Hugging Face's logo

thrunlab
/
Mistral_Sparse_refined_web_graceful_reg_90p_2024-03-14

Text Generation
Transformers
Safetensors
sparse_mistral
Generated from Trainer
custom_code
Model card Files Community
lukeleeai commited on
Commit
dd481c5
·
verified ·
1 Parent(s): 8dd4bc3

End of training

Browse files
Files changed (5) hide show
  1. README.md +9 -9
  2. config.json +2 -2
  3. model-00001-of-00003.safetensors +1 -1
  4. model-00002-of-00003.safetensors +1 -1
  5. model-00003-of-00003.safetensors +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 3.2117
19
 
20
  ## Model description
21
 
@@ -51,14 +51,14 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-----:|:----:|:---------------:|
54
- | 3.6973 | 0.01 | 25 | 2.3992 |
55
- | 3.6504 | 0.02 | 50 | 2.3855 |
56
- | 3.6737 | 0.02 | 75 | 2.3872 |
57
- | 3.5868 | 0.03 | 100 | 2.4532 |
58
- | 3.5604 | 0.04 | 125 | 2.4999 |
59
- | 3.4312 | 0.05 | 150 | 2.5201 |
60
- | 3.3355 | 0.06 | 175 | 2.5216 |
61
- | 3.3825 | 0.06 | 200 | 2.5236 |
62
 
63
 
64
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 3.1992
19
 
20
  ## Model description
21
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-----:|:----:|:---------------:|
54
+ | 3.6978 | 0.01 | 25 | 2.3995 |
55
+ | 3.651 | 0.02 | 50 | 2.3858 |
56
+ | 3.6755 | 0.02 | 75 | 2.3870 |
57
+ | 3.5904 | 0.03 | 100 | 2.4495 |
58
+ | 3.5636 | 0.04 | 125 | 2.4981 |
59
+ | 3.4337 | 0.05 | 150 | 2.5197 |
60
+ | 3.3356 | 0.06 | 175 | 2.5215 |
61
+ | 3.3829 | 0.06 | 200 | 2.5234 |
62
 
63
 
64
  ### Framework versions
config.json CHANGED
@@ -29,7 +29,7 @@
29
  0.10732196271419525,
30
  0.12738214433193207,
31
  0.1414242684841156,
32
- 0.15346036851406097,
33
  0.16349045932292938,
34
  0.1675025075674057,
35
  0.1675025075674057,
@@ -37,7 +37,7 @@
37
  0.1735205501317978,
38
  0.17552657425403595,
39
  0.1775325983762741,
40
- 0.18756268918514252,
41
  0.1935807317495346,
42
  0.19759276509284973,
43
  0.21364091336727142,
 
29
  0.10732196271419525,
30
  0.12738214433193207,
31
  0.1414242684841156,
32
+ 0.15546639263629913,
33
  0.16349045932292938,
34
  0.1675025075674057,
35
  0.1675025075674057,
 
37
  0.1735205501317978,
38
  0.17552657425403595,
39
  0.1775325983762741,
40
+ 0.18956869840621948,
41
  0.1935807317495346,
42
  0.19759276509284973,
43
  0.21364091336727142,
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:824e1239d9fae01a0d92076a96352399912e41d2ab3770881a2165c5004dae3e
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:266a466bbb9e54f96f47eef2c06d2735b44e8aa8ec13e8edec7a83439f5efa72
3
  size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a14f497d6e09056c31f8d91a735b9025435eab785f3842a46e2377147881a34
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ef52d7f7c0a3c78947311fed9515046829e339d6ecd46f23fd3eacf34148535
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f7814c4a55aa339eeed03a589db54cc81730b2e3484eebd1155b908483efea73
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a912fda040ea3a959e05fee84c57ca990ed702145ce81691ec25877ce5680644
3
  size 4540516344