Commit
•
b49a884
1
Parent(s):
cb6f416
End of training
Browse files- README.md +319 -0
- adapter_config.json +26 -0
- adapter_model.safetensors +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +42 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,319 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- sft
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: TheBloke/Mistral-7B-v0.1-GPTQ
|
| 9 |
+
model-index:
|
| 10 |
+
- name: mistral-rand-300k
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# mistral-rand-300k
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [TheBloke/Mistral-7B-v0.1-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-v0.1-GPTQ) on the None dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.3537
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 2e-05
|
| 41 |
+
- train_batch_size: 16
|
| 42 |
+
- eval_batch_size: 64
|
| 43 |
+
- seed: 42
|
| 44 |
+
- gradient_accumulation_steps: 2
|
| 45 |
+
- total_train_batch_size: 32
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: cosine
|
| 48 |
+
- training_steps: 250
|
| 49 |
+
- mixed_precision_training: Native AMP
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 55 |
+
| 1.6373 | 0.01 | 50 | 0.8699 |
|
| 56 |
+
| 0.7891 | 0.02 | 100 | 0.7454 |
|
| 57 |
+
| 0.7135 | 0.02 | 150 | 0.6984 |
|
| 58 |
+
| 0.6931 | 0.03 | 200 | 0.6722 |
|
| 59 |
+
| 0.6592 | 0.08 | 250 | 0.6407 |
|
| 60 |
+
| 0.634 | 0.1 | 300 | 0.6212 |
|
| 61 |
+
| 0.61 | 0.11 | 350 | 0.6015 |
|
| 62 |
+
| 0.5961 | 0.13 | 400 | 0.5892 |
|
| 63 |
+
| 0.5795 | 0.14 | 450 | 0.5773 |
|
| 64 |
+
| 0.5765 | 0.16 | 500 | 0.5683 |
|
| 65 |
+
| 0.5619 | 0.18 | 550 | 0.5612 |
|
| 66 |
+
| 0.5558 | 0.19 | 600 | 0.5519 |
|
| 67 |
+
| 0.5572 | 0.21 | 650 | 0.5438 |
|
| 68 |
+
| 0.5467 | 0.22 | 700 | 0.5348 |
|
| 69 |
+
| 0.5303 | 0.24 | 750 | 0.5248 |
|
| 70 |
+
| 0.5307 | 0.26 | 800 | 0.5135 |
|
| 71 |
+
| 0.508 | 0.27 | 850 | 0.5036 |
|
| 72 |
+
| 0.5087 | 0.29 | 900 | 0.5009 |
|
| 73 |
+
| 0.5073 | 0.3 | 950 | 0.4945 |
|
| 74 |
+
| 0.5078 | 0.32 | 1000 | 0.4916 |
|
| 75 |
+
| 0.5089 | 0.34 | 1050 | 0.4893 |
|
| 76 |
+
| 0.4829 | 0.35 | 1100 | 0.4862 |
|
| 77 |
+
| 0.4872 | 0.37 | 1150 | 0.4832 |
|
| 78 |
+
| 0.4845 | 0.39 | 1200 | 0.4803 |
|
| 79 |
+
| 0.4993 | 0.4 | 1250 | 0.4774 |
|
| 80 |
+
| 0.475 | 0.42 | 1300 | 0.4746 |
|
| 81 |
+
| 0.4836 | 0.43 | 1350 | 0.4735 |
|
| 82 |
+
| 0.4748 | 0.45 | 1400 | 0.4708 |
|
| 83 |
+
| 0.4809 | 0.47 | 1450 | 0.4693 |
|
| 84 |
+
| 0.4755 | 0.48 | 1500 | 0.4668 |
|
| 85 |
+
| 0.4679 | 0.5 | 1550 | 0.4644 |
|
| 86 |
+
| 0.4685 | 0.51 | 1600 | 0.4622 |
|
| 87 |
+
| 0.4706 | 0.53 | 1650 | 0.4611 |
|
| 88 |
+
| 0.4673 | 0.55 | 1700 | 0.4605 |
|
| 89 |
+
| 0.4539 | 0.56 | 1750 | 0.4577 |
|
| 90 |
+
| 0.4501 | 0.58 | 1800 | 0.4560 |
|
| 91 |
+
| 0.4638 | 0.59 | 1850 | 0.4542 |
|
| 92 |
+
| 0.4663 | 0.61 | 1900 | 0.4521 |
|
| 93 |
+
| 0.4638 | 0.63 | 1950 | 0.4509 |
|
| 94 |
+
| 0.4562 | 0.64 | 2000 | 0.4501 |
|
| 95 |
+
| 0.4535 | 0.66 | 2050 | 0.4496 |
|
| 96 |
+
| 0.4548 | 0.67 | 2100 | 0.4470 |
|
| 97 |
+
| 0.442 | 0.69 | 2150 | 0.4453 |
|
| 98 |
+
| 0.4543 | 0.71 | 2200 | 0.4449 |
|
| 99 |
+
| 0.4435 | 0.72 | 2250 | 0.4428 |
|
| 100 |
+
| 0.4633 | 0.74 | 2300 | 0.4418 |
|
| 101 |
+
| 0.4438 | 0.75 | 2350 | 0.4416 |
|
| 102 |
+
| 0.4443 | 0.77 | 2400 | 0.4392 |
|
| 103 |
+
| 0.4424 | 0.79 | 2450 | 0.4386 |
|
| 104 |
+
| 0.4341 | 0.8 | 2500 | 0.4367 |
|
| 105 |
+
| 0.4329 | 0.82 | 2550 | 0.4353 |
|
| 106 |
+
| 0.4356 | 0.83 | 2600 | 0.4349 |
|
| 107 |
+
| 0.4384 | 0.85 | 2650 | 0.4351 |
|
| 108 |
+
| 0.4327 | 0.87 | 2700 | 0.4321 |
|
| 109 |
+
| 0.4356 | 0.88 | 2750 | 0.4323 |
|
| 110 |
+
| 0.4428 | 0.9 | 2800 | 0.4310 |
|
| 111 |
+
| 0.4358 | 0.91 | 2850 | 0.4304 |
|
| 112 |
+
| 0.4322 | 0.93 | 2900 | 0.4293 |
|
| 113 |
+
| 0.4336 | 0.95 | 2950 | 0.4280 |
|
| 114 |
+
| 0.4296 | 0.96 | 3000 | 0.4269 |
|
| 115 |
+
| 0.4365 | 0.98 | 3050 | 0.4267 |
|
| 116 |
+
| 0.4313 | 0.99 | 3100 | 0.4250 |
|
| 117 |
+
| 0.4256 | 1.01 | 3150 | 0.4251 |
|
| 118 |
+
| 0.4258 | 1.03 | 3200 | 0.4241 |
|
| 119 |
+
| 0.4245 | 1.04 | 3250 | 0.4225 |
|
| 120 |
+
| 0.4161 | 1.06 | 3300 | 0.4223 |
|
| 121 |
+
| 0.4228 | 1.07 | 3350 | 0.4215 |
|
| 122 |
+
| 0.4194 | 1.09 | 3400 | 0.4205 |
|
| 123 |
+
| 0.4331 | 1.11 | 3450 | 0.4193 |
|
| 124 |
+
| 0.4246 | 1.12 | 3500 | 0.4191 |
|
| 125 |
+
| 0.4246 | 1.14 | 3550 | 0.4173 |
|
| 126 |
+
| 0.4229 | 1.16 | 3600 | 0.4175 |
|
| 127 |
+
| 0.4128 | 1.17 | 3650 | 0.4160 |
|
| 128 |
+
| 0.4189 | 1.19 | 3700 | 0.4156 |
|
| 129 |
+
| 0.4154 | 1.2 | 3750 | 0.4148 |
|
| 130 |
+
| 0.4263 | 1.22 | 3800 | 0.4140 |
|
| 131 |
+
| 0.4124 | 1.24 | 3850 | 0.4139 |
|
| 132 |
+
| 0.4201 | 1.25 | 3900 | 0.4132 |
|
| 133 |
+
| 0.4224 | 1.27 | 3950 | 0.4122 |
|
| 134 |
+
| 0.4114 | 1.28 | 4000 | 0.4122 |
|
| 135 |
+
| 0.4169 | 1.3 | 4050 | 0.4112 |
|
| 136 |
+
| 0.4167 | 1.32 | 4100 | 0.4107 |
|
| 137 |
+
| 0.4019 | 1.33 | 4150 | 0.4095 |
|
| 138 |
+
| 0.4142 | 1.35 | 4200 | 0.4087 |
|
| 139 |
+
| 0.4086 | 1.36 | 4250 | 0.4080 |
|
| 140 |
+
| 0.406 | 1.38 | 4300 | 0.4075 |
|
| 141 |
+
| 0.4091 | 1.4 | 4350 | 0.4069 |
|
| 142 |
+
| 0.4149 | 1.41 | 4400 | 0.4062 |
|
| 143 |
+
| 0.4078 | 1.43 | 4450 | 0.4054 |
|
| 144 |
+
| 0.3997 | 1.44 | 4500 | 0.4052 |
|
| 145 |
+
| 0.3985 | 1.46 | 4550 | 0.4040 |
|
| 146 |
+
| 0.4035 | 1.48 | 4600 | 0.4035 |
|
| 147 |
+
| 0.3982 | 1.49 | 4650 | 0.4025 |
|
| 148 |
+
| 0.4018 | 1.51 | 4700 | 0.4030 |
|
| 149 |
+
| 0.4078 | 1.52 | 4750 | 0.4021 |
|
| 150 |
+
| 0.3991 | 1.54 | 4800 | 0.4010 |
|
| 151 |
+
| 0.4033 | 1.56 | 4850 | 0.4003 |
|
| 152 |
+
| 0.3964 | 1.57 | 4900 | 0.4005 |
|
| 153 |
+
| 0.3965 | 1.59 | 4950 | 0.3993 |
|
| 154 |
+
| 0.407 | 1.6 | 5000 | 0.3994 |
|
| 155 |
+
| 0.4036 | 1.62 | 5050 | 0.3983 |
|
| 156 |
+
| 0.4063 | 1.64 | 5100 | 0.3980 |
|
| 157 |
+
| 0.3857 | 1.65 | 5150 | 0.3973 |
|
| 158 |
+
| 0.3949 | 1.67 | 5200 | 0.3973 |
|
| 159 |
+
| 0.3872 | 1.68 | 5250 | 0.3965 |
|
| 160 |
+
| 0.393 | 1.7 | 5300 | 0.3959 |
|
| 161 |
+
| 0.3891 | 1.72 | 5350 | 0.3955 |
|
| 162 |
+
| 0.3903 | 1.73 | 5400 | 0.3950 |
|
| 163 |
+
| 0.3941 | 1.75 | 5450 | 0.3947 |
|
| 164 |
+
| 0.3879 | 1.76 | 5500 | 0.3941 |
|
| 165 |
+
| 0.4016 | 1.78 | 5550 | 0.3937 |
|
| 166 |
+
| 0.3936 | 1.8 | 5600 | 0.3929 |
|
| 167 |
+
| 0.4005 | 1.81 | 5650 | 0.3932 |
|
| 168 |
+
| 0.3939 | 1.83 | 5700 | 0.3923 |
|
| 169 |
+
| 0.4032 | 1.85 | 5750 | 0.3921 |
|
| 170 |
+
| 0.3921 | 1.86 | 5800 | 0.3921 |
|
| 171 |
+
| 0.3903 | 1.88 | 5850 | 0.3905 |
|
| 172 |
+
| 0.3983 | 1.89 | 5900 | 0.3910 |
|
| 173 |
+
| 0.3806 | 1.91 | 5950 | 0.3897 |
|
| 174 |
+
| 0.3964 | 1.93 | 6000 | 0.3906 |
|
| 175 |
+
| 0.3866 | 1.94 | 6050 | 0.3890 |
|
| 176 |
+
| 0.3882 | 1.96 | 6100 | 0.3888 |
|
| 177 |
+
| 0.3835 | 1.97 | 6150 | 0.3885 |
|
| 178 |
+
| 0.3921 | 1.99 | 6200 | 0.3875 |
|
| 179 |
+
| 0.388 | 2.01 | 6250 | 0.3878 |
|
| 180 |
+
| 0.3829 | 2.02 | 6300 | 0.3872 |
|
| 181 |
+
| 0.3814 | 2.04 | 6350 | 0.3867 |
|
| 182 |
+
| 0.3818 | 2.05 | 6400 | 0.3862 |
|
| 183 |
+
| 0.3802 | 2.07 | 6450 | 0.3860 |
|
| 184 |
+
| 0.3739 | 2.09 | 6500 | 0.3853 |
|
| 185 |
+
| 0.3771 | 2.1 | 6550 | 0.3852 |
|
| 186 |
+
| 0.3732 | 2.12 | 6600 | 0.3846 |
|
| 187 |
+
| 0.385 | 2.13 | 6650 | 0.3849 |
|
| 188 |
+
| 0.3767 | 2.15 | 6700 | 0.3833 |
|
| 189 |
+
| 0.3802 | 2.17 | 6750 | 0.3836 |
|
| 190 |
+
| 0.3844 | 2.18 | 6800 | 0.3828 |
|
| 191 |
+
| 0.3761 | 2.2 | 6850 | 0.3826 |
|
| 192 |
+
| 0.3765 | 2.21 | 6900 | 0.3826 |
|
| 193 |
+
| 0.3787 | 2.23 | 6950 | 0.3825 |
|
| 194 |
+
| 0.378 | 2.25 | 7000 | 0.3815 |
|
| 195 |
+
| 0.3792 | 2.26 | 7050 | 0.3815 |
|
| 196 |
+
| 0.3908 | 2.28 | 7100 | 0.3811 |
|
| 197 |
+
| 0.3757 | 2.29 | 7150 | 0.3810 |
|
| 198 |
+
| 0.376 | 2.31 | 7200 | 0.3804 |
|
| 199 |
+
| 0.3785 | 2.33 | 7250 | 0.3805 |
|
| 200 |
+
| 0.3744 | 2.34 | 7300 | 0.3797 |
|
| 201 |
+
| 0.3984 | 2.36 | 7350 | 0.3791 |
|
| 202 |
+
| 0.3833 | 2.37 | 7400 | 0.3792 |
|
| 203 |
+
| 0.3808 | 2.39 | 7450 | 0.3785 |
|
| 204 |
+
| 0.3803 | 2.41 | 7500 | 0.3786 |
|
| 205 |
+
| 0.3828 | 2.42 | 7550 | 0.3778 |
|
| 206 |
+
| 0.3697 | 2.44 | 7600 | 0.3780 |
|
| 207 |
+
| 0.3692 | 2.45 | 7650 | 0.3763 |
|
| 208 |
+
| 0.3808 | 2.47 | 7700 | 0.3769 |
|
| 209 |
+
| 0.3764 | 2.49 | 7750 | 0.3763 |
|
| 210 |
+
| 0.3865 | 2.5 | 7800 | 0.3763 |
|
| 211 |
+
| 0.375 | 2.52 | 7850 | 0.3760 |
|
| 212 |
+
| 0.368 | 2.53 | 7900 | 0.3755 |
|
| 213 |
+
| 0.3632 | 2.55 | 7950 | 0.3757 |
|
| 214 |
+
| 0.3792 | 2.57 | 8000 | 0.3758 |
|
| 215 |
+
| 0.374 | 2.58 | 8050 | 0.3748 |
|
| 216 |
+
| 0.3689 | 2.6 | 8100 | 0.3741 |
|
| 217 |
+
| 0.3843 | 2.62 | 8150 | 0.3741 |
|
| 218 |
+
| 0.3669 | 2.63 | 8200 | 0.3739 |
|
| 219 |
+
| 0.368 | 2.65 | 8250 | 0.3732 |
|
| 220 |
+
| 0.3726 | 2.66 | 8300 | 0.3734 |
|
| 221 |
+
| 0.3653 | 2.68 | 8350 | 0.3728 |
|
| 222 |
+
| 0.3777 | 2.7 | 8400 | 0.3732 |
|
| 223 |
+
| 0.3625 | 2.71 | 8450 | 0.3724 |
|
| 224 |
+
| 0.3749 | 2.73 | 8500 | 0.3716 |
|
| 225 |
+
| 0.3708 | 2.74 | 8550 | 0.3725 |
|
| 226 |
+
| 0.3618 | 2.76 | 8600 | 0.3711 |
|
| 227 |
+
| 0.3659 | 2.78 | 8650 | 0.3714 |
|
| 228 |
+
| 0.3661 | 2.79 | 8700 | 0.3711 |
|
| 229 |
+
| 0.3771 | 2.81 | 8750 | 0.3714 |
|
| 230 |
+
| 0.3637 | 2.82 | 8800 | 0.3704 |
|
| 231 |
+
| 0.3768 | 2.84 | 8850 | 0.3700 |
|
| 232 |
+
| 0.3722 | 2.86 | 8900 | 0.3701 |
|
| 233 |
+
| 0.366 | 2.87 | 8950 | 0.3693 |
|
| 234 |
+
| 0.3716 | 2.89 | 9000 | 0.3690 |
|
| 235 |
+
| 0.3622 | 2.9 | 9050 | 0.3688 |
|
| 236 |
+
| 0.3594 | 2.92 | 9100 | 0.3682 |
|
| 237 |
+
| 0.368 | 2.94 | 9150 | 0.3680 |
|
| 238 |
+
| 0.3538 | 2.95 | 9200 | 0.3678 |
|
| 239 |
+
| 0.3578 | 2.97 | 9250 | 0.3676 |
|
| 240 |
+
| 0.3685 | 2.98 | 9300 | 0.3679 |
|
| 241 |
+
| 0.3631 | 3.0 | 9350 | 0.3674 |
|
| 242 |
+
| 0.3645 | 3.02 | 9400 | 0.3665 |
|
| 243 |
+
| 0.3654 | 3.03 | 9450 | 0.3671 |
|
| 244 |
+
| 0.3502 | 3.05 | 9500 | 0.3662 |
|
| 245 |
+
| 0.356 | 3.06 | 9550 | 0.3665 |
|
| 246 |
+
| 0.3642 | 3.08 | 9600 | 0.3662 |
|
| 247 |
+
| 0.3688 | 3.1 | 9650 | 0.3659 |
|
| 248 |
+
| 0.3514 | 3.11 | 9700 | 0.3655 |
|
| 249 |
+
| 0.3463 | 3.13 | 9750 | 0.3656 |
|
| 250 |
+
| 0.3517 | 3.14 | 9800 | 0.3651 |
|
| 251 |
+
| 0.3666 | 3.16 | 9850 | 0.3650 |
|
| 252 |
+
| 0.3617 | 3.18 | 9900 | 0.3660 |
|
| 253 |
+
| 0.3452 | 3.19 | 9950 | 0.3649 |
|
| 254 |
+
| 0.3591 | 3.21 | 10000 | 0.3647 |
|
| 255 |
+
| 0.3509 | 3.22 | 10050 | 0.3643 |
|
| 256 |
+
| 0.3618 | 3.24 | 10100 | 0.3641 |
|
| 257 |
+
| 0.3571 | 3.26 | 10150 | 0.3640 |
|
| 258 |
+
| 0.3587 | 3.27 | 10200 | 0.3633 |
|
| 259 |
+
| 0.3664 | 3.29 | 10250 | 0.3637 |
|
| 260 |
+
| 0.3502 | 3.3 | 10300 | 0.3633 |
|
| 261 |
+
| 0.373 | 3.32 | 10350 | 0.3626 |
|
| 262 |
+
| 0.3623 | 3.34 | 10400 | 0.3622 |
|
| 263 |
+
| 0.3554 | 3.35 | 10450 | 0.3624 |
|
| 264 |
+
| 0.3511 | 3.37 | 10500 | 0.3622 |
|
| 265 |
+
| 0.3534 | 3.39 | 10550 | 0.3626 |
|
| 266 |
+
| 0.3473 | 3.4 | 10600 | 0.3620 |
|
| 267 |
+
| 0.3563 | 3.42 | 10650 | 0.3618 |
|
| 268 |
+
| 0.3612 | 3.43 | 10700 | 0.3614 |
|
| 269 |
+
| 0.3587 | 3.45 | 10750 | 0.3610 |
|
| 270 |
+
| 0.3521 | 3.47 | 10800 | 0.3609 |
|
| 271 |
+
| 0.3443 | 3.48 | 10850 | 0.3610 |
|
| 272 |
+
| 0.3615 | 3.5 | 10900 | 0.3608 |
|
| 273 |
+
| 0.3589 | 3.51 | 10950 | 0.3609 |
|
| 274 |
+
| 0.364 | 3.53 | 11000 | 0.3598 |
|
| 275 |
+
| 0.3498 | 3.55 | 11050 | 0.3600 |
|
| 276 |
+
| 0.3541 | 3.56 | 11100 | 0.3597 |
|
| 277 |
+
| 0.3555 | 3.58 | 11150 | 0.3594 |
|
| 278 |
+
| 0.3491 | 3.59 | 11200 | 0.3596 |
|
| 279 |
+
| 0.3498 | 3.61 | 11250 | 0.3589 |
|
| 280 |
+
| 0.3484 | 3.63 | 11300 | 0.3590 |
|
| 281 |
+
| 0.3483 | 3.64 | 11350 | 0.3586 |
|
| 282 |
+
| 0.3533 | 3.66 | 11400 | 0.3580 |
|
| 283 |
+
| 0.3479 | 3.67 | 11450 | 0.3589 |
|
| 284 |
+
| 0.3539 | 3.69 | 11500 | 0.3580 |
|
| 285 |
+
| 0.3507 | 3.71 | 11550 | 0.3582 |
|
| 286 |
+
| 0.3534 | 3.72 | 11600 | 0.3579 |
|
| 287 |
+
| 0.3559 | 3.74 | 11650 | 0.3575 |
|
| 288 |
+
| 0.3477 | 3.75 | 11700 | 0.3577 |
|
| 289 |
+
| 0.3501 | 3.77 | 11750 | 0.3574 |
|
| 290 |
+
| 0.3491 | 3.79 | 11800 | 0.3569 |
|
| 291 |
+
| 0.3661 | 3.8 | 11850 | 0.3569 |
|
| 292 |
+
| 0.3455 | 3.82 | 11900 | 0.3568 |
|
| 293 |
+
| 0.3522 | 3.83 | 11950 | 0.3564 |
|
| 294 |
+
| 0.3532 | 3.85 | 12000 | 0.3562 |
|
| 295 |
+
| 0.3513 | 3.87 | 12050 | 0.3559 |
|
| 296 |
+
| 0.3527 | 3.88 | 12100 | 0.3561 |
|
| 297 |
+
| 0.3575 | 3.9 | 12150 | 0.3556 |
|
| 298 |
+
| 0.3403 | 3.92 | 12200 | 0.3550 |
|
| 299 |
+
| 0.3495 | 3.93 | 12250 | 0.3554 |
|
| 300 |
+
| 0.3514 | 3.95 | 12300 | 0.3548 |
|
| 301 |
+
| 0.3556 | 3.96 | 12350 | 0.3547 |
|
| 302 |
+
| 0.3549 | 3.98 | 12400 | 0.3545 |
|
| 303 |
+
| 0.3541 | 4.0 | 12450 | 0.3542 |
|
| 304 |
+
| 0.3477 | 4.01 | 12500 | 0.3551 |
|
| 305 |
+
| 0.3449 | 4.03 | 12550 | 0.3542 |
|
| 306 |
+
| 0.3426 | 4.04 | 12600 | 0.3552 |
|
| 307 |
+
| 0.3411 | 4.06 | 12650 | 0.3545 |
|
| 308 |
+
| 0.3476 | 4.08 | 12700 | 0.3540 |
|
| 309 |
+
| 0.3547 | 4.09 | 12750 | 0.3536 |
|
| 310 |
+
| 0.3529 | 4.11 | 12800 | 0.3537 |
|
| 311 |
+
|
| 312 |
+
|
| 313 |
+
### Framework versions
|
| 314 |
+
|
| 315 |
+
- PEFT 0.7.1
|
| 316 |
+
- Transformers 4.36.2
|
| 317 |
+
- Pytorch 2.1.2+cu121
|
| 318 |
+
- Datasets 2.16.1
|
| 319 |
+
- Tokenizers 0.15.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "TheBloke/Mistral-7B-v0.1-GPTQ",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"loftq_config": {},
|
| 12 |
+
"lora_alpha": 64,
|
| 13 |
+
"lora_dropout": 0.1,
|
| 14 |
+
"megatron_config": null,
|
| 15 |
+
"megatron_core": "megatron.core",
|
| 16 |
+
"modules_to_save": null,
|
| 17 |
+
"peft_type": "LORA",
|
| 18 |
+
"r": 64,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
+
"revision": null,
|
| 21 |
+
"target_modules": [
|
| 22 |
+
"q_proj",
|
| 23 |
+
"v_proj"
|
| 24 |
+
],
|
| 25 |
+
"task_type": "CAUSAL_LM"
|
| 26 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf34bab6568ddda35b33eab99ededacf76455e13fce7305458a39b61716f837d
|
| 3 |
+
size 109069176
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": true,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": true,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"additional_special_tokens": [],
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"clean_up_tokenization_spaces": false,
|
| 33 |
+
"eos_token": "</s>",
|
| 34 |
+
"legacy": true,
|
| 35 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 36 |
+
"pad_token": "</s>",
|
| 37 |
+
"sp_model_kwargs": {},
|
| 38 |
+
"spaces_between_special_tokens": false,
|
| 39 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 40 |
+
"unk_token": "<unk>",
|
| 41 |
+
"use_default_system_prompt": true
|
| 42 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94d4040ebbe971787fcd9a56c98db182dc69dfee6b72d61df454ddebedf3b2f5
|
| 3 |
+
size 4664
|