Hugging Face's logo

alexlawtengyi
/
model_te

Text Generation
Transformers
TensorBoard
Safetensors
llama
Generated from Trainer
trl
sft
text-generation-inference
Inference Endpoints
8-bit precision
bitsandbytes
Model card Files Metrics Community
alexlawtengyi commited on
Commit
d0ef6b6
•
1 Parent(s): 229e5ea

End of training

Browse files
Files changed (3) hide show
  1. README.md +9 -9
  2. runs/Oct02_03-56-33_e317c68d82b2/events.out.tfevents.1727841406.e317c68d82b2.228.2 +2 -2
  3. runs/Oct02_03-56-33_e317c68d82b2/events.out.tfevents.1727841607.e317c68d82b2.228.3 +3 -0
README.md CHANGED
@@ -7,19 +7,19 @@ tags:
7
  metrics:
8
  - matthews_correlation
9
  model-index:
10
- - name: distilbert-base-uncased-finetuned-cola
11
  results: []
12
  ---
13
 
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
- # distilbert-base-uncased-finetuned-cola
18
 
19
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.6369
22
- - Matthews Correlation: 0.5207
23
 
24
  ## Model description
25
 
@@ -50,11 +50,11 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
53
- | 0.5345 | 1.0 | 535 | 0.4586 | 0.4388 |
54
- | 0.3657 | 2.0 | 1070 | 0.4648 | 0.5137 |
55
- | 0.2511 | 3.0 | 1605 | 0.6369 | 0.5207 |
56
- | 0.183 | 4.0 | 2140 | 0.8016 | 0.5153 |
57
- | 0.1355 | 5.0 | 2675 | 0.8438 | 0.5158 |
58
 
59
 
60
  ### Framework versions
 
7
  metrics:
8
  - matthews_correlation
9
  model-index:
10
+ - name: model_te
11
  results: []
12
  ---
13
 
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
+ # model_te
18
 
19
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 1.0733
22
+ - Matthews Correlation: 0.5324
23
 
24
  ## Model description
25
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
53
+ | 0.1729 | 1.0 | 535 | 0.6953 | 0.5007 |
54
+ | 0.1152 | 2.0 | 1070 | 0.9441 | 0.5200 |
55
+ | 0.0809 | 3.0 | 1605 | 0.9402 | 0.5150 |
56
+ | 0.1009 | 4.0 | 2140 | 1.0245 | 0.5297 |
57
+ | 0.0797 | 5.0 | 2675 | 1.0733 | 0.5324 |
58
 
59
 
60
  ### Framework versions
runs/Oct02_03-56-33_e317c68d82b2/events.out.tfevents.1727841406.e317c68d82b2.228.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f76cd4ca14a3d981f23b6506125d042ea17dc3be54836b1988c2b24129f8e4f4
3
- size 7738
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0586abdc9426024efe074356266c8087f9ea34e1c7b3802017e714b2bd27715a
3
+ size 8092
runs/Oct02_03-56-33_e317c68d82b2/events.out.tfevents.1727841607.e317c68d82b2.228.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b6248adbb59e2fc5b35d572a199575cbae55bfd7057252c3ab4f79a7458cbcc
3
+ size 423