Hugging Face's logo

jaki-1
/
shawgpt-ft

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
jaki-1 commited on
Commit
e3bc4fc
•
1 Parent(s): 387698f

jaki-1/ATS-ft

Browse files
Files changed (3) hide show
  1. README.md +16 -16
  2. adapter_model.safetensors +1 -1
  3. training_args.bin +2 -2
README.md CHANGED
@@ -1,9 +1,9 @@
1
  ---
2
- license: apache-2.0
3
  library_name: peft
 
4
  tags:
5
  - generated_from_trainer
6
- base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
7
  model-index:
8
  - name: shawgpt-ft
9
  results: []
@@ -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 the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 2.7929
20
 
21
  ## Model description
22
 
@@ -51,22 +51,22 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
- | 3.921 | 0.9892 | 69 | 3.1268 |
55
- | 2.7734 | 1.9928 | 139 | 2.7793 |
56
- | 2.5538 | 2.9964 | 209 | 2.7026 |
57
- | 2.4648 | 4.0 | 279 | 2.7008 |
58
- | 2.4164 | 4.9892 | 348 | 2.7113 |
59
- | 2.3266 | 5.9928 | 418 | 2.6972 |
60
- | 2.2489 | 6.9964 | 488 | 2.7195 |
61
- | 2.1813 | 8.0 | 558 | 2.7573 |
62
- | 2.2002 | 8.9892 | 627 | 2.7826 |
63
- | 2.0955 | 9.8925 | 690 | 2.7929 |
64
 
65
 
66
  ### Framework versions
67
 
68
- - PEFT 0.10.0
69
- - Transformers 4.40.1
70
  - Pytorch 2.1.0+cu121
71
- - Datasets 2.19.0
72
  - Tokenizers 0.19.1
 
1
  ---
2
+ base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
3
  library_name: peft
4
+ license: apache-2.0
5
  tags:
6
  - generated_from_trainer
 
7
  model-index:
8
  - name: shawgpt-ft
9
  results: []
 
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 the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.7806
20
 
21
  ## Model description
22
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
+ | 1.1706 | 0.9919 | 92 | 1.0061 |
55
+ | 0.9987 | 1.9946 | 185 | 0.9524 |
56
+ | 0.9563 | 2.9973 | 278 | 0.9146 |
57
+ | 0.9325 | 3.9919 | 368 | 0.8862 |
58
+ | 0.9031 | 4.9919 | 460 | 0.8586 |
59
+ | 0.8689 | 5.9946 | 553 | 0.8344 |
60
+ | 0.8449 | 6.9973 | 646 | 0.8135 |
61
+ | 0.8345 | 7.9919 | 736 | 0.7974 |
62
+ | 0.8167 | 8.9919 | 828 | 0.7855 |
63
+ | 0.7919 | 9.9838 | 920 | 0.7806 |
64
 
65
 
66
  ### Framework versions
67
 
68
+ - PEFT 0.11.1
69
+ - Transformers 4.41.2
70
  - Pytorch 2.1.0+cu121
71
+ - Datasets 2.20.0
72
  - Tokenizers 0.19.1
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b22f0234e828eda519a2feb165a1b5a54cfba85c92d7b973835564fd9215653e
3
  size 8397056
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f84f290c43ce00f9afccc405ec0edc3f6bc095c01e318625fc504fcd3e6c07e3
3
  size 8397056
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a86abca39f7d9147cf0d7a0e7b695f4c012b7073c976153eb12f682533d4125e
3
- size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfe2444613968dc9b28bba9708f16b6133476441eb626ce575474908c9b39911
3
+ size 5112