Hugging Face's logo

BaoTNguyen
/
ncis

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
BaoTNguyen commited on
Commit
06a6308
•
1 Parent(s): 2548c2e

baotnguyen/ncis

Browse files
Files changed (7) hide show
  1. README.md +14 -12
  2. adapter_config.json +3 -3
  3. adapter_model.safetensors +1 -1
  4. runs/Jul23_17-40-44_8c40040baa47/events.out.tfevents.1721756445.8c40040baa47.34.0 +3 -0
  5. runs/Jul23_17-47-51_8c40040baa47/events.out.tfevents.1721756871.8c40040baa47.34.1 +3 -0
  6. runs/Jul23_17-47-51_8c40040baa47/events.out.tfevents.1721757827.8c40040baa47.34.2 +3 -0
  7. training_args.bin +2 -2
README.md CHANGED
@@ -14,14 +14,14 @@ model-index:
14
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
  should probably proofread and complete it, then remove this comment. -->
16
 
17
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/phdatdt/Fine%20tuning%20mistral%207B/runs/pjl3k4ui)
18
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/phdatdt/Fine%20tuning%20mistral%207B/runs/x9rk8c6l)
19
  # ncis
20
 
21
  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.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.7879
24
- - Accuracy: 0.8376
25
 
26
  ## Model description
27
 
@@ -52,18 +52,20 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
55
- | 0.4594 | 1.0 | 19 | 1.8113 | 0.7265 |
56
- | 0.0891 | 2.0 | 38 | 1.3579 | 0.7778 |
57
- | 0.0006 | 3.0 | 57 | 0.7879 | 0.8376 |
58
- | 0.0001 | 4.0 | 76 | 3.2639 | 0.6496 |
59
- | 0.0 | 5.0 | 95 | 2.6519 | 0.7179 |
60
- | 0.0 | 6.0 | 114 | 2.5846 | 0.7179 |
 
 
61
 
62
 
63
  ### Framework versions
64
 
65
  - PEFT 0.11.1
66
- - Transformers 4.42.4
67
  - Pytorch 2.1.2
68
- - Datasets 2.16.0
69
  - Tokenizers 0.19.1
 
14
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
  should probably proofread and complete it, then remove this comment. -->
16
 
17
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/phdatdt/Fine%20tuning%20mistral%207B/runs/oq39mcox)
18
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/phdatdt/Fine%20tuning%20mistral%207B/runs/nvldh0a4)
19
  # ncis
20
 
21
  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.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.8580
24
+ - Accuracy: 0.8632
25
 
26
  ## Model description
27
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
55
+ | 0.343 | 1.0 | 19 | 2.4278 | 0.7094 |
56
+ | 0.0705 | 2.0 | 38 | 0.8580 | 0.8632 |
57
+ | 0.0314 | 3.0 | 57 | 1.6827 | 0.7949 |
58
+ | 0.0 | 4.0 | 76 | 1.7959 | 0.7949 |
59
+ | 0.0 | 5.0 | 95 | 1.8000 | 0.7949 |
60
+ | 0.0 | 6.0 | 114 | 1.7949 | 0.7949 |
61
+ | 0.0 | 7.0 | 133 | 1.7876 | 0.7949 |
62
+ | 0.0 | 8.0 | 152 | 1.7850 | 0.7949 |
63
 
64
 
65
  ### Framework versions
66
 
67
  - PEFT 0.11.1
68
+ - Transformers 4.43.1
69
  - Pytorch 2.1.2
70
+ - Datasets 2.20.0
71
  - Tokenizers 0.19.1
adapter_config.json CHANGED
@@ -23,10 +23,10 @@
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
- "q_proj",
27
- "o_proj",
28
  "v_proj",
29
- "k_proj"
 
 
30
  ],
31
  "task_type": "SEQ_CLS",
32
  "use_dora": false,
 
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
 
 
26
  "v_proj",
27
+ "k_proj",
28
+ "q_proj",
29
+ "o_proj"
30
  ],
31
  "task_type": "SEQ_CLS",
32
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:180ccb4a99ecf4458183ac60294d3201c52dcf42b0f84e7eab3396aa1916fdc0
3
  size 54593240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90bd1fea156c0fe7f259b1d0ed34a78a85d1d6b958cb36af6d6c85572b0ffa04
3
  size 54593240
runs/Jul23_17-40-44_8c40040baa47/events.out.tfevents.1721756445.8c40040baa47.34.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8495b9c73bb7b3e9fda9d454c8e4f5059c54f71816b4d3ce311a3a8b7b130c5
3
+ size 5404
runs/Jul23_17-47-51_8c40040baa47/events.out.tfevents.1721756871.8c40040baa47.34.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b6090ded67942a28c789715305df77e8b178a1c08d5ddbd9b69f5b13d888f1b
3
+ size 10384
runs/Jul23_17-47-51_8c40040baa47/events.out.tfevents.1721757827.8c40040baa47.34.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19245ae8e240f48bb2b3e2a07308a7688a238e7ab779d2b866aa80403bf33409
3
+ size 411
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad6b44d882eead592af580018bfa24ca9b8a3359cb8a4486457b4c12daabb67e
3
- size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73c1f8c6b53b38f446892de67dcb6532145fddf3d608cc141c491610f191db99
3
+ size 5176