Training in progress, step 100
Browse files- README.md +178 -0
- adapter_config.json +29 -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 +1,178 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: peiyi9979/math-shepherd-mistral-7b-prm
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
- precision
|
| 9 |
+
- recall
|
| 10 |
+
- f1
|
| 11 |
+
model-index:
|
| 12 |
+
- name: v3b_mistral_lora
|
| 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 |
+
# v3b_mistral_lora
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [peiyi9979/math-shepherd-mistral-7b-prm](https://huggingface.co/peiyi9979/math-shepherd-mistral-7b-prm) on an unknown dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.0126
|
| 24 |
+
- Accuracy: 0.9936
|
| 25 |
+
- Precision: 0.8793
|
| 26 |
+
- Recall: 0.9808
|
| 27 |
+
- F1: 0.9273
|
| 28 |
+
|
| 29 |
+
## Model description
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Intended uses & limitations
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training and evaluation data
|
| 38 |
+
|
| 39 |
+
More information needed
|
| 40 |
+
|
| 41 |
+
## Training procedure
|
| 42 |
+
|
| 43 |
+
### Training hyperparameters
|
| 44 |
+
|
| 45 |
+
The following hyperparameters were used during training:
|
| 46 |
+
- learning_rate: 2e-05
|
| 47 |
+
- train_batch_size: 8
|
| 48 |
+
- eval_batch_size: 8
|
| 49 |
+
- seed: 765837
|
| 50 |
+
- distributed_type: multi-GPU
|
| 51 |
+
- num_devices: 4
|
| 52 |
+
- gradient_accumulation_steps: 2
|
| 53 |
+
- total_train_batch_size: 64
|
| 54 |
+
- total_eval_batch_size: 32
|
| 55 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 56 |
+
- lr_scheduler_type: cosine
|
| 57 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 58 |
+
- num_epochs: 1
|
| 59 |
+
|
| 60 |
+
### Training results
|
| 61 |
+
|
| 62 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|
| 63 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
|
| 64 |
+
| No log | 0 | 0 | 0.3911 | 0.9098 | 0.2222 | 0.4615 | 0.3 |
|
| 65 |
+
| 0.7904 | 0.0095 | 20 | 0.3855 | 0.9163 | 0.24 | 0.4615 | 0.3158 |
|
| 66 |
+
| 0.6496 | 0.0190 | 40 | 0.3578 | 0.9300 | 0.2603 | 0.3654 | 0.304 |
|
| 67 |
+
| 0.5209 | 0.0284 | 60 | 0.3011 | 0.9469 | 0.2941 | 0.1923 | 0.2326 |
|
| 68 |
+
| 0.482 | 0.0379 | 80 | 0.2597 | 0.9525 | 0.3478 | 0.1538 | 0.2133 |
|
| 69 |
+
| 0.4165 | 0.0474 | 100 | 0.2602 | 0.9549 | 0.4524 | 0.3654 | 0.4043 |
|
| 70 |
+
| 0.5055 | 0.0569 | 120 | 0.2183 | 0.9614 | 0.5345 | 0.5962 | 0.5636 |
|
| 71 |
+
| 0.2795 | 0.0664 | 140 | 0.1609 | 0.9541 | 0.4699 | 0.75 | 0.5778 |
|
| 72 |
+
| 0.3314 | 0.0758 | 160 | 0.1574 | 0.9316 | 0.3659 | 0.8654 | 0.5143 |
|
| 73 |
+
| 0.257 | 0.0853 | 180 | 0.1001 | 0.9597 | 0.5119 | 0.8269 | 0.6324 |
|
| 74 |
+
| 0.3089 | 0.0948 | 200 | 0.0747 | 0.9750 | 0.6567 | 0.8462 | 0.7395 |
|
| 75 |
+
| 0.329 | 0.1043 | 220 | 0.0722 | 0.9742 | 0.6471 | 0.8462 | 0.7333 |
|
| 76 |
+
| 0.4088 | 0.1138 | 240 | 0.0581 | 0.9815 | 0.7458 | 0.8462 | 0.7928 |
|
| 77 |
+
| 0.2598 | 0.1233 | 260 | 0.0531 | 0.9815 | 0.7458 | 0.8462 | 0.7928 |
|
| 78 |
+
| 0.1978 | 0.1327 | 280 | 0.0428 | 0.9863 | 0.8070 | 0.8846 | 0.8440 |
|
| 79 |
+
| 0.1661 | 0.1422 | 300 | 0.0452 | 0.9839 | 0.75 | 0.9231 | 0.8276 |
|
| 80 |
+
| 0.2944 | 0.1517 | 320 | 0.0511 | 0.9815 | 0.7101 | 0.9423 | 0.8099 |
|
| 81 |
+
| 0.2463 | 0.1612 | 340 | 0.0379 | 0.9847 | 0.7463 | 0.9615 | 0.8403 |
|
| 82 |
+
| 0.1767 | 0.1707 | 360 | 0.0379 | 0.9871 | 0.7812 | 0.9615 | 0.8621 |
|
| 83 |
+
| 0.1581 | 0.1801 | 380 | 0.0315 | 0.9903 | 0.8571 | 0.9231 | 0.8889 |
|
| 84 |
+
| 0.1162 | 0.1896 | 400 | 0.0378 | 0.9863 | 0.7692 | 0.9615 | 0.8547 |
|
| 85 |
+
| 0.1442 | 0.1991 | 420 | 0.0395 | 0.9855 | 0.7656 | 0.9423 | 0.8448 |
|
| 86 |
+
| 0.1957 | 0.2086 | 440 | 0.0343 | 0.9903 | 0.8333 | 0.9615 | 0.8929 |
|
| 87 |
+
| 0.2593 | 0.2181 | 460 | 0.0308 | 0.9919 | 0.875 | 0.9423 | 0.9074 |
|
| 88 |
+
| 0.1137 | 0.2275 | 480 | 0.0236 | 0.9936 | 0.8929 | 0.9615 | 0.9259 |
|
| 89 |
+
| 0.2213 | 0.2370 | 500 | 0.0264 | 0.9879 | 0.7846 | 0.9808 | 0.8718 |
|
| 90 |
+
| 0.2092 | 0.2465 | 520 | 0.0336 | 0.9895 | 0.8197 | 0.9615 | 0.8850 |
|
| 91 |
+
| 0.2247 | 0.2560 | 540 | 0.0287 | 0.9928 | 0.8909 | 0.9423 | 0.9159 |
|
| 92 |
+
| 0.2684 | 0.2655 | 560 | 0.0286 | 0.9919 | 0.8621 | 0.9615 | 0.9091 |
|
| 93 |
+
| 0.1485 | 0.2749 | 580 | 0.0354 | 0.9895 | 0.8197 | 0.9615 | 0.8850 |
|
| 94 |
+
| 0.1168 | 0.2844 | 600 | 0.0274 | 0.9928 | 0.8909 | 0.9423 | 0.9159 |
|
| 95 |
+
| 0.1899 | 0.2939 | 620 | 0.0262 | 0.9911 | 0.8475 | 0.9615 | 0.9009 |
|
| 96 |
+
| 0.1626 | 0.3034 | 640 | 0.0274 | 0.9895 | 0.8197 | 0.9615 | 0.8850 |
|
| 97 |
+
| 0.1919 | 0.3129 | 660 | 0.0435 | 0.9847 | 0.7324 | 1.0 | 0.8455 |
|
| 98 |
+
| 0.1953 | 0.3224 | 680 | 0.0215 | 0.9936 | 0.8929 | 0.9615 | 0.9259 |
|
| 99 |
+
| 0.1978 | 0.3318 | 700 | 0.0260 | 0.9903 | 0.8333 | 0.9615 | 0.8929 |
|
| 100 |
+
| 0.311 | 0.3413 | 720 | 0.0168 | 0.9944 | 0.9091 | 0.9615 | 0.9346 |
|
| 101 |
+
| 0.226 | 0.3508 | 740 | 0.0166 | 0.9928 | 0.8525 | 1.0 | 0.9204 |
|
| 102 |
+
| 0.1394 | 0.3603 | 760 | 0.0195 | 0.9919 | 0.85 | 0.9808 | 0.9107 |
|
| 103 |
+
| 0.1702 | 0.3698 | 780 | 0.0358 | 0.9855 | 0.75 | 0.9808 | 0.85 |
|
| 104 |
+
| 0.1413 | 0.3792 | 800 | 0.0269 | 0.9911 | 0.8361 | 0.9808 | 0.9027 |
|
| 105 |
+
| 0.2015 | 0.3887 | 820 | 0.0238 | 0.9911 | 0.8361 | 0.9808 | 0.9027 |
|
| 106 |
+
| 0.1752 | 0.3982 | 840 | 0.0253 | 0.9895 | 0.8 | 1.0 | 0.8889 |
|
| 107 |
+
| 0.212 | 0.4077 | 860 | 0.0250 | 0.9911 | 0.8475 | 0.9615 | 0.9009 |
|
| 108 |
+
| 0.1556 | 0.4172 | 880 | 0.0247 | 0.9928 | 0.8909 | 0.9423 | 0.9159 |
|
| 109 |
+
| 0.1495 | 0.4266 | 900 | 0.0141 | 0.9919 | 0.85 | 0.9808 | 0.9107 |
|
| 110 |
+
| 0.1666 | 0.4361 | 920 | 0.0187 | 0.9936 | 0.9074 | 0.9423 | 0.9245 |
|
| 111 |
+
| 0.1475 | 0.4456 | 940 | 0.0199 | 0.9911 | 0.8361 | 0.9808 | 0.9027 |
|
| 112 |
+
| 0.1459 | 0.4551 | 960 | 0.0166 | 0.9919 | 0.8387 | 1.0 | 0.9123 |
|
| 113 |
+
| 0.1264 | 0.4646 | 980 | 0.0155 | 0.9936 | 0.8793 | 0.9808 | 0.9273 |
|
| 114 |
+
| 0.1389 | 0.4740 | 1000 | 0.0152 | 0.9944 | 0.9091 | 0.9615 | 0.9346 |
|
| 115 |
+
| 0.1433 | 0.4835 | 1020 | 0.0147 | 0.9944 | 0.9091 | 0.9615 | 0.9346 |
|
| 116 |
+
| 0.1389 | 0.4930 | 1040 | 0.0126 | 0.9968 | 0.9444 | 0.9808 | 0.9623 |
|
| 117 |
+
| 0.1452 | 0.5025 | 1060 | 0.0230 | 0.9903 | 0.8125 | 1.0 | 0.8966 |
|
| 118 |
+
| 0.1623 | 0.5120 | 1080 | 0.0128 | 0.9952 | 0.9259 | 0.9615 | 0.9434 |
|
| 119 |
+
| 0.1179 | 0.5215 | 1100 | 0.0156 | 0.9952 | 0.8966 | 1.0 | 0.9455 |
|
| 120 |
+
| 0.1256 | 0.5309 | 1120 | 0.0175 | 0.9952 | 0.9107 | 0.9808 | 0.9444 |
|
| 121 |
+
| 0.1536 | 0.5404 | 1140 | 0.0221 | 0.9919 | 0.85 | 0.9808 | 0.9107 |
|
| 122 |
+
| 0.1873 | 0.5499 | 1160 | 0.0234 | 0.9903 | 0.8125 | 1.0 | 0.8966 |
|
| 123 |
+
| 0.1234 | 0.5594 | 1180 | 0.0174 | 0.9944 | 0.9091 | 0.9615 | 0.9346 |
|
| 124 |
+
| 0.205 | 0.5689 | 1200 | 0.0162 | 0.9944 | 0.8814 | 1.0 | 0.9369 |
|
| 125 |
+
| 0.1975 | 0.5783 | 1220 | 0.0155 | 0.9944 | 0.9091 | 0.9615 | 0.9346 |
|
| 126 |
+
| 0.1302 | 0.5878 | 1240 | 0.0131 | 0.9960 | 0.9123 | 1.0 | 0.9541 |
|
| 127 |
+
| 0.2996 | 0.5973 | 1260 | 0.0172 | 0.9944 | 0.8814 | 1.0 | 0.9369 |
|
| 128 |
+
| 0.1381 | 0.6068 | 1280 | 0.0145 | 0.9936 | 0.8929 | 0.9615 | 0.9259 |
|
| 129 |
+
| 0.1559 | 0.6163 | 1300 | 0.0142 | 0.9936 | 0.8929 | 0.9615 | 0.9259 |
|
| 130 |
+
| 0.1588 | 0.6257 | 1320 | 0.0194 | 0.9911 | 0.8361 | 0.9808 | 0.9027 |
|
| 131 |
+
| 0.1101 | 0.6352 | 1340 | 0.0149 | 0.9936 | 0.8929 | 0.9615 | 0.9259 |
|
| 132 |
+
| 0.1533 | 0.6447 | 1360 | 0.0152 | 0.9936 | 0.8667 | 1.0 | 0.9286 |
|
| 133 |
+
| 0.1567 | 0.6542 | 1380 | 0.0139 | 0.9928 | 0.8772 | 0.9615 | 0.9174 |
|
| 134 |
+
| 0.1771 | 0.6637 | 1400 | 0.0176 | 0.9936 | 0.8793 | 0.9808 | 0.9273 |
|
| 135 |
+
| 0.1531 | 0.6731 | 1420 | 0.0142 | 0.9928 | 0.8772 | 0.9615 | 0.9174 |
|
| 136 |
+
| 0.1366 | 0.6826 | 1440 | 0.0157 | 0.9928 | 0.8525 | 1.0 | 0.9204 |
|
| 137 |
+
| 0.1597 | 0.6921 | 1460 | 0.0149 | 0.9944 | 0.8814 | 1.0 | 0.9369 |
|
| 138 |
+
| 0.1527 | 0.7016 | 1480 | 0.0156 | 0.9919 | 0.8387 | 1.0 | 0.9123 |
|
| 139 |
+
| 0.2199 | 0.7111 | 1500 | 0.0137 | 0.9944 | 0.8814 | 1.0 | 0.9369 |
|
| 140 |
+
| 0.2215 | 0.7205 | 1520 | 0.0140 | 0.9944 | 0.8814 | 1.0 | 0.9369 |
|
| 141 |
+
| 0.199 | 0.7300 | 1540 | 0.0167 | 0.9936 | 0.8667 | 1.0 | 0.9286 |
|
| 142 |
+
| 0.1505 | 0.7395 | 1560 | 0.0106 | 0.9960 | 0.9273 | 0.9808 | 0.9533 |
|
| 143 |
+
| 0.2082 | 0.7490 | 1580 | 0.0146 | 0.9928 | 0.8525 | 1.0 | 0.9204 |
|
| 144 |
+
| 0.1431 | 0.7585 | 1600 | 0.0108 | 0.9944 | 0.8947 | 0.9808 | 0.9358 |
|
| 145 |
+
| 0.1388 | 0.7680 | 1620 | 0.0125 | 0.9952 | 0.8966 | 1.0 | 0.9455 |
|
| 146 |
+
| 0.1221 | 0.7774 | 1640 | 0.0100 | 0.9960 | 0.9273 | 0.9808 | 0.9533 |
|
| 147 |
+
| 0.1571 | 0.7869 | 1660 | 0.0108 | 0.9960 | 0.9273 | 0.9808 | 0.9533 |
|
| 148 |
+
| 0.1472 | 0.7964 | 1680 | 0.0115 | 0.9944 | 0.8947 | 0.9808 | 0.9358 |
|
| 149 |
+
| 0.1236 | 0.8059 | 1700 | 0.0121 | 0.9936 | 0.8793 | 0.9808 | 0.9273 |
|
| 150 |
+
| 0.1477 | 0.8154 | 1720 | 0.0113 | 0.9952 | 0.9107 | 0.9808 | 0.9444 |
|
| 151 |
+
| 0.1781 | 0.8248 | 1740 | 0.0139 | 0.9936 | 0.8793 | 0.9808 | 0.9273 |
|
| 152 |
+
| 0.1517 | 0.8343 | 1760 | 0.0129 | 0.9936 | 0.8793 | 0.9808 | 0.9273 |
|
| 153 |
+
| 0.1811 | 0.8438 | 1780 | 0.0123 | 0.9944 | 0.8947 | 0.9808 | 0.9358 |
|
| 154 |
+
| 0.1592 | 0.8533 | 1800 | 0.0136 | 0.9944 | 0.8814 | 1.0 | 0.9369 |
|
| 155 |
+
| 0.0799 | 0.8628 | 1820 | 0.0149 | 0.9944 | 0.8814 | 1.0 | 0.9369 |
|
| 156 |
+
| 0.1294 | 0.8722 | 1840 | 0.0130 | 0.9944 | 0.8814 | 1.0 | 0.9369 |
|
| 157 |
+
| 0.2076 | 0.8817 | 1860 | 0.0121 | 0.9936 | 0.8793 | 0.9808 | 0.9273 |
|
| 158 |
+
| 0.1628 | 0.8912 | 1880 | 0.0121 | 0.9936 | 0.8793 | 0.9808 | 0.9273 |
|
| 159 |
+
| 0.156 | 0.9007 | 1900 | 0.0128 | 0.9936 | 0.8793 | 0.9808 | 0.9273 |
|
| 160 |
+
| 0.0762 | 0.9102 | 1920 | 0.0128 | 0.9936 | 0.8793 | 0.9808 | 0.9273 |
|
| 161 |
+
| 0.1372 | 0.9196 | 1940 | 0.0124 | 0.9936 | 0.8793 | 0.9808 | 0.9273 |
|
| 162 |
+
| 0.0837 | 0.9291 | 1960 | 0.0123 | 0.9936 | 0.8793 | 0.9808 | 0.9273 |
|
| 163 |
+
| 0.1353 | 0.9386 | 1980 | 0.0126 | 0.9936 | 0.8793 | 0.9808 | 0.9273 |
|
| 164 |
+
| 0.1914 | 0.9481 | 2000 | 0.0127 | 0.9936 | 0.8793 | 0.9808 | 0.9273 |
|
| 165 |
+
| 0.1072 | 0.9576 | 2020 | 0.0127 | 0.9936 | 0.8793 | 0.9808 | 0.9273 |
|
| 166 |
+
| 0.2165 | 0.9671 | 2040 | 0.0129 | 0.9936 | 0.8793 | 0.9808 | 0.9273 |
|
| 167 |
+
| 0.1417 | 0.9765 | 2060 | 0.0127 | 0.9936 | 0.8793 | 0.9808 | 0.9273 |
|
| 168 |
+
| 0.101 | 0.9860 | 2080 | 0.0126 | 0.9936 | 0.8793 | 0.9808 | 0.9273 |
|
| 169 |
+
| 0.2136 | 0.9955 | 2100 | 0.0126 | 0.9936 | 0.8793 | 0.9808 | 0.9273 |
|
| 170 |
+
|
| 171 |
+
|
| 172 |
+
### Framework versions
|
| 173 |
+
|
| 174 |
+
- PEFT 0.13.2
|
| 175 |
+
- Transformers 4.46.0
|
| 176 |
+
- Pytorch 2.5.1+cu124
|
| 177 |
+
- Datasets 3.1.0
|
| 178 |
+
- Tokenizers 0.20.3
|
adapter_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "peiyi9979/math-shepherd-mistral-7b-prm",
|
| 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": 32,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 16,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"q_proj",
|
| 24 |
+
"v_proj"
|
| 25 |
+
],
|
| 26 |
+
"task_type": "CAUSAL_LM",
|
| 27 |
+
"use_dora": false,
|
| 28 |
+
"use_rslora": false
|
| 29 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4881c1416e4e60ff3fc448f414717d7cc514f4df723130438bc8a0ac0797bfd4
|
| 3 |
+
size 27280152
|
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 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": true,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": true,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
}
|
| 30 |
+
},
|
| 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 sha256:4ecd4b75950b987770c42135c3af97eab30994c1b33645440f4b3c525ddb354a
|
| 3 |
+
size 5240
|