Hugging Face's logo

irenewds
/
shawgpt-ft

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
irenewds commited on
Commit
ec1202f
·
verified ·
1 Parent(s): 784b5e4

irenewds/shawgpt-ft

Browse files
Files changed (4) hide show
  1. README.md +16 -16
  2. runs/Oct24_19-20-12_1f4e1c060daf/events.out.tfevents.1729797618.1f4e1c060daf.3103.6 +3 -0
  3. runs/Oct24_19-20-27_1f4e1c060daf/events.out.tfevents.1729797628.1f4e1c060daf.3103.7 +3 -0
  4. training_args.bin +1 -1
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: 1.4675
20
 
21
  ## Model description
22
 
@@ -35,7 +35,7 @@ More information needed
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
- - learning_rate: 0.00015
39
  - train_batch_size: 4
40
  - eval_batch_size: 4
41
  - seed: 42
@@ -51,20 +51,20 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-------:|:----:|:---------------:|
54
- | 4.6055 | 0.9231 | 3 | 4.0311 |
55
- | 4.1731 | 1.8462 | 6 | 3.6064 |
56
- | 3.6829 | 2.7692 | 9 | 3.2058 |
57
- | 2.4342 | 4.0 | 13 | 2.7664 |
58
- | 2.8888 | 4.9231 | 16 | 2.4957 |
59
- | 2.5378 | 5.8462 | 19 | 2.2613 |
60
- | 2.2353 | 6.7692 | 22 | 2.0239 |
61
- | 1.4921 | 8.0 | 26 | 1.8148 |
62
- | 1.8263 | 8.9231 | 29 | 1.7127 |
63
- | 1.6847 | 9.8462 | 32 | 1.6285 |
64
- | 1.6188 | 10.7692 | 35 | 1.5605 |
65
- | 1.13 | 12.0 | 39 | 1.4999 |
66
- | 1.488 | 12.9231 | 42 | 1.4764 |
67
- | 1.2276 | 13.8462 | 45 | 1.4675 |
68
 
69
 
70
  ### 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: 1.3630
20
 
21
  ## Model description
22
 
 
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
+ - learning_rate: 0.0002
39
  - train_batch_size: 4
40
  - eval_batch_size: 4
41
  - seed: 42
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-------:|:----:|:---------------:|
54
+ | 4.5929 | 0.9231 | 3 | 3.9701 |
55
+ | 4.0424 | 1.8462 | 6 | 3.4314 |
56
+ | 3.4326 | 2.7692 | 9 | 2.9386 |
57
+ | 2.1966 | 4.0 | 13 | 2.4495 |
58
+ | 2.5197 | 4.9231 | 16 | 2.1497 |
59
+ | 2.0957 | 5.8462 | 19 | 1.8726 |
60
+ | 1.8112 | 6.7692 | 22 | 1.7120 |
61
+ | 1.2405 | 8.0 | 26 | 1.5321 |
62
+ | 1.4946 | 8.9231 | 29 | 1.4462 |
63
+ | 1.3901 | 9.8462 | 32 | 1.4060 |
64
+ | 1.3781 | 10.7692 | 35 | 1.3861 |
65
+ | 0.9873 | 12.0 | 39 | 1.3718 |
66
+ | 1.3301 | 12.9231 | 42 | 1.3656 |
67
+ | 1.1055 | 13.8462 | 45 | 1.3630 |
68
 
69
 
70
  ### Framework versions
runs/Oct24_19-20-12_1f4e1c060daf/events.out.tfevents.1729797618.1f4e1c060daf.3103.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:654c73eef1e15f6158be30b65d9d84f88930b18bbf2f42d4568a05e72f1f74b2
3
+ size 4184
runs/Oct24_19-20-27_1f4e1c060daf/events.out.tfevents.1729797628.1f4e1c060daf.3103.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8a026ada6fdf7963a9492b6b3bf95a7c89b670666485d5446a5b2e0a0651d1c
3
+ size 12552
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:023476b94d79af97ff9f39f01d7facdda61b8aaaaff1a07986c51bf0f5a941a0
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c99249e625a9cbea47a8357a4c23c8d42a0c77e17f4dcbd3df88a0e58da6dfe8
3
  size 5176