Hugging Face's logo

BaoTNguyen
/
ncis

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
BaoTNguyen commited on
Commit
317e34d
•
1 Parent(s): 76b122d

baotnguyen/ncis

Browse files
Files changed (5) hide show
  1. README.md +10 -10
  2. adapter_model.safetensors +1 -1
  3. runs/Jul22_18-46-19_90cc069fc707/events.out.tfevents.1721673980.90cc069fc707.34.12 +3 -0
  4. runs/Jul22_18-46-19_90cc069fc707/events.out.tfevents.1721674573.90cc069fc707.34.13 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -20,12 +20,13 @@ should probably proofread and complete it, then remove this comment. -->
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/ujkstyig)
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/4xqrob1d)
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
  # ncis
24
 
25
  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.
26
  It achieves the following results on the evaluation set:
27
- - Loss: 0.3363
28
- - Accuracy: 0.9231
29
 
30
  ## Model description
31
 
@@ -44,24 +45,23 @@ More information needed
44
  ### Training hyperparameters
45
 
46
  The following hyperparameters were used during training:
47
- - learning_rate: 7.5e-05
48
  - train_batch_size: 16
49
  - eval_batch_size: 16
50
  - seed: 42
51
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
  - lr_scheduler_type: linear
53
- - num_epochs: 8
54
 
55
  ### Training results
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
58
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
59
- | 0.5027 | 1.0 | 19 | 1.7724 | 0.6496 |
60
- | 0.0243 | 2.0 | 38 | 1.3924 | 0.7607 |
61
- | 0.0 | 3.0 | 57 | 0.3363 | 0.9231 |
62
- | 0.0 | 4.0 | 76 | 3.2341 | 0.6325 |
63
- | 0.0 | 5.0 | 95 | 3.7350 | 0.5726 |
64
- | 0.0 | 6.0 | 114 | 3.7031 | 0.5726 |
65
 
66
 
67
  ### Framework versions
 
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/ujkstyig)
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/4xqrob1d)
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
  # ncis
25
 
26
  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.
27
  It achieves the following results on the evaluation set:
28
+ - Loss: 0.8589
29
+ - Accuracy: 0.8205
30
 
31
  ## Model description
32
 
 
45
  ### Training hyperparameters
46
 
47
  The following hyperparameters were used during training:
48
+ - learning_rate: 0.0001
49
  - train_batch_size: 16
50
  - eval_batch_size: 16
51
  - seed: 42
52
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
  - lr_scheduler_type: linear
54
+ - num_epochs: 6
55
 
56
  ### Training results
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
59
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
60
+ | 0.5641 | 1.0 | 19 | 1.7375 | 0.6496 |
61
+ | 0.0034 | 2.0 | 38 | 0.8589 | 0.8205 |
62
+ | 0.0 | 3.0 | 57 | 1.2763 | 0.7692 |
63
+ | 0.0 | 4.0 | 76 | 1.3331 | 0.7692 |
64
+ | 0.0 | 5.0 | 95 | 1.3380 | 0.7692 |
 
65
 
66
 
67
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46137ea6e37505cac166e695031a21408b9713fa7a73783a938b5a9364438d4f
3
  size 54593240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7585b86fd9ab388962672fa7edfe491525ec813c7ebf0b8f26882dc9335187f
3
  size 54593240
runs/Jul22_18-46-19_90cc069fc707/events.out.tfevents.1721673980.90cc069fc707.34.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1d635a0dac4ac533f37e93695db9bdb3af4a57b81f70349116aba3d07d7bfcb
3
+ size 8490
runs/Jul22_18-46-19_90cc069fc707/events.out.tfevents.1721674573.90cc069fc707.34.13 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01330b564ed4e52dc2b86cc9faca99eccd3f07a303dcfe48cb657cab6befa976
3
+ size 405
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7040d3a277e60cb9c8009355eca52383eb2249b75284662fc63e610091a0f887
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffcb371fc1749a568224e775b91905372fedbc0aca04c489537e2de8f4a173cb
3
  size 5112