Hugging Face's logo

BaoTNguyen
/
ncis

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
BaoTNguyen commited on
Commit
eb92ef0
•
1 Parent(s): 930dce0

baotnguyen/ncis

Browse files
Files changed (6) hide show
  1. README.md +11 -11
  2. adapter_config.json +3 -3
  3. adapter_model.safetensors +1 -1
  4. runs/Jul31_17-19-47_8507bc94503f/events.out.tfevents.1722446387.8507bc94503f.82.0 +3 -0
  5. runs/Jul31_17-19-47_8507bc94503f/events.out.tfevents.1722448147.8507bc94503f.82.1 +3 -0
  6. training_args.bin +1 -1
README.md CHANGED
@@ -14,13 +14,12 @@ 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/92tgfr4g)
18
  # ncis
19
 
20
  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.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.1145
23
- - Accuracy: 0.9697
24
 
25
  ## Model description
26
 
@@ -51,19 +50,20 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
- | 0.8268 | 1.0 | 37 | 0.4646 | 0.8030 |
55
- | 0.8255 | 2.0 | 74 | 0.2184 | 0.9040 |
56
- | 0.3172 | 3.0 | 111 | 0.2934 | 0.9192 |
57
- | 0.0518 | 4.0 | 148 | 0.1145 | 0.9697 |
58
- | 0.0066 | 5.0 | 185 | 0.1204 | 0.9697 |
59
- | 0.026 | 6.0 | 222 | 0.1884 | 0.9495 |
60
- | 0.0012 | 7.0 | 259 | 0.2145 | 0.9545 |
 
61
 
62
 
63
  ### Framework versions
64
 
65
  - PEFT 0.12.0
66
- - Transformers 4.43.2
67
  - Pytorch 2.1.2
68
  - Datasets 2.20.0
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
  # ncis
18
 
19
  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.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.1321
22
+ - Accuracy: 0.9596
23
 
24
  ## Model description
25
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | 0.5872 | 1.0 | 37 | 0.3532 | 0.8535 |
54
+ | 0.3902 | 2.0 | 74 | 0.2625 | 0.8737 |
55
+ | 0.169 | 3.0 | 111 | 0.1820 | 0.9495 |
56
+ | 0.1978 | 4.0 | 148 | 0.1502 | 0.9596 |
57
+ | 0.1401 | 5.0 | 185 | 0.1321 | 0.9596 |
58
+ | 0.0175 | 6.0 | 222 | 0.2037 | 0.9394 |
59
+ | 0.0101 | 7.0 | 259 | 0.1677 | 0.9495 |
60
+ | 0.0001 | 8.0 | 296 | 0.1633 | 0.9545 |
61
 
62
 
63
  ### Framework versions
64
 
65
  - PEFT 0.12.0
66
+ - Transformers 4.43.3
67
  - Pytorch 2.1.2
68
  - Datasets 2.20.0
69
  - Tokenizers 0.19.1
adapter_config.json CHANGED
@@ -23,10 +23,10 @@
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
- "v_proj",
27
  "o_proj",
28
- "q_proj",
29
- "k_proj"
 
30
  ],
31
  "task_type": "SEQ_CLS",
32
  "use_dora": false,
 
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
 
26
  "o_proj",
27
+ "v_proj",
28
+ "k_proj",
29
+ "q_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 sha256:1be9b8ad1462b8d33e7d8a7170ac4eb2ef33db144cf09467cf3fe025f8fbce92
3
  size 54593240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f0b7623ed65d0216f0009374b0641ff3186ffbcb90e66f8e9fadd1c53886454
3
  size 54593240
runs/Jul31_17-19-47_8507bc94503f/events.out.tfevents.1722446387.8507bc94503f.82.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb80c7544d2e1ac9d0d93a90c739d05a4cc3409ef1c4a1862df602e699e77930
3
+ size 20672
runs/Jul31_17-19-47_8507bc94503f/events.out.tfevents.1722448147.8507bc94503f.82.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07b09c5e0b9642068f1fac704bf228e5c794f1c617307d71eea96f0a7454d455
3
+ size 411
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75cfa01ba8e272e07b160a97927ee4253900b314ede7ae7a139cf60917fa564d
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f10b2da25e483b21a07f0f2387e349fb61c153113e54b1dc722d3f324a5cce80
3
  size 5176