Hugging Face's logo

NanQiangHF
/
gemma2_9b_it_bwgenerator

PEFT
Safetensors
gemma2
trl
sft
Generated from Trainer
Model card Files Community
NanQiangHF commited on
Commit
663599a
•
1 Parent(s): 0d60d20

gemma2_9b_it_bwgenerator

Browse files
Files changed (3) hide show
  1. README.md +10 -14
  2. adapter_model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [google/gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.0963
22
 
23
  ## Model description
24
 
@@ -51,19 +51,15 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
- | 0.6428 | 0.0760 | 50 | 0.2721 |
55
- | 0.2051 | 0.1520 | 100 | 0.1771 |
56
- | 0.1636 | 0.2281 | 150 | 0.1520 |
57
- | 0.145 | 0.3041 | 200 | 0.1364 |
58
- | 0.1307 | 0.3801 | 250 | 0.1226 |
59
- | 0.1119 | 0.4561 | 300 | 0.1044 |
60
- | 0.1029 | 0.5321 | 350 | 0.1016 |
61
- | 0.1001 | 0.6082 | 400 | 0.1000 |
62
- | 0.0984 | 0.6842 | 450 | 0.1000 |
63
- | 0.0968 | 0.7602 | 500 | 0.0984 |
64
- | 0.0956 | 0.8362 | 550 | 0.0972 |
65
- | 0.0948 | 0.9122 | 600 | 0.0967 |
66
- | 0.0938 | 0.9883 | 650 | 0.0963 |
67
 
68
 
69
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [google/gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.1001
22
 
23
  ## Model description
24
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
+ | 0.6548 | 0.1050 | 50 | 0.2791 |
55
+ | 0.2089 | 0.2100 | 100 | 0.1805 |
56
+ | 0.1682 | 0.3149 | 150 | 0.1557 |
57
+ | 0.1494 | 0.4199 | 200 | 0.1405 |
58
+ | 0.1362 | 0.5249 | 250 | 0.1293 |
59
+ | 0.126 | 0.6299 | 300 | 0.1210 |
60
+ | 0.1109 | 0.7349 | 350 | 0.1042 |
61
+ | 0.1033 | 0.8398 | 400 | 0.1012 |
62
+ | 0.1007 | 0.9448 | 450 | 0.1001 |
 
 
 
 
63
 
64
 
65
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:86881a409712dbbb8d601e854d101b476e6890adbaddc24d24fdc1d5535ca368
3
  size 8967968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecade1651b4b4587e0f1190619cb62e2119567eb658adb42f1d7bf6bcfb41e3d
3
  size 8967968
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7b30eec2d367638f21ed1bde33df68b80b813f9359af8dbead206ca21207817
3
  size 5560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05e21837e8a761ab3dc54b02ea60d7cb10f02fe9cb237fff709bbc9f645d7ca5
3
  size 5560