning_rate": 4.206978588421887e-05, |
| "loss": 0.0049, |
| "step": 10000 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_loss": 0.06971824169158936, |
| "eval_runtime": 70.4814, |
| "eval_samples_per_second": 560.276, |
| "step": 10088 |
| }, |
| { |
| "epoch": 8.33, |
| "learning_rate": 4.167327517842982e-05, |
| "loss": 0.0045, |
| "step": 10500 |
| }, |
| { |
| "epoch": 8.72, |
| "learning_rate": 4.127676447264076e-05, |
| "loss": 0.0043, |
| "step": 11000 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_loss": 0.06489751487970352, |
| "eval_runtime": 70.4921, |
| "eval_samples_per_second": 560.19, |
| "step": 11349 |
| }, |
| { |
| "epoch": 9.12, |
| "learning_rate": 4.0880253766851704e-05, |
| "loss": 0.0043, |
| "step": 11500 |
| }, |
| { |
| "epoch": 9.52, |
| "learning_rate": 4.048374306106265e-05, |
| "loss": 0.0039, |
| "step": 12000 |
| }, |
| { |
| "epoch": 9.91, |
| "learning_rate": 4.0087232355273596e-05, |
| "loss": 0.0042, |
| "step": 12500 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_loss": 0.06486855447292328, |
| "eval_runtime": 70.4903, |
| "eval_samples_per_second": 560.205, |
| "step": 12610 |
| }, |
| { |
| "epoch": 10.31, |
| "learning_rate": 3.9690721649484535e-05, |
| "loss": 0.0037, |
| "step": 13000 |
| }, |
| { |
| "epoch": 10.71, |
| "learning_rate": 3.929421094369548e-05, |
| "loss": 0.0037, |
| "step": 13500 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_loss": 0.06568709015846252, |
| "eval_runtime": 70.5212, |
| "eval_samples_per_second": 559.96, |
| "step": 13871 |
| }, |
| { |
| "epoch": 11.1, |
| "learning_rate": 3.889770023790643e-05, |
| "loss": 0.0036, |
| "step": 14000 |
| }, |
| { |
| "epoch": 11.5, |
| "learning_rate": 3.850118953211737e-05, |
| "loss": 0.0033, |
| "step": 14500 |
| }, |
| { |
| "epoch": 11.9, |
| "learning_rate": 3.810467882632831e-05, |
| "loss": 0.0034, |
| "step": 15000 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_loss": 0.0637156292796135, |
| "eval_runtime": 70.5037, |
| "eval_samples_per_second": 560.098, |
| "step": 15132 |
| } |
| ], |
| "max_steps": 63050, |
| "num_train_epochs": 50, |
| "total_flos": 8.14042362618455e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
