Hugging Face's logo

BaoTNguyen
/
ncis

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
BaoTNguyen commited on
Commit
1ec9767
•
1 Parent(s): f4160ac

baotnguyen/ncis

Browse files
Files changed (5) hide show
  1. README.md +9 -9
  2. adapter_model.safetensors +1 -1
  3. runs/Jul22_20-15-05_90cc069fc707/events.out.tfevents.1721679306.90cc069fc707.34.16 +3 -0
  4. runs/Jul22_20-15-05_90cc069fc707/events.out.tfevents.1721680014.90cc069fc707.34.17 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -22,12 +22,13 @@ should probably proofread and complete it, then remove this comment. -->
22
  [<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/errke2dy)
23
  [<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/ljcim1zv)
24
  [<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/0115kz44)
 
25
  # ncis
26
 
27
  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.
28
  It achieves the following results on the evaluation set:
29
- - Loss: 0.3313
30
- - Accuracy: 0.9060
31
 
32
  ## Model description
33
 
@@ -58,13 +59,12 @@ The following hyperparameters were used during training:
58
 
59
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
60
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
61
- | 0.7319 | 1.0 | 19 | 1.0418 | 0.7350 |
62
- | 0.0004 | 2.0 | 38 | 0.9800 | 0.7350 |
63
- | 0.0003 | 3.0 | 57 | 5.5397 | 0.4615 |
64
- | 0.0387 | 4.0 | 76 | 0.3313 | 0.9060 |
65
- | 0.0001 | 5.0 | 95 | 2.5728 | 0.6752 |
66
- | 0.0 | 6.0 | 114 | 5.2674 | 0.4957 |
67
- | 0.0 | 7.0 | 133 | 5.1163 | 0.4957 |
68
 
69
 
70
  ### Framework versions
 
22
  [<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/errke2dy)
23
  [<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/ljcim1zv)
24
  [<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/0115kz44)
25
+ [<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/cj8xou9q)
26
  # ncis
27
 
28
  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.
29
  It achieves the following results on the evaluation set:
30
+ - Loss: 0.7880
31
+ - Accuracy: 0.8376
32
 
33
  ## Model description
34
 
 
59
 
60
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
61
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
62
+ | 0.4594 | 1.0 | 19 | 1.8115 | 0.7265 |
63
+ | 0.0891 | 2.0 | 38 | 1.3580 | 0.7778 |
64
+ | 0.0006 | 3.0 | 57 | 0.7880 | 0.8376 |
65
+ | 0.0001 | 4.0 | 76 | 3.2674 | 0.6496 |
66
+ | 0.0 | 5.0 | 95 | 2.6575 | 0.7179 |
67
+ | 0.0 | 6.0 | 114 | 2.5903 | 0.7179 |
 
68
 
69
 
70
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:590b82bd03fd2f2926c95006569c87f9a9ffdd3ea62407653f04fb3d42e1c06d
3
  size 54593240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f99e98f81c452c9ab831eb896b61b0461158bef9f71452f4bc9e9438389a345d
3
  size 54593240
runs/Jul22_20-15-05_90cc069fc707/events.out.tfevents.1721679306.90cc069fc707.34.16 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5946e782a208639b42b23560ab03fd73fe361a6390e53b76699714e574846ac
3
+ size 9015
runs/Jul22_20-15-05_90cc069fc707/events.out.tfevents.1721680014.90cc069fc707.34.17 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abdbd61dc7f3e487748f6277c88df4c423021a805717167b987a9975e2a12cc2
3
+ size 405
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2432b301b8be89eda557cbcdb47255b2e17fdc233f3479491e35f3508b8aeddf
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e79768fc259f1de54d417434c673d3672bacdd3c82ed75fbabfd9697c2874378
3
  size 5112