Hugging Face's logo

stefanj0
/
t5gemma-math-corrector

PEFT
Safetensors
Transformers
lora
Model card Files
xet
 Community
stefanj0 commited on
Commit
f405c7c
·
verified ·
1 Parent(s): cf0eea4

Model save

Browse files
Files changed (2) hide show
  1. README.md +5 -5
  2. adapter_model.safetensors +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/t5gemma-s-s-ul2-it](https://huggingface.co/google/t5gemma-s-s-ul2-it) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 7.1757
22
 
23
  ## Model description
24
 
@@ -53,10 +53,10 @@ The following hyperparameters were used during training:
53
 
54
  | Training Loss | Epoch | Step | Validation Loss |
55
  |:-------------:|:------:|:----:|:---------------:|
56
- | 0.0108 | 0.6774 | 200 | 4.4378 |
57
- | 0.0034 | 1.3522 | 400 | 7.0770 |
58
- | 0.002 | 2.0271 | 600 | 7.6245 |
59
- | 0.0011 | 2.7045 | 800 | 7.1757 |
60
 
61
 
62
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [google/t5gemma-s-s-ul2-it](https://huggingface.co/google/t5gemma-s-s-ul2-it) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 3.8249
22
 
23
  ## Model description
24
 
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss |
55
  |:-------------:|:------:|:----:|:---------------:|
56
+ | 0.0085 | 0.6415 | 200 | 0.6018 |
57
+ | 0.0029 | 1.2823 | 400 | 1.9704 |
58
+ | 0.001 | 1.9238 | 600 | 3.8351 |
59
+ | 0.0005 | 2.5646 | 800 | 3.8249 |
60
 
61
 
62
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f7a164557eb74ce102f82cd4df90a332f6f0dfbadf4438231beee9da629f888f
3
  size 8297288
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb7edc022a38beb145ffb51c73bf9826a63972fa7eb7866f4c9659074c1a8c43
3
  size 8297288