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
|
| 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_default
|
| 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_default
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [unsloth/Qwen2-7B](https://huggingface.co/unsloth/Qwen2-7B) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 2.0259
|
| 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 |
+
| 2.1169 | 0.0206 | 8 | 2.0201 |
|
| 55 |
+
| 2.1264 | 0.0412 | 16 | 2.0886 |
|
| 56 |
+
| 2.1468 | 0.0618 | 24 | 2.0745 |
|
| 57 |
+
| 2.0954 | 0.0824 | 32 | 2.0725 |
|
| 58 |
+
| 2.136 | 0.1031 | 40 | 2.0759 |
|
| 59 |
+
| 2.1289 | 0.1237 | 48 | 2.1111 |
|
| 60 |
+
| 2.131 | 0.1443 | 56 | 2.0744 |
|
| 61 |
+
| 2.1168 | 0.1649 | 64 | 2.0766 |
|
| 62 |
+
| 2.149 | 0.1855 | 72 | 2.1028 |
|
| 63 |
+
| 2.1947 | 0.2061 | 80 | 2.0999 |
|
| 64 |
+
| 2.1727 | 0.2267 | 88 | 2.0999 |
|
| 65 |
+
| 2.1438 | 0.2473 | 96 | 2.0979 |
|
| 66 |
+
| 2.1639 | 0.2680 | 104 | 2.0984 |
|
| 67 |
+
| 2.0768 | 0.2886 | 112 | 2.0967 |
|
| 68 |
+
| 2.1262 | 0.3092 | 120 | 2.0943 |
|
| 69 |
+
| 2.1261 | 0.3298 | 128 | 2.0995 |
|
| 70 |
+
| 2.1411 | 0.3504 | 136 | 2.1028 |
|
| 71 |
+
| 2.1369 | 0.3710 | 144 | 2.1030 |
|
| 72 |
+
| 2.1419 | 0.3916 | 152 | 2.0989 |
|
| 73 |
+
| 2.165 | 0.4122 | 160 | 2.0972 |
|
| 74 |
+
| 2.1948 | 0.4329 | 168 | 2.0925 |
|
| 75 |
+
| 2.1076 | 0.4535 | 176 | 2.0968 |
|
| 76 |
+
| 2.1183 | 0.4741 | 184 | 2.0916 |
|
| 77 |
+
| 2.16 | 0.4947 | 192 | 2.0885 |
|
| 78 |
+
| 2.0938 | 0.5153 | 200 | 2.0884 |
|
| 79 |
+
| 2.1387 | 0.5359 | 208 | 2.0866 |
|
| 80 |
+
| 2.1735 | 0.5565 | 216 | 2.0854 |
|
| 81 |
+
| 2.0786 | 0.5771 | 224 | 2.0755 |
|
| 82 |
+
| 2.0929 | 0.5977 | 232 | 2.0793 |
|
| 83 |
+
| 2.0871 | 0.6184 | 240 | 2.0635 |
|
| 84 |
+
| 2.0744 | 0.6390 | 248 | 2.0637 |
|
| 85 |
+
| 2.1142 | 0.6596 | 256 | 2.0616 |
|
| 86 |
+
| 2.0861 | 0.6802 | 264 | 2.0570 |
|
| 87 |
+
| 2.1428 | 0.7008 | 272 | 2.0534 |
|
| 88 |
+
| 2.0474 | 0.7214 | 280 | 2.0486 |
|
| 89 |
+
| 2.1296 | 0.7420 | 288 | 2.0439 |
|
| 90 |
+
| 2.062 | 0.7626 | 296 | 2.0425 |
|
| 91 |
+
| 2.0758 | 0.7833 | 304 | 2.0405 |
|
| 92 |
+
| 2.0604 | 0.8039 | 312 | 2.0370 |
|
| 93 |
+
| 2.0963 | 0.8245 | 320 | 2.0361 |
|
| 94 |
+
| 2.0926 | 0.8451 | 328 | 2.0342 |
|
| 95 |
+
| 2.0571 | 0.8657 | 336 | 2.0307 |
|
| 96 |
+
| 2.0858 | 0.8863 | 344 | 2.0297 |
|
| 97 |
+
| 2.066 | 0.9069 | 352 | 2.0270 |
|
| 98 |
+
| 2.1284 | 0.9275 | 360 | 2.0260 |
|
| 99 |
+
| 2.0618 | 0.9481 | 368 | 2.0257 |
|
| 100 |
+
| 2.1074 | 0.9688 | 376 | 2.0256 |
|
| 101 |
+
| 2.0625 | 0.9894 | 384 | 2.0259 |
|
| 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:b1b59c2ec60e103198cb5839c8441f3ff6bce3fbdcc4488e845bdab3f5109093
|
| 3 |
size 80792096
|