cem13/complaint_to_sythoms_mix_8x7b
Browse files- README.md +235 -0
- adapter_config.json +35 -0
- adapter_model.safetensors +3 -0
- runs/Aug12_07-24-44_9bcd5dae9cf3/events.out.tfevents.1723447489.9bcd5dae9cf3.1307.0 +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +43 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,235 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: mistralai/Mixtral-8x7B-v0.1
|
| 3 |
+
datasets:
|
| 4 |
+
- generator
|
| 5 |
+
library_name: peft
|
| 6 |
+
license: apache-2.0
|
| 7 |
+
tags:
|
| 8 |
+
- trl
|
| 9 |
+
- sft
|
| 10 |
+
- generated_from_trainer
|
| 11 |
+
model-index:
|
| 12 |
+
- name: Mixtral_Alpace_v2
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# Mixtral_Alpace_v2
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [mistralai/Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) on the generator dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.5881
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 2.5e-05
|
| 43 |
+
- train_batch_size: 8
|
| 44 |
+
- eval_batch_size: 8
|
| 45 |
+
- seed: 42
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- lr_scheduler_warmup_steps: 15
|
| 49 |
+
- num_epochs: 15
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
+
|:-------------:|:-------:|:----:|:---------------:|
|
| 55 |
+
| 1.5291 | 0.0870 | 10 | 1.6326 |
|
| 56 |
+
| 1.58 | 0.1739 | 20 | 1.5665 |
|
| 57 |
+
| 1.4109 | 0.2609 | 30 | 1.4856 |
|
| 58 |
+
| 1.4493 | 0.3478 | 40 | 1.4159 |
|
| 59 |
+
| 1.2503 | 0.4348 | 50 | 1.3493 |
|
| 60 |
+
| 1.2441 | 0.5217 | 60 | 1.2719 |
|
| 61 |
+
| 1.1923 | 0.6087 | 70 | 1.1930 |
|
| 62 |
+
| 1.1158 | 0.6957 | 80 | 1.1193 |
|
| 63 |
+
| 1.0184 | 0.7826 | 90 | 1.0541 |
|
| 64 |
+
| 1.0231 | 0.8696 | 100 | 1.0056 |
|
| 65 |
+
| 0.9731 | 0.9565 | 110 | 0.9619 |
|
| 66 |
+
| 0.892 | 1.0435 | 120 | 0.9170 |
|
| 67 |
+
| 0.911 | 1.1304 | 130 | 0.8727 |
|
| 68 |
+
| 0.7789 | 1.2174 | 140 | 0.8338 |
|
| 69 |
+
| 0.8049 | 1.3043 | 150 | 0.8041 |
|
| 70 |
+
| 0.7691 | 1.3913 | 160 | 0.7788 |
|
| 71 |
+
| 0.7869 | 1.4783 | 170 | 0.7589 |
|
| 72 |
+
| 0.7366 | 1.5652 | 180 | 0.7428 |
|
| 73 |
+
| 0.7436 | 1.6522 | 190 | 0.7282 |
|
| 74 |
+
| 0.7271 | 1.7391 | 200 | 0.7157 |
|
| 75 |
+
| 0.6809 | 1.8261 | 210 | 0.7056 |
|
| 76 |
+
| 0.7068 | 1.9130 | 220 | 0.6960 |
|
| 77 |
+
| 0.6446 | 2.0 | 230 | 0.6872 |
|
| 78 |
+
| 0.6682 | 2.0870 | 240 | 0.6819 |
|
| 79 |
+
| 0.7003 | 2.1739 | 250 | 0.6745 |
|
| 80 |
+
| 0.6859 | 2.2609 | 260 | 0.6701 |
|
| 81 |
+
| 0.6169 | 2.3478 | 270 | 0.6655 |
|
| 82 |
+
| 0.666 | 2.4348 | 280 | 0.6607 |
|
| 83 |
+
| 0.6325 | 2.5217 | 290 | 0.6575 |
|
| 84 |
+
| 0.6408 | 2.6087 | 300 | 0.6536 |
|
| 85 |
+
| 0.6371 | 2.6957 | 310 | 0.6507 |
|
| 86 |
+
| 0.5933 | 2.7826 | 320 | 0.6474 |
|
| 87 |
+
| 0.6313 | 2.8696 | 330 | 0.6450 |
|
| 88 |
+
| 0.6453 | 2.9565 | 340 | 0.6421 |
|
| 89 |
+
| 0.6807 | 3.0435 | 350 | 0.6407 |
|
| 90 |
+
| 0.6217 | 3.1304 | 360 | 0.6390 |
|
| 91 |
+
| 0.589 | 3.2174 | 370 | 0.6355 |
|
| 92 |
+
| 0.5591 | 3.3043 | 380 | 0.6337 |
|
| 93 |
+
| 0.6818 | 3.3913 | 390 | 0.6319 |
|
| 94 |
+
| 0.6269 | 3.4783 | 400 | 0.6306 |
|
| 95 |
+
| 0.611 | 3.5652 | 410 | 0.6286 |
|
| 96 |
+
| 0.5602 | 3.6522 | 420 | 0.6268 |
|
| 97 |
+
| 0.6735 | 3.7391 | 430 | 0.6251 |
|
| 98 |
+
| 0.5269 | 3.8261 | 440 | 0.6246 |
|
| 99 |
+
| 0.6109 | 3.9130 | 450 | 0.6232 |
|
| 100 |
+
| 0.5745 | 4.0 | 460 | 0.6221 |
|
| 101 |
+
| 0.6348 | 4.0870 | 470 | 0.6227 |
|
| 102 |
+
| 0.5398 | 4.1739 | 480 | 0.6203 |
|
| 103 |
+
| 0.6145 | 4.2609 | 490 | 0.6194 |
|
| 104 |
+
| 0.621 | 4.3478 | 500 | 0.6178 |
|
| 105 |
+
| 0.6123 | 4.4348 | 510 | 0.6172 |
|
| 106 |
+
| 0.6113 | 4.5217 | 520 | 0.6162 |
|
| 107 |
+
| 0.5991 | 4.6087 | 530 | 0.6154 |
|
| 108 |
+
| 0.5244 | 4.6957 | 540 | 0.6143 |
|
| 109 |
+
| 0.5832 | 4.7826 | 550 | 0.6136 |
|
| 110 |
+
| 0.6284 | 4.8696 | 560 | 0.6120 |
|
| 111 |
+
| 0.54 | 4.9565 | 570 | 0.6121 |
|
| 112 |
+
| 0.541 | 5.0435 | 580 | 0.6120 |
|
| 113 |
+
| 0.5204 | 5.1304 | 590 | 0.6108 |
|
| 114 |
+
| 0.5961 | 5.2174 | 600 | 0.6101 |
|
| 115 |
+
| 0.5522 | 5.3043 | 610 | 0.6098 |
|
| 116 |
+
| 0.5778 | 5.3913 | 620 | 0.6087 |
|
| 117 |
+
| 0.6059 | 5.4783 | 630 | 0.6090 |
|
| 118 |
+
| 0.5852 | 5.5652 | 640 | 0.6085 |
|
| 119 |
+
| 0.5687 | 5.6522 | 650 | 0.6072 |
|
| 120 |
+
| 0.5685 | 5.7391 | 660 | 0.6061 |
|
| 121 |
+
| 0.593 | 5.8261 | 670 | 0.6052 |
|
| 122 |
+
| 0.5975 | 5.9130 | 680 | 0.6055 |
|
| 123 |
+
| 0.5489 | 6.0 | 690 | 0.6047 |
|
| 124 |
+
| 0.567 | 6.0870 | 700 | 0.6049 |
|
| 125 |
+
| 0.5706 | 6.1739 | 710 | 0.6035 |
|
| 126 |
+
| 0.658 | 6.2609 | 720 | 0.6024 |
|
| 127 |
+
| 0.559 | 6.3478 | 730 | 0.6023 |
|
| 128 |
+
| 0.545 | 6.4348 | 740 | 0.6019 |
|
| 129 |
+
| 0.6096 | 6.5217 | 750 | 0.6021 |
|
| 130 |
+
| 0.5385 | 6.6087 | 760 | 0.6018 |
|
| 131 |
+
| 0.5505 | 6.6957 | 770 | 0.6012 |
|
| 132 |
+
| 0.5058 | 6.7826 | 780 | 0.6003 |
|
| 133 |
+
| 0.5899 | 6.8696 | 790 | 0.5999 |
|
| 134 |
+
| 0.5102 | 6.9565 | 800 | 0.5995 |
|
| 135 |
+
| 0.5185 | 7.0435 | 810 | 0.5995 |
|
| 136 |
+
| 0.5055 | 7.1304 | 820 | 0.5991 |
|
| 137 |
+
| 0.5907 | 7.2174 | 830 | 0.5997 |
|
| 138 |
+
| 0.5636 | 7.3043 | 840 | 0.5991 |
|
| 139 |
+
| 0.5505 | 7.3913 | 850 | 0.5986 |
|
| 140 |
+
| 0.5621 | 7.4783 | 860 | 0.5977 |
|
| 141 |
+
| 0.4968 | 7.5652 | 870 | 0.5976 |
|
| 142 |
+
| 0.5713 | 7.6522 | 880 | 0.5970 |
|
| 143 |
+
| 0.5968 | 7.7391 | 890 | 0.5970 |
|
| 144 |
+
| 0.531 | 7.8261 | 900 | 0.5964 |
|
| 145 |
+
| 0.538 | 7.9130 | 910 | 0.5959 |
|
| 146 |
+
| 0.6087 | 8.0 | 920 | 0.5959 |
|
| 147 |
+
| 0.5845 | 8.0870 | 930 | 0.5963 |
|
| 148 |
+
| 0.5197 | 8.1739 | 940 | 0.5960 |
|
| 149 |
+
| 0.5128 | 8.2609 | 950 | 0.5959 |
|
| 150 |
+
| 0.5613 | 8.3478 | 960 | 0.5956 |
|
| 151 |
+
| 0.5268 | 8.4348 | 970 | 0.5953 |
|
| 152 |
+
| 0.5696 | 8.5217 | 980 | 0.5952 |
|
| 153 |
+
| 0.5755 | 8.6087 | 990 | 0.5941 |
|
| 154 |
+
| 0.5014 | 8.6957 | 1000 | 0.5945 |
|
| 155 |
+
| 0.5568 | 8.7826 | 1010 | 0.5936 |
|
| 156 |
+
| 0.5934 | 8.8696 | 1020 | 0.5944 |
|
| 157 |
+
| 0.5178 | 8.9565 | 1030 | 0.5941 |
|
| 158 |
+
| 0.4618 | 9.0435 | 1040 | 0.5936 |
|
| 159 |
+
| 0.4867 | 9.1304 | 1050 | 0.5934 |
|
| 160 |
+
| 0.5402 | 9.2174 | 1060 | 0.5937 |
|
| 161 |
+
| 0.5177 | 9.3043 | 1070 | 0.5936 |
|
| 162 |
+
| 0.5825 | 9.3913 | 1080 | 0.5926 |
|
| 163 |
+
| 0.5523 | 9.4783 | 1090 | 0.5929 |
|
| 164 |
+
| 0.583 | 9.5652 | 1100 | 0.5920 |
|
| 165 |
+
| 0.5232 | 9.6522 | 1110 | 0.5927 |
|
| 166 |
+
| 0.5367 | 9.7391 | 1120 | 0.5920 |
|
| 167 |
+
| 0.5321 | 9.8261 | 1130 | 0.5913 |
|
| 168 |
+
| 0.5672 | 9.9130 | 1140 | 0.5910 |
|
| 169 |
+
| 0.5549 | 10.0 | 1150 | 0.5910 |
|
| 170 |
+
| 0.5191 | 10.0870 | 1160 | 0.5915 |
|
| 171 |
+
| 0.5463 | 10.1739 | 1170 | 0.5915 |
|
| 172 |
+
| 0.5275 | 10.2609 | 1180 | 0.5913 |
|
| 173 |
+
| 0.5484 | 10.3478 | 1190 | 0.5915 |
|
| 174 |
+
| 0.5293 | 10.4348 | 1200 | 0.5910 |
|
| 175 |
+
| 0.519 | 10.5217 | 1210 | 0.5903 |
|
| 176 |
+
| 0.5129 | 10.6087 | 1220 | 0.5898 |
|
| 177 |
+
| 0.5793 | 10.6957 | 1230 | 0.5900 |
|
| 178 |
+
| 0.4481 | 10.7826 | 1240 | 0.5901 |
|
| 179 |
+
| 0.5309 | 10.8696 | 1250 | 0.5903 |
|
| 180 |
+
| 0.5887 | 10.9565 | 1260 | 0.5898 |
|
| 181 |
+
| 0.5109 | 11.0435 | 1270 | 0.5907 |
|
| 182 |
+
| 0.5776 | 11.1304 | 1280 | 0.5902 |
|
| 183 |
+
| 0.4984 | 11.2174 | 1290 | 0.5898 |
|
| 184 |
+
| 0.5656 | 11.3043 | 1300 | 0.5898 |
|
| 185 |
+
| 0.4931 | 11.3913 | 1310 | 0.5902 |
|
| 186 |
+
| 0.531 | 11.4783 | 1320 | 0.5900 |
|
| 187 |
+
| 0.5163 | 11.5652 | 1330 | 0.5892 |
|
| 188 |
+
| 0.5314 | 11.6522 | 1340 | 0.5894 |
|
| 189 |
+
| 0.4766 | 11.7391 | 1350 | 0.5893 |
|
| 190 |
+
| 0.5201 | 11.8261 | 1360 | 0.5896 |
|
| 191 |
+
| 0.6127 | 11.9130 | 1370 | 0.5889 |
|
| 192 |
+
| 0.5441 | 12.0 | 1380 | 0.5888 |
|
| 193 |
+
| 0.5258 | 12.0870 | 1390 | 0.5894 |
|
| 194 |
+
| 0.5722 | 12.1739 | 1400 | 0.5887 |
|
| 195 |
+
| 0.5228 | 12.2609 | 1410 | 0.5891 |
|
| 196 |
+
| 0.524 | 12.3478 | 1420 | 0.5884 |
|
| 197 |
+
| 0.4951 | 12.4348 | 1430 | 0.5894 |
|
| 198 |
+
| 0.5235 | 12.5217 | 1440 | 0.5893 |
|
| 199 |
+
| 0.5071 | 12.6087 | 1450 | 0.5889 |
|
| 200 |
+
| 0.5417 | 12.6957 | 1460 | 0.5886 |
|
| 201 |
+
| 0.4882 | 12.7826 | 1470 | 0.5889 |
|
| 202 |
+
| 0.548 | 12.8696 | 1480 | 0.5889 |
|
| 203 |
+
| 0.529 | 12.9565 | 1490 | 0.5889 |
|
| 204 |
+
| 0.5646 | 13.0435 | 1500 | 0.5887 |
|
| 205 |
+
| 0.5142 | 13.1304 | 1510 | 0.5889 |
|
| 206 |
+
| 0.5161 | 13.2174 | 1520 | 0.5886 |
|
| 207 |
+
| 0.5008 | 13.3043 | 1530 | 0.5888 |
|
| 208 |
+
| 0.5187 | 13.3913 | 1540 | 0.5887 |
|
| 209 |
+
| 0.5334 | 13.4783 | 1550 | 0.5886 |
|
| 210 |
+
| 0.5099 | 13.5652 | 1560 | 0.5884 |
|
| 211 |
+
| 0.5644 | 13.6522 | 1570 | 0.5888 |
|
| 212 |
+
| 0.5242 | 13.7391 | 1580 | 0.5882 |
|
| 213 |
+
| 0.4912 | 13.8261 | 1590 | 0.5886 |
|
| 214 |
+
| 0.5459 | 13.9130 | 1600 | 0.5884 |
|
| 215 |
+
| 0.5204 | 14.0 | 1610 | 0.5881 |
|
| 216 |
+
| 0.4644 | 14.0870 | 1620 | 0.5884 |
|
| 217 |
+
| 0.5364 | 14.1739 | 1630 | 0.5885 |
|
| 218 |
+
| 0.5852 | 14.2609 | 1640 | 0.5887 |
|
| 219 |
+
| 0.5135 | 14.3478 | 1650 | 0.5884 |
|
| 220 |
+
| 0.5192 | 14.4348 | 1660 | 0.5885 |
|
| 221 |
+
| 0.5093 | 14.5217 | 1670 | 0.5880 |
|
| 222 |
+
| 0.5398 | 14.6087 | 1680 | 0.5884 |
|
| 223 |
+
| 0.469 | 14.6957 | 1690 | 0.5882 |
|
| 224 |
+
| 0.5163 | 14.7826 | 1700 | 0.5883 |
|
| 225 |
+
| 0.5165 | 14.8696 | 1710 | 0.5883 |
|
| 226 |
+
| 0.5441 | 14.9565 | 1720 | 0.5881 |
|
| 227 |
+
|
| 228 |
+
|
| 229 |
+
### Framework versions
|
| 230 |
+
|
| 231 |
+
- PEFT 0.12.0
|
| 232 |
+
- Transformers 4.44.0
|
| 233 |
+
- Pytorch 2.4.0+cu121
|
| 234 |
+
- Datasets 2.20.0
|
| 235 |
+
- Tokenizers 0.19.1
|
adapter_config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "mistralai/Mixtral-8x7B-v0.1",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.1,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 64,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"down_proj",
|
| 24 |
+
"o_proj",
|
| 25 |
+
"k_proj",
|
| 26 |
+
"q_proj",
|
| 27 |
+
"lm_head",
|
| 28 |
+
"gate_proj",
|
| 29 |
+
"v_proj",
|
| 30 |
+
"up_proj"
|
| 31 |
+
],
|
| 32 |
+
"task_type": "CAUSAL_LM",
|
| 33 |
+
"use_dora": false,
|
| 34 |
+
"use_rslora": false
|
| 35 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28c25b5955384c7f1cdbd3faa1f80d43eb7119c32b3f1dc5a912f8d14ab7191f
|
| 3 |
+
size 751667752
|
runs/Aug12_07-24-44_9bcd5dae9cf3/events.out.tfevents.1723447489.9bcd5dae9cf3.1307.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:879769f8f8dbaa626026e478b17ffe8ec362a25009f0495435622817ed2e4cee
|
| 3 |
+
size 88975
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 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 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"additional_special_tokens": [],
|
| 32 |
+
"bos_token": "<s>",
|
| 33 |
+
"clean_up_tokenization_spaces": false,
|
| 34 |
+
"eos_token": "</s>",
|
| 35 |
+
"legacy": true,
|
| 36 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 37 |
+
"pad_token": "</s>",
|
| 38 |
+
"sp_model_kwargs": {},
|
| 39 |
+
"spaces_between_special_tokens": false,
|
| 40 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 41 |
+
"unk_token": "<unk>",
|
| 42 |
+
"use_default_system_prompt": false
|
| 43 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6143df11c770bb500f028645adeb1c6c16aa2d198b7648eb603005a4b0aa840
|
| 3 |
+
size 5432
|