--- license: apache-2.0 library_name: peft tags: - generated_from_trainer base_model: mistralai/Mixtral-8x7B-Instruct-v0.1 model-index: - name: Mixtral-8x7B-Instruct-v0.1 results: [] --- # Mixtral-8x7B-Instruct-v0.1 This model is a fine-tuned version of [mistralai/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.3898 ## 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: 5e-05 - train_batch_size: 1 - eval_batch_size: 1 - 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 | |:-------------:|:-----:|:----:|:---------------:| | 1.8837 | 0.01 | 5 | 1.7824 | | 1.8578 | 0.02 | 10 | 1.7336 | | 1.6828 | 0.02 | 15 | 1.6999 | | 1.8063 | 0.03 | 20 | 1.6716 | | 1.6728 | 0.04 | 25 | 1.6400 | | 1.5326 | 0.05 | 30 | 1.6079 | | 1.5742 | 0.05 | 35 | 1.5795 | | 1.6315 | 0.06 | 40 | 1.5597 | | 1.6111 | 0.07 | 45 | 1.5449 | | 1.5815 | 0.08 | 50 | 1.5359 | | 1.4937 | 0.09 | 55 | 1.5234 | | 1.4524 | 0.09 | 60 | 1.5177 | | 1.4922 | 0.1 | 65 | 1.5150 | | 1.5636 | 0.11 | 70 | 1.5058 | | 1.5303 | 0.12 | 75 | 1.5020 | | 1.4182 | 0.12 | 80 | 1.5003 | | 1.4375 | 0.13 | 85 | 1.4919 | | 1.4287 | 0.14 | 90 | 1.4873 | | 1.5023 | 0.15 | 95 | 1.4859 | | 1.5331 | 0.16 | 100 | 1.4800 | | 1.4797 | 0.16 | 105 | 1.4784 | | 1.476 | 0.17 | 110 | 1.4741 | | 1.5398 | 0.18 | 115 | 1.4702 | | 1.4086 | 0.19 | 120 | 1.4670 | | 1.4222 | 0.19 | 125 | 1.4648 | | 1.4033 | 0.2 | 130 | 1.4623 | | 1.5386 | 0.21 | 135 | 1.4608 | | 1.4959 | 0.22 | 140 | 1.4583 | | 1.4908 | 0.22 | 145 | 1.4542 | | 1.4669 | 0.23 | 150 | 1.4510 | | 1.4733 | 0.24 | 155 | 1.4477 | | 1.5692 | 0.25 | 160 | 1.4458 | | 1.484 | 0.26 | 165 | 1.4468 | | 1.4186 | 0.26 | 170 | 1.4432 | | 1.3907 | 0.27 | 175 | 1.4391 | | 1.4489 | 0.28 | 180 | 1.4392 | | 1.471 | 0.29 | 185 | 1.4364 | | 1.31 | 0.29 | 190 | 1.4344 | | 1.3949 | 0.3 | 195 | 1.4324 | | 1.4094 | 0.31 | 200 | 1.4306 | | 1.4235 | 0.32 | 205 | 1.4275 | | 1.5056 | 0.33 | 210 | 1.4271 | | 1.4281 | 0.33 | 215 | 1.4251 | | 1.4329 | 0.34 | 220 | 1.4236 | | 1.3791 | 0.35 | 225 | 1.4221 | | 1.4189 | 0.36 | 230 | 1.4207 | | 1.4192 | 0.36 | 235 | 1.4198 | | 1.3807 | 0.37 | 240 | 1.4187 | | 1.4362 | 0.38 | 245 | 1.4177 | | 1.419 | 0.39 | 250 | 1.4174 | | 1.5039 | 0.4 | 255 | 1.4176 | | 1.4323 | 0.4 | 260 | 1.4160 | | 1.5249 | 0.41 | 265 | 1.4154 | | 1.4462 | 0.42 | 270 | 1.4144 | | 1.2841 | 0.43 | 275 | 1.4137 | | 1.3764 | 0.43 | 280 | 1.4137 | | 1.3063 | 0.44 | 285 | 1.4123 | | 1.4296 | 0.45 | 290 | 1.4122 | | 1.4333 | 0.46 | 295 | 1.4110 | | 1.3113 | 0.47 | 300 | 1.4103 | | 1.3138 | 0.47 | 305 | 1.4103 | | 1.3951 | 0.48 | 310 | 1.4104 | | 1.3592 | 0.49 | 315 | 1.4099 | | 1.458 | 0.5 | 320 | 1.4094 | | 1.4037 | 0.5 | 325 | 1.4094 | | 1.4431 | 0.51 | 330 | 1.4086 | | 1.3595 | 0.52 | 335 | 1.4076 | | 1.3198 | 0.53 | 340 | 1.4061 | | 1.3967 | 0.53 | 345 | 1.4054 | | 1.254 | 0.54 | 350 | 1.4049 | | 1.3324 | 0.55 | 355 | 1.4047 | | 1.2428 | 0.56 | 360 | 1.4037 | | 1.3976 | 0.57 | 365 | 1.4033 | | 1.4226 | 0.57 | 370 | 1.4036 | | 1.3678 | 0.58 | 375 | 1.4038 | | 1.4634 | 0.59 | 380 | 1.4028 | | 1.4325 | 0.6 | 385 | 1.4018 | | 1.3175 | 0.6 | 390 | 1.4013 | | 1.3263 | 0.61 | 395 | 1.4007 | | 1.3653 | 0.62 | 400 | 1.4019 | | 1.3804 | 0.63 | 405 | 1.4009 | | 1.3686 | 0.64 | 410 | 1.4003 | | 1.3975 | 0.64 | 415 | 1.4003 | | 1.3289 | 0.65 | 420 | 1.4000 | | 1.3336 | 0.66 | 425 | 1.3991 | | 1.3958 | 0.67 | 430 | 1.3979 | | 1.2227 | 0.67 | 435 | 1.3972 | | 1.3202 | 0.68 | 440 | 1.3967 | | 1.3508 | 0.69 | 445 | 1.3963 | | 1.4077 | 0.7 | 450 | 1.3956 | | 1.4148 | 0.71 | 455 | 1.3952 | | 1.4219 | 0.71 | 460 | 1.3948 | | 1.3802 | 0.72 | 465 | 1.3949 | | 1.301 | 0.73 | 470 | 1.3945 | | 1.2894 | 0.74 | 475 | 1.3938 | | 1.3469 | 0.74 | 480 | 1.3940 | | 1.2852 | 0.75 | 485 | 1.3941 | | 1.4896 | 0.76 | 490 | 1.3933 | | 1.3953 | 0.77 | 495 | 1.3929 | | 1.3624 | 0.78 | 500 | 1.3926 | | 1.4719 | 0.78 | 505 | 1.3927 | | 1.3274 | 0.79 | 510 | 1.3920 | | 1.2106 | 0.8 | 515 | 1.3917 | | 1.3851 | 0.81 | 520 | 1.3918 | | 1.344 | 0.81 | 525 | 1.3916 | | 1.3197 | 0.82 | 530 | 1.3917 | | 1.3426 | 0.83 | 535 | 1.3922 | | 1.266 | 0.84 | 540 | 1.3919 | | 1.392 | 0.84 | 545 | 1.3918 | | 1.325 | 0.85 | 550 | 1.3918 | | 1.4706 | 0.86 | 555 | 1.3915 | | 1.3695 | 0.87 | 560 | 1.3910 | | 1.4036 | 0.88 | 565 | 1.3912 | | 1.3042 | 0.88 | 570 | 1.3912 | | 1.2578 | 0.89 | 575 | 1.3912 | | 1.3579 | 0.9 | 580 | 1.3915 | | 1.3324 | 0.91 | 585 | 1.3913 | | 1.5166 | 0.91 | 590 | 1.3911 | | 1.3563 | 0.92 | 595 | 1.3907 | | 1.4271 | 0.93 | 600 | 1.3901 | | 1.4084 | 0.94 | 605 | 1.3899 | | 1.3975 | 0.95 | 610 | 1.3897 | | 1.3887 | 0.95 | 615 | 1.3896 | | 1.4221 | 0.96 | 620 | 1.3898 | | 1.4031 | 0.97 | 625 | 1.3898 | | 1.3114 | 0.98 | 630 | 1.3897 | | 1.4907 | 0.98 | 635 | 1.3896 | | 1.3519 | 0.99 | 640 | 1.3898 | | 1.3648 | 1.0 | 645 | 1.3898 | ### Framework versions - PEFT 0.7.1 - Transformers 4.36.2 - Pytorch 2.1.0+cu118 - Datasets 2.16.1 - Tokenizers 0.15.0