Hugging Face's logo

BaoTNguyen
/
ncis

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
BaoTNguyen commited on
Commit
b30364b
•
1 Parent(s): d6508d4

baotnguyen/ncis

Browse files
Files changed (5) hide show
  1. README.md +10 -9
  2. adapter_model.safetensors +1 -1
  3. runs/Jul24_20-12-08_09a71601efe2/events.out.tfevents.1721851928.09a71601efe2.34.7 +3 -0
  4. runs/Jul24_20-12-08_09a71601efe2/events.out.tfevents.1721852155.09a71601efe2.34.8 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -18,11 +18,12 @@ should probably proofread and complete it, then remove this comment. -->
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/3ct7kp9n)
19
  [<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/w9jgqdxj)
20
  [<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/9065m82c)
 
21
  # ncis
22
 
23
  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.
24
  It achieves the following results on the evaluation set:
25
- - Loss: 0.0117
26
  - Accuracy: 1.0
27
 
28
  ## Model description
@@ -54,14 +55,14 @@ The following hyperparameters were used during training:
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
56
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
57
- | No log | 1.0 | 5 | 0.4909 | 0.76 |
58
- | No log | 2.0 | 10 | 0.1935 | 0.88 |
59
- | 0.4954 | 3.0 | 15 | 0.1898 | 0.88 |
60
- | 0.4954 | 4.0 | 20 | 0.0117 | 1.0 |
61
- | 0.4954 | 5.0 | 25 | 0.1394 | 0.96 |
62
- | 0.0039 | 6.0 | 30 | 0.9255 | 0.88 |
63
- | 0.0039 | 7.0 | 35 | 0.3563 | 0.88 |
64
- | 0.0039 | 8.0 | 40 | 0.2003 | 0.96 |
65
 
66
 
67
  ### Framework versions
 
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/3ct7kp9n)
19
  [<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/w9jgqdxj)
20
  [<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/9065m82c)
21
+ [<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/gpbdho1v)
22
  # ncis
23
 
24
  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.
25
  It achieves the following results on the evaluation set:
26
+ - Loss: 0.0000
27
  - Accuracy: 1.0
28
 
29
  ## Model description
 
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
57
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
58
+ | 1.3885 | 1.0 | 5 | 0.0599 | 1.0 |
59
+ | 0.3902 | 2.0 | 10 | 0.0331 | 0.96 |
60
+ | 0.0039 | 3.0 | 15 | 0.0008 | 1.0 |
61
+ | 0.0014 | 4.0 | 20 | 0.0150 | 1.0 |
62
+ | 0.0 | 5.0 | 25 | 0.2502 | 0.96 |
63
+ | 0.0003 | 6.0 | 30 | 0.0001 | 1.0 |
64
+ | 0.0 | 7.0 | 35 | 0.0000 | 1.0 |
65
+ | 0.0 | 8.0 | 40 | 0.0000 | 1.0 |
66
 
67
 
68
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a790d6592682b69de9c66b5fdebd84695b7e898ef7bd41139b62b62ddf33057
3
  size 54593240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:749fbd36872b275f608df5943e51eab86a116f6816d7b06fb9c4fdd8ffef83e2
3
  size 54593240
runs/Jul24_20-12-08_09a71601efe2/events.out.tfevents.1721851928.09a71601efe2.34.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cfcc5f38b900e8370f66642990cd822fe954770d703db15fa1ebde949412b4d
3
+ size 9943
runs/Jul24_20-12-08_09a71601efe2/events.out.tfevents.1721852155.09a71601efe2.34.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3f8502b70edf9aa306d00a8784ceb7d98311b6763f038599102f12251f346e5
3
+ size 405
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5de407abc38869591baff8bed5e53f9e849a045c163327013778e66c29b0f6c
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff0661baef9d588c846b9bd359c7253093451b9677e22b0cf61e6fcd42b2d2d9
3
  size 5176