Hugging Face's logo

lenatr99
/
lora_fine_tuned_copa

PEFT
Safetensors
Generated from Trainer
Model card Files Community
lenatr99 commited on
Commit
c18f86a
·
verified ·
1 Parent(s): 94a0699

lora_fine_tuned_copa

Browse files
Files changed (5) hide show
  1. README.md +12 -12
  2. adapter_config.json +2 -2
  3. adapter_model.safetensors +1 -1
  4. tokenizer.json +1 -6
  5. training_args.bin +1 -1
README.md CHANGED
@@ -19,9 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.6931
23
- - Accuracy: 0.5
24
- - F1: 0.4926
25
 
26
  ## Model description
27
 
@@ -40,7 +40,7 @@ More information needed
40
  ### Training hyperparameters
41
 
42
  The following hyperparameters were used during training:
43
- - learning_rate: 0.003
44
  - train_batch_size: 8
45
  - eval_batch_size: 8
46
  - seed: 42
@@ -52,14 +52,14 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
54
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
55
- | 0.7084 | 1.0 | 50 | 0.6932 | 0.49 | 0.4905 |
56
- | 0.6986 | 2.0 | 100 | 0.6931 | 0.61 | 0.6096 |
57
- | 0.6975 | 3.0 | 150 | 0.6931 | 0.51 | 0.4904 |
58
- | 0.6953 | 4.0 | 200 | 0.6931 | 0.54 | 0.5332 |
59
- | 0.7156 | 5.0 | 250 | 0.6931 | 0.54 | 0.5195 |
60
- | 0.7023 | 6.0 | 300 | 0.6931 | 0.5 | 0.4971 |
61
- | 0.6998 | 7.0 | 350 | 0.6931 | 0.47 | 0.4711 |
62
- | 0.7122 | 8.0 | 400 | 0.6931 | 0.5 | 0.4926 |
63
 
64
 
65
  ### Framework versions
 
19
 
20
  This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.6918
23
+ - Accuracy: 0.46
24
+ - F1: 0.4570
25
 
26
  ## Model description
27
 
 
40
  ### Training hyperparameters
41
 
42
  The following hyperparameters were used during training:
43
+ - learning_rate: 2e-05
44
  - train_batch_size: 8
45
  - eval_batch_size: 8
46
  - seed: 42
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
54
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
55
+ | 0.7088 | 1.0 | 50 | 0.6921 | 0.48 | 0.48 |
56
+ | 0.7024 | 2.0 | 100 | 0.6922 | 0.49 | 0.4894 |
57
+ | 0.6993 | 3.0 | 150 | 0.6921 | 0.46 | 0.4587 |
58
+ | 0.7005 | 4.0 | 200 | 0.6920 | 0.48 | 0.4788 |
59
+ | 0.6989 | 5.0 | 250 | 0.6919 | 0.47 | 0.4679 |
60
+ | 0.7018 | 6.0 | 300 | 0.6919 | 0.46 | 0.4570 |
61
+ | 0.6943 | 7.0 | 350 | 0.6919 | 0.46 | 0.4570 |
62
+ | 0.6943 | 8.0 | 400 | 0.6918 | 0.46 | 0.4570 |
63
 
64
 
65
  ### Framework versions
adapter_config.json CHANGED
@@ -23,8 +23,8 @@
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
- "query",
27
- "value"
28
  ],
29
  "task_type": "SEQ_CLS",
30
  "use_dora": false,
 
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
+ "value",
27
+ "query"
28
  ],
29
  "task_type": "SEQ_CLS",
30
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02d41790d5cb18e1ada562b6398f368a69796cd66fc4d9f9668655fb534d400e
3
  size 2369340
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65f5d0916af603844c871e35585bac13c79886ad6be40dd12dcd67ef7d61503a
3
  size 2369340
tokenizer.json CHANGED
@@ -1,11 +1,6 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 512,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
  "padding": null,
10
  "added_tokens": [
11
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9982591867b4765dd74b7368650bd1ab1daecab7035e4c5ea1f09089d13fefa1
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50de8ae2c84dc0052d904a564af3c6ffe2371819ebf144d304483b2aa98b12d4
3
  size 4984