End of training
Browse files- README.md +110 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: unsloth/qwen2-7b-bnb-4bit
|
| 3 |
+
library_name: peft
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
tags:
|
| 6 |
+
- unsloth
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: Qwen2-7B_pct_ortho
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# Qwen2-7B_pct_ortho
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [unsloth/qwen2-7b-bnb-4bit](https://huggingface.co/unsloth/qwen2-7b-bnb-4bit) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 2.1027
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 0.0003
|
| 40 |
+
- train_batch_size: 8
|
| 41 |
+
- eval_batch_size: 8
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 8
|
| 44 |
+
- total_train_batch_size: 64
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: cosine
|
| 47 |
+
- lr_scheduler_warmup_ratio: 0.02
|
| 48 |
+
- num_epochs: 1
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 54 |
+
| 2.1596 | 0.0206 | 8 | 2.0832 |
|
| 55 |
+
| 2.095 | 0.0412 | 16 | 2.0465 |
|
| 56 |
+
| 2.1302 | 0.0618 | 24 | 2.0538 |
|
| 57 |
+
| 2.0886 | 0.0824 | 32 | 2.0696 |
|
| 58 |
+
| 2.1386 | 0.1031 | 40 | 2.0840 |
|
| 59 |
+
| 2.141 | 0.1237 | 48 | 2.0979 |
|
| 60 |
+
| 2.1451 | 0.1443 | 56 | 2.0972 |
|
| 61 |
+
| 2.1323 | 0.1649 | 64 | 2.1059 |
|
| 62 |
+
| 2.152 | 0.1855 | 72 | 2.1132 |
|
| 63 |
+
| 2.2215 | 0.2061 | 80 | 2.1120 |
|
| 64 |
+
| 2.187 | 0.2267 | 88 | 2.1149 |
|
| 65 |
+
| 2.1712 | 0.2473 | 96 | 2.1171 |
|
| 66 |
+
| 2.2009 | 0.2680 | 104 | 2.1281 |
|
| 67 |
+
| 2.1177 | 0.2886 | 112 | 2.1351 |
|
| 68 |
+
| 2.1735 | 0.3092 | 120 | 2.1326 |
|
| 69 |
+
| 2.1785 | 0.3298 | 128 | 2.1293 |
|
| 70 |
+
| 2.1826 | 0.3504 | 136 | 2.1398 |
|
| 71 |
+
| 2.1799 | 0.3710 | 144 | 2.1419 |
|
| 72 |
+
| 2.1817 | 0.3916 | 152 | 2.1564 |
|
| 73 |
+
| 2.2199 | 0.4122 | 160 | 2.1452 |
|
| 74 |
+
| 2.2533 | 0.4329 | 168 | 2.1420 |
|
| 75 |
+
| 2.1606 | 0.4535 | 176 | 2.1434 |
|
| 76 |
+
| 2.1773 | 0.4741 | 184 | 2.1394 |
|
| 77 |
+
| 2.2177 | 0.4947 | 192 | 2.1369 |
|
| 78 |
+
| 2.1614 | 0.5153 | 200 | 2.1360 |
|
| 79 |
+
| 2.2003 | 0.5359 | 208 | 2.1389 |
|
| 80 |
+
| 2.2389 | 0.5565 | 216 | 2.1424 |
|
| 81 |
+
| 2.1515 | 0.5771 | 224 | 2.1329 |
|
| 82 |
+
| 2.16 | 0.5977 | 232 | 2.1388 |
|
| 83 |
+
| 2.1584 | 0.6184 | 240 | 2.1229 |
|
| 84 |
+
| 2.1446 | 0.6390 | 248 | 2.1275 |
|
| 85 |
+
| 2.19 | 0.6596 | 256 | 2.1256 |
|
| 86 |
+
| 2.1612 | 0.6802 | 264 | 2.1182 |
|
| 87 |
+
| 2.2218 | 0.7008 | 272 | 2.1202 |
|
| 88 |
+
| 2.1112 | 0.7214 | 280 | 2.1163 |
|
| 89 |
+
| 2.2125 | 0.7420 | 288 | 2.1118 |
|
| 90 |
+
| 2.1432 | 0.7626 | 296 | 2.1115 |
|
| 91 |
+
| 2.1537 | 0.7833 | 304 | 2.1066 |
|
| 92 |
+
| 2.1391 | 0.8039 | 312 | 2.1069 |
|
| 93 |
+
| 2.1831 | 0.8245 | 320 | 2.1115 |
|
| 94 |
+
| 2.1835 | 0.8451 | 328 | 2.1099 |
|
| 95 |
+
| 2.1461 | 0.8657 | 336 | 2.1126 |
|
| 96 |
+
| 2.183 | 0.8863 | 344 | 2.1060 |
|
| 97 |
+
| 2.1507 | 0.9069 | 352 | 2.1017 |
|
| 98 |
+
| 2.216 | 0.9275 | 360 | 2.1033 |
|
| 99 |
+
| 2.1464 | 0.9481 | 368 | 2.1032 |
|
| 100 |
+
| 2.1925 | 0.9688 | 376 | 2.1028 |
|
| 101 |
+
| 2.1514 | 0.9894 | 384 | 2.1027 |
|
| 102 |
+
|
| 103 |
+
|
| 104 |
+
### Framework versions
|
| 105 |
+
|
| 106 |
+
- PEFT 0.12.0
|
| 107 |
+
- Transformers 4.44.0
|
| 108 |
+
- Pytorch 2.4.0+cu121
|
| 109 |
+
- Datasets 2.20.0
|
| 110 |
+
- Tokenizers 0.19.1
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 80792096
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14a2f0637c273ea92d9a5405905c6ff17c1ba0de4b4a86f6a857b3703528cfe2
|
| 3 |
size 80792096
|