--- base_model: meta-llama/Llama-3.1-8B library_name: peft license: llama3.1 tags: - generated_from_trainer model-index: - name: llama3.1-8B_finetune_genQA_wiki_r64_v2 results: [] --- # llama3.1-8B_finetune_genQA_wiki_r64_v2 This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.3744 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 3.6e-05 - train_batch_size: 4 - eval_batch_size: 4 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 1 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:------:|:-----:|:---------------:| | 0.5552 | 0.0028 | 200 | 0.4789 | | 0.3971 | 0.0057 | 400 | 0.4757 | | 0.576 | 0.0085 | 600 | 0.4745 | | 0.5104 | 0.0113 | 800 | 0.4738 | | 0.6768 | 0.0142 | 1000 | 0.4725 | | 0.4755 | 0.0170 | 1200 | 0.4715 | | 0.304 | 0.0199 | 1400 | 0.4706 | | 0.5975 | 0.0227 | 1600 | 0.4703 | | 0.4878 | 0.0255 | 1800 | 0.4692 | | 0.3835 | 0.0284 | 2000 | 0.4684 | | 0.5211 | 0.0312 | 2200 | 0.4683 | | 0.4565 | 0.0340 | 2400 | 0.4673 | | 0.4741 | 0.0369 | 2600 | 0.4671 | | 0.4993 | 0.0397 | 2800 | 0.4664 | | 0.2234 | 0.0426 | 3000 | 0.4664 | | 0.5535 | 0.0454 | 3200 | 0.4654 | | 0.4021 | 0.0482 | 3400 | 0.4649 | | 0.5119 | 0.0511 | 3600 | 0.4640 | | 0.4791 | 0.0539 | 3800 | 0.4634 | | 0.3927 | 0.0567 | 4000 | 0.4619 | | 0.5627 | 0.0596 | 4200 | 0.4614 | | 0.3563 | 0.0624 | 4400 | 0.4608 | | 0.4719 | 0.0652 | 4600 | 0.4604 | | 0.562 | 0.0681 | 4800 | 0.4593 | | 0.5258 | 0.0709 | 5000 | 0.4591 | | 0.4483 | 0.0738 | 5200 | 0.4583 | | 0.4827 | 0.0766 | 5400 | 0.4572 | | 0.3712 | 0.0794 | 5600 | 0.4577 | | 0.3198 | 0.0823 | 5800 | 0.4565 | | 0.4168 | 0.0851 | 6000 | 0.4567 | | 0.4166 | 0.0879 | 6200 | 0.4566 | | 0.3014 | 0.0908 | 6400 | 0.4557 | | 0.397 | 0.0936 | 6600 | 0.4550 | | 0.4803 | 0.0965 | 6800 | 0.4540 | | 0.4119 | 0.0993 | 7000 | 0.4540 | | 0.5685 | 0.1021 | 7200 | 0.4532 | | 0.4883 | 0.1050 | 7400 | 0.4532 | | 0.5795 | 0.1078 | 7600 | 0.4531 | | 0.5066 | 0.1106 | 7800 | 0.4524 | | 0.4414 | 0.1135 | 8000 | 0.4522 | | 0.3382 | 0.1163 | 8200 | 0.4520 | | 0.5088 | 0.1191 | 8400 | 0.4521 | | 0.4083 | 0.1220 | 8600 | 0.4523 | | 0.437 | 0.1248 | 8800 | 0.4518 | | 0.3769 | 0.1277 | 9000 | 0.4513 | | 0.3828 | 0.1305 | 9200 | 0.4513 | | 0.5162 | 0.1333 | 9400 | 0.4506 | | 0.3603 | 0.1362 | 9600 | 0.4501 | | 0.6039 | 0.1390 | 9800 | 0.4500 | | 0.3339 | 0.1418 | 10000 | 0.4493 | | 0.3821 | 0.1447 | 10200 | 0.4491 | | 0.478 | 0.1475 | 10400 | 0.4488 | | 0.3994 | 0.1504 | 10600 | 0.4481 | | 0.4471 | 0.1532 | 10800 | 0.4474 | | 0.4102 | 0.1560 | 11000 | 0.4471 | | 0.3164 | 0.1589 | 11200 | 0.4464 | | 0.3487 | 0.1617 | 11400 | 0.4458 | | 0.4359 | 0.1645 | 11600 | 0.4455 | | 0.5473 | 0.1674 | 11800 | 0.4450 | | 0.5629 | 0.1702 | 12000 | 0.4452 | | 0.5864 | 0.1730 | 12200 | 0.4446 | | 0.4339 | 0.1759 | 12400 | 0.4442 | | 0.3727 | 0.1787 | 12600 | 0.4447 | | 0.4229 | 0.1816 | 12800 | 0.4439 | | 0.4888 | 0.1844 | 13000 | 0.4437 | | 0.4252 | 0.1872 | 13200 | 0.4439 | | 0.5414 | 0.1901 | 13400 | 0.4432 | | 0.4577 | 0.1929 | 13600 | 0.4429 | | 0.4698 | 0.1957 | 13800 | 0.4425 | | 0.488 | 0.1986 | 14000 | 0.4423 | | 0.3836 | 0.2014 | 14200 | 0.4419 | | 0.4724 | 0.2043 | 14400 | 0.4415 | | 0.4451 | 0.2071 | 14600 | 0.4412 | | 0.4409 | 0.2099 | 14800 | 0.4408 | | 0.4377 | 0.2128 | 15000 | 0.4410 | | 0.4688 | 0.2156 | 15200 | 0.4408 | | 0.4975 | 0.2184 | 15400 | 0.4406 | | 0.5752 | 0.2213 | 15600 | 0.4405 | | 0.4824 | 0.2241 | 15800 | 0.4399 | | 0.379 | 0.2270 | 16000 | 0.4396 | | 0.5237 | 0.2298 | 16200 | 0.4396 | | 0.491 | 0.2326 | 16400 | 0.4389 | | 0.4132 | 0.2355 | 16600 | 0.4388 | | 0.4417 | 0.2383 | 16800 | 0.4385 | | 0.4859 | 0.2411 | 17000 | 0.4380 | | 0.4579 | 0.2440 | 17200 | 0.4377 | | 0.5186 | 0.2468 | 17400 | 0.4366 | | 0.4055 | 0.2496 | 17600 | 0.4362 | | 0.5011 | 0.2525 | 17800 | 0.4359 | | 0.3842 | 0.2553 | 18000 | 0.4350 | | 0.5457 | 0.2582 | 18200 | 0.4352 | | 0.5447 | 0.2610 | 18400 | 0.4350 | | 0.4722 | 0.2638 | 18600 | 0.4349 | | 0.4229 | 0.2667 | 18800 | 0.4340 | | 0.5047 | 0.2695 | 19000 | 0.4338 | | 0.2641 | 0.2723 | 19200 | 0.4340 | | 0.3937 | 0.2752 | 19400 | 0.4333 | | 0.4082 | 0.2780 | 19600 | 0.4332 | | 0.3958 | 0.2809 | 19800 | 0.4317 | | 0.4929 | 0.2837 | 20000 | 0.4315 | | 0.4739 | 0.2865 | 20200 | 0.4313 | | 0.5014 | 0.2894 | 20400 | 0.4316 | | 0.3236 | 0.2922 | 20600 | 0.4308 | | 0.3615 | 0.2950 | 20800 | 0.4299 | | 0.4235 | 0.2979 | 21000 | 0.4297 | | 0.2811 | 0.3007 | 21200 | 0.4295 | | 0.2743 | 0.3035 | 21400 | 0.4287 | | 0.4718 | 0.3064 | 21600 | 0.4290 | | 0.5184 | 0.3092 | 21800 | 0.4289 | | 0.3954 | 0.3121 | 22000 | 0.4289 | | 0.4478 | 0.3149 | 22200 | 0.4288 | | 0.4001 | 0.3177 | 22400 | 0.4288 | | 0.4768 | 0.3206 | 22600 | 0.4288 | | 0.3908 | 0.3234 | 22800 | 0.4284 | | 0.4068 | 0.3262 | 23000 | 0.4280 | | 0.3719 | 0.3291 | 23200 | 0.4270 | | 0.3995 | 0.3319 | 23400 | 0.4266 | | 0.4877 | 0.3348 | 23600 | 0.4262 | | 0.5297 | 0.3376 | 23800 | 0.4262 | | 0.4355 | 0.3404 | 24000 | 0.4259 | | 0.4551 | 0.3433 | 24200 | 0.4255 | | 0.4737 | 0.3461 | 24400 | 0.4253 | | 0.3971 | 0.3489 | 24600 | 0.4252 | | 0.3989 | 0.3518 | 24800 | 0.4247 | | 0.5214 | 0.3546 | 25000 | 0.4246 | | 0.4378 | 0.3574 | 25200 | 0.4244 | | 0.5113 | 0.3603 | 25400 | 0.4246 | | 0.4544 | 0.3631 | 25600 | 0.4246 | | 0.4151 | 0.3660 | 25800 | 0.4244 | | 0.3019 | 0.3688 | 26000 | 0.4243 | | 0.4397 | 0.3716 | 26200 | 0.4242 | | 0.5191 | 0.3745 | 26400 | 0.4238 | | 0.3183 | 0.3773 | 26600 | 0.4237 | | 0.203 | 0.3801 | 26800 | 0.4236 | | 0.522 | 0.3830 | 27000 | 0.4231 | | 0.4159 | 0.3858 | 27200 | 0.4232 | | 0.348 | 0.3887 | 27400 | 0.4231 | | 0.5155 | 0.3915 | 27600 | 0.4229 | | 0.5407 | 0.3943 | 27800 | 0.4226 | | 0.4152 | 0.3972 | 28000 | 0.4219 | | 0.4148 | 0.4 | 28200 | 0.4213 | | 0.5514 | 0.4028 | 28400 | 0.4206 | | 0.4132 | 0.4057 | 28600 | 0.4201 | | 0.4249 | 0.4085 | 28800 | 0.4199 | | 0.4003 | 0.4113 | 29000 | 0.4199 | | 0.3864 | 0.4142 | 29200 | 0.4194 | | 0.3573 | 0.4170 | 29400 | 0.4192 | | 0.4098 | 0.4199 | 29600 | 0.4185 | | 0.3843 | 0.4227 | 29800 | 0.4187 | | 0.5306 | 0.4255 | 30000 | 0.4187 | | 0.2888 | 0.4284 | 30200 | 0.4183 | | 0.2458 | 0.4312 | 30400 | 0.4176 | | 0.3408 | 0.4340 | 30600 | 0.4169 | | 0.4499 | 0.4369 | 30800 | 0.4162 | | 0.4447 | 0.4397 | 31000 | 0.4157 | | 0.523 | 0.4426 | 31200 | 0.4160 | | 0.47 | 0.4454 | 31400 | 0.4160 | | 0.3046 | 0.4482 | 31600 | 0.4155 | | 0.4464 | 0.4511 | 31800 | 0.4156 | | 0.4347 | 0.4539 | 32000 | 0.4152 | | 0.5663 | 0.4567 | 32200 | 0.4152 | | 0.4236 | 0.4596 | 32400 | 0.4150 | | 0.4682 | 0.4624 | 32600 | 0.4143 | | 0.2078 | 0.4652 | 32800 | 0.4138 | | 0.4289 | 0.4681 | 33000 | 0.4135 | | 0.4123 | 0.4709 | 33200 | 0.4134 | | 0.2913 | 0.4738 | 33400 | 0.4132 | | 0.3788 | 0.4766 | 33600 | 0.4131 | | 0.3111 | 0.4794 | 33800 | 0.4132 | | 0.5047 | 0.4823 | 34000 | 0.4124 | | 0.3096 | 0.4851 | 34200 | 0.4124 | | 0.5126 | 0.4879 | 34400 | 0.4121 | | 0.5116 | 0.4908 | 34600 | 0.4117 | | 0.3009 | 0.4936 | 34800 | 0.4115 | | 0.5036 | 0.4965 | 35000 | 0.4108 | | 0.4221 | 0.4993 | 35200 | 0.4109 | | 0.5021 | 0.5021 | 35400 | 0.4109 | | 0.2946 | 0.5050 | 35600 | 0.4108 | | 0.4487 | 0.5078 | 35800 | 0.4104 | | 0.3863 | 0.5106 | 36000 | 0.4103 | | 0.3043 | 0.5135 | 36200 | 0.4097 | | 0.5039 | 0.5163 | 36400 | 0.4092 | | 0.537 | 0.5191 | 36600 | 0.4087 | | 0.3525 | 0.5220 | 36800 | 0.4082 | | 0.3099 | 0.5248 | 37000 | 0.4081 | | 0.4568 | 0.5277 | 37200 | 0.4080 | | 0.1907 | 0.5305 | 37400 | 0.4079 | | 0.5096 | 0.5333 | 37600 | 0.4074 | | 0.4411 | 0.5362 | 37800 | 0.4068 | | 0.4075 | 0.5390 | 38000 | 0.4070 | | 0.5252 | 0.5418 | 38200 | 0.4067 | | 0.2606 | 0.5447 | 38400 | 0.4060 | | 0.4556 | 0.5475 | 38600 | 0.4060 | | 0.3456 | 0.5504 | 38800 | 0.4056 | | 0.2922 | 0.5532 | 39000 | 0.4050 | | 0.4582 | 0.5560 | 39200 | 0.4043 | | 0.3284 | 0.5589 | 39400 | 0.4039 | | 0.511 | 0.5617 | 39600 | 0.4035 | | 0.4445 | 0.5645 | 39800 | 0.4035 | | 0.2857 | 0.5674 | 40000 | 0.4035 | | 0.4778 | 0.5702 | 40200 | 0.4030 | | 0.4949 | 0.5730 | 40400 | 0.4025 | | 0.4691 | 0.5759 | 40600 | 0.4021 | | 0.6142 | 0.5787 | 40800 | 0.4022 | | 0.2999 | 0.5816 | 41000 | 0.4011 | | 0.4709 | 0.5844 | 41200 | 0.4010 | | 0.3927 | 0.5872 | 41400 | 0.4004 | | 0.4305 | 0.5901 | 41600 | 0.4001 | | 0.4798 | 0.5929 | 41800 | 0.3988 | | 0.5321 | 0.5957 | 42000 | 0.3988 | | 0.5152 | 0.5986 | 42200 | 0.3987 | | 0.3418 | 0.6014 | 42400 | 0.3984 | | 0.4056 | 0.6043 | 42600 | 0.3984 | | 0.2357 | 0.6071 | 42800 | 0.3983 | | 0.3883 | 0.6099 | 43000 | 0.3980 | | 0.4356 | 0.6128 | 43200 | 0.3978 | | 0.3481 | 0.6156 | 43400 | 0.3977 | | 0.3969 | 0.6184 | 43600 | 0.3971 | | 0.459 | 0.6213 | 43800 | 0.3969 | | 0.3185 | 0.6241 | 44000 | 0.3969 | | 0.4342 | 0.6270 | 44200 | 0.3963 | | 0.448 | 0.6298 | 44400 | 0.3961 | | 0.4198 | 0.6326 | 44600 | 0.3958 | | 0.3038 | 0.6355 | 44800 | 0.3957 | | 0.3628 | 0.6383 | 45000 | 0.3953 | | 0.4918 | 0.6411 | 45200 | 0.3954 | | 0.5577 | 0.6440 | 45400 | 0.3953 | | 0.2738 | 0.6468 | 45600 | 0.3952 | | 0.481 | 0.6496 | 45800 | 0.3948 | | 0.4624 | 0.6525 | 46000 | 0.3945 | | 0.4184 | 0.6553 | 46200 | 0.3943 | | 0.5 | 0.6582 | 46400 | 0.3942 | | 0.3874 | 0.6610 | 46600 | 0.3941 | | 0.4107 | 0.6638 | 46800 | 0.3939 | | 0.4462 | 0.6667 | 47000 | 0.3938 | | 0.4787 | 0.6695 | 47200 | 0.3934 | | 0.2831 | 0.6723 | 47400 | 0.3932 | | 0.3612 | 0.6752 | 47600 | 0.3933 | | 0.2958 | 0.6780 | 47800 | 0.3928 | | 0.2881 | 0.6809 | 48000 | 0.3926 | | 0.3764 | 0.6837 | 48200 | 0.3927 | | 0.3935 | 0.6865 | 48400 | 0.3926 | | 0.448 | 0.6894 | 48600 | 0.3923 | | 0.4448 | 0.6922 | 48800 | 0.3918 | | 0.3697 | 0.6950 | 49000 | 0.3918 | | 0.4227 | 0.6979 | 49200 | 0.3917 | | 0.4456 | 0.7007 | 49400 | 0.3914 | | 0.4413 | 0.7035 | 49600 | 0.3913 | | 0.466 | 0.7064 | 49800 | 0.3912 | | 0.2918 | 0.7092 | 50000 | 0.3910 | | 0.3252 | 0.7121 | 50200 | 0.3908 | | 0.198 | 0.7149 | 50400 | 0.3905 | | 0.2525 | 0.7177 | 50600 | 0.3903 | | 0.483 | 0.7206 | 50800 | 0.3901 | | 0.458 | 0.7234 | 51000 | 0.3898 | | 0.4184 | 0.7262 | 51200 | 0.3898 | | 0.385 | 0.7291 | 51400 | 0.3894 | | 0.3237 | 0.7319 | 51600 | 0.3893 | | 0.3709 | 0.7348 | 51800 | 0.3889 | | 0.2904 | 0.7376 | 52000 | 0.3890 | | 0.362 | 0.7404 | 52200 | 0.3888 | | 0.4254 | 0.7433 | 52400 | 0.3885 | | 0.4099 | 0.7461 | 52600 | 0.3884 | | 0.2335 | 0.7489 | 52800 | 0.3881 | | 0.4477 | 0.7518 | 53000 | 0.3880 | | 0.3345 | 0.7546 | 53200 | 0.3878 | | 0.3674 | 0.7574 | 53400 | 0.3873 | | 0.435 | 0.7603 | 53600 | 0.3874 | | 0.4013 | 0.7631 | 53800 | 0.3873 | | 0.3666 | 0.7660 | 54000 | 0.3868 | | 0.3511 | 0.7688 | 54200 | 0.3864 | | 0.4599 | 0.7716 | 54400 | 0.3862 | | 0.4172 | 0.7745 | 54600 | 0.3859 | | 0.3722 | 0.7773 | 54800 | 0.3857 | | 0.459 | 0.7801 | 55000 | 0.3853 | | 0.3358 | 0.7830 | 55200 | 0.3848 | | 0.3544 | 0.7858 | 55400 | 0.3847 | | 0.3254 | 0.7887 | 55600 | 0.3846 | | 0.443 | 0.7915 | 55800 | 0.3845 | | 0.1945 | 0.7943 | 56000 | 0.3844 | | 0.4167 | 0.7972 | 56200 | 0.3842 | | 0.4281 | 0.8 | 56400 | 0.3838 | | 0.4496 | 0.8028 | 56600 | 0.3836 | | 0.4004 | 0.8057 | 56800 | 0.3834 | | 0.4789 | 0.8085 | 57000 | 0.3832 | | 0.37 | 0.8113 | 57200 | 0.3831 | | 0.3972 | 0.8142 | 57400 | 0.3830 | | 0.4429 | 0.8170 | 57600 | 0.3827 | | 0.5432 | 0.8199 | 57800 | 0.3825 | | 0.4448 | 0.8227 | 58000 | 0.3825 | | 0.4668 | 0.8255 | 58200 | 0.3820 | | 0.3144 | 0.8284 | 58400 | 0.3815 | | 0.3173 | 0.8312 | 58600 | 0.3812 | | 0.4206 | 0.8340 | 58800 | 0.3811 | | 0.3072 | 0.8369 | 59000 | 0.3810 | | 0.3854 | 0.8397 | 59200 | 0.3806 | | 0.3892 | 0.8426 | 59400 | 0.3805 | | 0.4497 | 0.8454 | 59600 | 0.3805 | | 0.4165 | 0.8482 | 59800 | 0.3805 | | 0.3679 | 0.8511 | 60000 | 0.3802 | | 0.4221 | 0.8539 | 60200 | 0.3796 | | 0.4912 | 0.8567 | 60400 | 0.3796 | | 0.4141 | 0.8596 | 60600 | 0.3794 | | 0.3999 | 0.8624 | 60800 | 0.3792 | | 0.3014 | 0.8652 | 61000 | 0.3788 | | 0.5035 | 0.8681 | 61200 | 0.3787 | | 0.4158 | 0.8709 | 61400 | 0.3784 | | 0.3597 | 0.8738 | 61600 | 0.3783 | | 0.4084 | 0.8766 | 61800 | 0.3782 | | 0.3475 | 0.8794 | 62000 | 0.3782 | | 0.3177 | 0.8823 | 62200 | 0.3781 | | 0.3705 | 0.8851 | 62400 | 0.3778 | | 0.4659 | 0.8879 | 62600 | 0.3776 | | 0.4417 | 0.8908 | 62800 | 0.3774 | | 0.435 | 0.8936 | 63000 | 0.3772 | | 0.4289 | 0.8965 | 63200 | 0.3772 | | 0.3551 | 0.8993 | 63400 | 0.3770 | | 0.4331 | 0.9021 | 63600 | 0.3770 | | 0.3531 | 0.9050 | 63800 | 0.3768 | | 0.4663 | 0.9078 | 64000 | 0.3767 | | 0.4011 | 0.9106 | 64200 | 0.3765 | | 0.344 | 0.9135 | 64400 | 0.3763 | | 0.3488 | 0.9163 | 64600 | 0.3762 | | 0.2881 | 0.9191 | 64800 | 0.3761 | | 0.4809 | 0.9220 | 65000 | 0.3760 | | 0.4229 | 0.9248 | 65200 | 0.3759 | | 0.4683 | 0.9277 | 65400 | 0.3757 | | 0.483 | 0.9305 | 65600 | 0.3756 | | 0.4342 | 0.9333 | 65800 | 0.3755 | | 0.2609 | 0.9362 | 66000 | 0.3754 | | 0.4405 | 0.9390 | 66200 | 0.3754 | | 0.4036 | 0.9418 | 66400 | 0.3754 | | 0.3688 | 0.9447 | 66600 | 0.3753 | | 0.3391 | 0.9475 | 66800 | 0.3752 | | 0.466 | 0.9504 | 67000 | 0.3751 | | 0.4023 | 0.9532 | 67200 | 0.3751 | | 0.4671 | 0.9560 | 67400 | 0.3750 | | 0.2545 | 0.9589 | 67600 | 0.3750 | | 0.2524 | 0.9617 | 67800 | 0.3749 | | 0.3833 | 0.9645 | 68000 | 0.3749 | | 0.4234 | 0.9674 | 68200 | 0.3749 | | 0.4267 | 0.9702 | 68400 | 0.3748 | | 0.3799 | 0.9730 | 68600 | 0.3747 | | 0.2952 | 0.9759 | 68800 | 0.3747 | | 0.2221 | 0.9787 | 69000 | 0.3746 | | 0.4635 | 0.9816 | 69200 | 0.3746 | | 0.2814 | 0.9844 | 69400 | 0.3745 | | 0.3765 | 0.9872 | 69600 | 0.3745 | | 0.4394 | 0.9901 | 69800 | 0.3745 | | 0.4303 | 0.9929 | 70000 | 0.3744 | | 0.2866 | 0.9957 | 70200 | 0.3744 | | 0.4629 | 0.9986 | 70400 | 0.3744 | ### Framework versions - PEFT 0.12.0 - Transformers 4.45.2 - Pytorch 2.4.0+cu121 - Datasets 3.0.0 - Tokenizers 0.20.1