此存储库包含 junelee's Wizard Vicuna 13B 的 GPTQ 模型文件 提供了多种GPTQ参数排列

{ "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "global_step": 1608, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 3.0769230769230774e-07, "loss": 0.7856, "step": 1 }, { "epoch": 0.0, "learning_rate": 6.153846153846155e-07, "loss": 0.786, "step": 2 }, { "epoch": 0.01, "learning_rate": 9.230769230769232e-07, "loss": 0.679, "step": 3 }, { "epoch": 0.01, "learning_rate": 1.230769230769231e-06, "loss": 0.692, "step": 4 }, { "epoch": 0.01, "learning_rate": 1.5384615384615387e-06, "loss": 0.6971, "step": 5 }, { "epoch": 0.01, "learning_rate": 1.8461538461538465e-06, "loss": 0.6911, "step": 6 }, { "epoch": 0.01, "learning_rate": 2.153846153846154e-06, "loss": 0.663, "step": 7 }, { "epoch": 0.01, "learning_rate": 2.461538461538462e-06, "loss": 0.6721, "step": 8 }, { "epoch": 0.02, "learning_rate": 2.7692307692307697e-06, "loss": 0.6357, "step": 9 }, { "epoch": 0.02, "learning_rate": 3.0769230769230774e-06, "loss": 0.6395, "step": 10 }, { "epoch": 0.02, "learning_rate": 3.384615384615385e-06, "loss": 0.6251, "step": 11 }, { "epoch": 0.02, "learning_rate": 3.692307692307693e-06, "loss": 0.6247, "step": 12 }, { "epoch": 0.02, "learning_rate": 4.000000000000001e-06, "loss": 0.6278, "step": 13 }, { "epoch": 0.03, "learning_rate": 4.307692307692308e-06, "loss": 0.6028, "step": 14 }, { "epoch": 0.03, "learning_rate": 4.615384615384616e-06, "loss": 0.6283, "step": 15 }, { "epoch": 0.03, "learning_rate": 4.923076923076924e-06, "loss": 0.5906, "step": 16 }, { "epoch": 0.03, "learning_rate": 5.230769230769232e-06, "loss": 0.5916, "step": 17 }, { "epoch": 0.03, "learning_rate": 5.538461538461539e-06, "loss": 0.5868, "step": 18 }, { "epoch": 0.04, "learning_rate": 5.846153846153847e-06, "loss": 0.6087, "step": 19 }, { "epoch": 0.04, "learning_rate": 6.153846153846155e-06, "loss": 0.6172, "step": 20 }, { "epoch": 0.04, "learning_rate": 6.461538461538463e-06, "loss": 0.6048, "step": 21 }, { "epoch": 0.04, "learning_rate": 6.76923076923077e-06, "loss": 0.6075, "step": 22 }, { "epoch": 0.04, "learning_rate": 7.076923076923078e-06, "loss": 0.6053, "step": 23 }, { "epoch": 0.04, "learning_rate": 7.384615384615386e-06, "loss": 0.5914, "step": 24 }, { "epoch": 0.05, "learning_rate": 7.692307692307694e-06, "loss": 0.5933, "step": 25 }, { "epoch": 0.05, "learning_rate": 8.000000000000001e-06, "loss": 0.564, "step": 26 }, { "epoch": 0.05, "learning_rate": 8.307692307692309e-06, "loss": 0.5566, "step": 27 }, { "epoch": 0.05, "learning_rate": 8.615384615384617e-06, "loss": 0.5935, "step": 28 }, { "epoch": 0.05, "learning_rate": 8.923076923076925e-06, "loss": 0.5778, "step": 29 }, { "epoch": 0.06, "learning_rate": 9.230769230769232e-06, "loss": 0.5658, "step": 30 }, { "epoch": 0.06, "learning_rate": 9.53846153846154e-06, "loss": 0.5945, "step": 31 }, { "epoch": 0.06, "learning_rate": 9.846153846153848e-06, "loss": 0.5691, "step": 32 }, { "epoch": 0.06, "learning_rate": 1.0153846153846154e-05, "loss": 0.5716, "step": 33 }, { "epoch": 0.06, "learning_rate": 1.0461538461538463e-05, "loss": 0.5659, "step": 34 }, { "epoch": 0.07, "learning_rate": 1.076923076923077e-05, "loss": 0.5747, "step": 35 }, { "epoch": 0.07, "learning_rate": 1.1076923076923079e-05, "loss": 0.5812, "step": 36 }, { "epoch": 0.07, "learning_rate": 1.1384615384615385e-05, "loss": 0.5545, "step": 37 }, { "epoch": 0.07, "learning_rate": 1.1692307692307694e-05, "loss": 0.5445, "step": 38 }, { "epoch": 0.07, "learning_rate": 1.2e-05, "loss": 0.5513, "step": 39 }, { "epoch": 0.07, "learning_rate": 1.230769230769231e-05, "loss": 0.5447, "step": 40 }, { "epoch": 0.08, "learning_rate": 1.2615384615384616e-05, "loss": 0.5714, "step": 41 }, { "epoch": 0.08, "learning_rate": 1.2923076923076925e-05, "loss": 0.5444, "step": 42 }, { "epoch": 0.08, "learning_rate": 1.3230769230769231e-05, "loss": 0.5682, "step": 43 }, { "epoch": 0.08, "learning_rate": 1.353846153846154e-05, "loss": 0.55, "step": 44 }, { "epoch": 0.08, "learning_rate": 1.3846153846153847e-05, "loss": 0.5543, "step": 45 }, { "epoch": 0.09, "learning_rate": 1.4153846153846156e-05, "loss": 0.5692, "step": 46 }, { "epoch": 0.09, "learning_rate": 1.4461538461538462e-05, "loss": 0.5613, "step": 47 }, { "epoch": 0.09, "learning_rate": 1.4769230769230772e-05, "loss": 0.5727, "step": 48 }, { "epoch": 0.09, "learning_rate": 1.5076923076923078e-05, "loss": 0.5557, "step": 49 }, { "epoch": 0.09, "learning_rate": 1.5384615384615387e-05, "loss": 0.5252, "step": 50 }, { "epoch": 0.1, "learning_rate": 1.5692307692307693e-05, "loss": 0.5369, "step": 51 }, { "epoch": 0.1, "learning_rate": 1.6000000000000003e-05, "loss": 0.5389, "step": 52 }, { "epoch": 0.1, "learning_rate": 1.630769230769231e-05, "loss": 0.5374, "step": 53 }, { "epoch": 0.1, "learning_rate": 1.6615384615384618e-05, "loss": 0.5702, "step": 54 }, { "epoch": 0.1, "learning_rate": 1.6923076923076924e-05, "loss": 0.5602, "step": 55 }, { "epoch": 0.1, "learning_rate": 1.7230769230769234e-05, "loss": 0.549, "step": 56 }, { "epoch": 0.11, "learning_rate": 1.753846153846154e-05, "loss": 0.5496, "step": 57 }, { "epoch": 0.11, "learning_rate": 1.784615384615385e-05, "loss": 0.5779, "step": 58 }, { "epoch": 0.11, "learning_rate": 1.8153846153846155e-05, "loss": 0.5565, "step": 59 }, { "epoch": 0.11, "learning_rate": 1.8461538461538465e-05, "loss": 0.5402, "step": 60 }, { "epoch": 0.11, "learning_rate": 1.876923076923077e-05, "loss": 0.537, "step": 61 }, { "epoch": 0.12, "learning_rate": 1.907692307692308e-05, "loss": 0.55, "step": 62 }, { "epoch": 0.12, "learning_rate": 1.9384615384615386e-05, "loss": 0.5635, "step": 63 }, { "epoch": 0.12, "learning_rate": 1.9692307692307696e-05, "loss": 0.5228, "step": 64 }, { "epoch": 0.12, "learning_rate": 2e-05, "loss": 0.5343, "step": 65 }, { "epoch": 0.12, "learning_rate": 1.999997927293795e-05, "lo