irenewds commited on
Commit
bf8b318
·
verified ·
1 Parent(s): ebba076

irenewds/shawgpt-ft

Browse files
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.2-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 1.8313
20
 
21
  ## Model description
22
 
@@ -51,21 +51,21 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-------:|:----:|:---------------:|
54
- | 4.6204 | 0.9231 | 3 | 4.1049 |
55
- | 4.3268 | 1.8462 | 6 | 3.8196 |
56
  | 3.985 | 2.7692 | 9 | 3.5435 |
57
  | 2.7386 | 4.0 | 13 | 3.1929 |
58
- | 3.3701 | 4.9231 | 16 | 2.9583 |
59
  | 3.0903 | 5.8462 | 19 | 2.7575 |
60
- | 2.8577 | 6.7692 | 22 | 2.5755 |
61
- | 1.9912 | 8.0 | 26 | 2.3843 |
62
- | 2.4753 | 8.9231 | 29 | 2.2330 |
63
- | 2.2774 | 9.8462 | 32 | 2.1009 |
64
- | 2.1576 | 10.7692 | 35 | 2.0061 |
65
- | 1.518 | 12.0 | 39 | 1.9157 |
66
- | 1.9689 | 12.9231 | 42 | 1.8699 |
67
- | 1.9021 | 13.8462 | 45 | 1.8422 |
68
- | 1.4411 | 14.7692 | 48 | 1.8313 |
69
 
70
 
71
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.2-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 1.8311
20
 
21
  ## Model description
22
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-------:|:----:|:---------------:|
54
+ | 4.6205 | 0.9231 | 3 | 4.1049 |
55
+ | 4.3268 | 1.8462 | 6 | 3.8197 |
56
  | 3.985 | 2.7692 | 9 | 3.5435 |
57
  | 2.7386 | 4.0 | 13 | 3.1929 |
58
+ | 3.3702 | 4.9231 | 16 | 2.9583 |
59
  | 3.0903 | 5.8462 | 19 | 2.7575 |
60
+ | 2.8575 | 6.7692 | 22 | 2.5753 |
61
+ | 1.9912 | 8.0 | 26 | 2.3841 |
62
+ | 2.4751 | 8.9231 | 29 | 2.2327 |
63
+ | 2.2772 | 9.8462 | 32 | 2.1008 |
64
+ | 2.1575 | 10.7692 | 35 | 2.0060 |
65
+ | 1.5179 | 12.0 | 39 | 1.9155 |
66
+ | 1.9687 | 12.9231 | 42 | 1.8698 |
67
+ | 1.902 | 13.8462 | 45 | 1.8420 |
68
+ | 1.4411 | 14.7692 | 48 | 1.8311 |
69
 
70
 
71
  ### Framework versions
runs/Oct24_20-24-25_1f4e1c060daf/events.out.tfevents.1729801468.1f4e1c060daf.28754.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:936f9b1181f904e23c150af10068def9ec78cfdb28bb2a4acc05c3a70329c2e8
3
+ size 4184
runs/Oct24_20-24-35_1f4e1c060daf/events.out.tfevents.1729801476.1f4e1c060daf.28754.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b921a6a6f4dfedb8e2d2f3c691578a53044a1e6dc008aec95c99770f161431c
3
+ size 13025
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:462d61a5b7cd5488240d17338187dd11a1d5255f45d6424999e6ae1ad7f34a09
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53fe9f760a52d0ef0bbea7db17b87239fea540e4f82f4e0a554529c88776e11c
3
  size 5176