Hugging Face's logo

anzeo
/
loha_fine_tuned_copa_croslo

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
anzeo commited on
Commit
6dfea1c
•
1 Parent(s): 701facc

loha_fine_tuned_copa_croslo

Browse files
Files changed (11) hide show
  1. README.md +13 -13
  2. adapter_config.json +2 -2
  3. adapter_model.safetensors +1 -1
  4. runs/May22_19-31-07_DESKTOP-22QTFDR/events.out.tfevents.1716399084.DESKTOP-22QTFDR.20468.4 +3 -0
  5. runs/May22_19-31-07_DESKTOP-22QTFDR/events.out.tfevents.1716399109.DESKTOP-22QTFDR.20468.5 +3 -0
  6. runs/May22_19-32-12_DESKTOP-22QTFDR/events.out.tfevents.1716399133.DESKTOP-22QTFDR.20468.6 +3 -0
  7. runs/May22_19-32-12_DESKTOP-22QTFDR/events.out.tfevents.1716399162.DESKTOP-22QTFDR.20468.7 +3 -0
  8. runs/May22_19-33-01_DESKTOP-22QTFDR/events.out.tfevents.1716399183.DESKTOP-22QTFDR.20468.8 +3 -0
  9. runs/May22_19-33-01_DESKTOP-22QTFDR/events.out.tfevents.1716399211.DESKTOP-22QTFDR.20468.9 +3 -0
  10. tokenizer.json +1 -6
  11. 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 [EMBEDDIA/crosloengual-bert](https://huggingface.co/EMBEDDIA/crosloengual-bert) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 1.2439
23
- - Accuracy: 0.64
24
- - F1: 0.6409
25
 
26
  ## Model description
27
 
@@ -53,19 +53,19 @@ The following hyperparameters were used during training:
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
54
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
55
  | 0.693 | 1.0 | 50 | 0.6764 | 0.56 | 0.56 |
56
- | 0.6401 | 2.0 | 100 | 0.6814 | 0.53 | 0.5304 |
57
- | 0.5345 | 3.0 | 150 | 0.6725 | 0.66 | 0.6592 |
58
- | 0.3293 | 4.0 | 200 | 0.8363 | 0.65 | 0.6509 |
59
- | 0.1831 | 5.0 | 250 | 0.9311 | 0.65 | 0.6507 |
60
- | 0.0662 | 6.0 | 300 | 1.0890 | 0.67 | 0.6707 |
61
- | 0.0238 | 7.0 | 350 | 1.1631 | 0.64 | 0.6409 |
62
- | 0.0364 | 8.0 | 400 | 1.2439 | 0.64 | 0.6409 |
63
 
64
 
65
  ### Framework versions
66
 
67
- - PEFT 0.10.1.dev0
68
- - Transformers 4.40.1
69
  - Pytorch 2.1.1+cu121
70
- - Datasets 2.19.0
71
  - Tokenizers 0.19.1
 
19
 
20
  This model is a fine-tuned version of [EMBEDDIA/crosloengual-bert](https://huggingface.co/EMBEDDIA/crosloengual-bert) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 1.3810
23
+ - Accuracy: 0.65
24
+ - F1: 0.6507
25
 
26
  ## Model description
27
 
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
54
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
55
  | 0.693 | 1.0 | 50 | 0.6764 | 0.56 | 0.56 |
56
+ | 0.6391 | 2.0 | 100 | 0.6594 | 0.59 | 0.5904 |
57
+ | 0.5208 | 3.0 | 150 | 0.6686 | 0.64 | 0.64 |
58
+ | 0.3196 | 4.0 | 200 | 0.9298 | 0.64 | 0.6409 |
59
+ | 0.1702 | 5.0 | 250 | 0.9696 | 0.61 | 0.6110 |
60
+ | 0.0585 | 6.0 | 300 | 1.2550 | 0.63 | 0.6308 |
61
+ | 0.0169 | 7.0 | 350 | 1.3515 | 0.64 | 0.6406 |
62
+ | 0.0156 | 8.0 | 400 | 1.3810 | 0.65 | 0.6507 |
63
 
64
 
65
  ### Framework versions
66
 
67
+ - PEFT 0.11.1
68
+ - Transformers 4.40.2
69
  - Pytorch 2.1.1+cu121
70
+ - Datasets 2.19.1
71
  - Tokenizers 0.19.1
adapter_config.json CHANGED
@@ -18,8 +18,8 @@
18
  "rank_pattern": {},
19
  "revision": null,
20
  "target_modules": [
21
- "query",
22
- "value"
23
  ],
24
  "task_type": "SEQ_CLS",
25
  "use_effective_conv2d": false
 
18
  "rank_pattern": {},
19
  "revision": null,
20
  "target_modules": [
21
+ "value",
22
+ "query"
23
  ],
24
  "task_type": "SEQ_CLS",
25
  "use_effective_conv2d": false
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:493e3322fad21af362d25b5da1f8e49a68deb922f5af235a9c4ba619bf3a1671
3
  size 4735028
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:523157d376b37d2c090f9ed2a94387e6d10ac34ce69af5ca4056c4fa8d8f61ac
3
  size 4735028
runs/May22_19-31-07_DESKTOP-22QTFDR/events.out.tfevents.1716399084.DESKTOP-22QTFDR.20468.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e6628567477cc9ee0be21dcbee72ba2886f7e161d707a9ed22a4f70706f8fcc
3
+ size 9649
runs/May22_19-31-07_DESKTOP-22QTFDR/events.out.tfevents.1716399109.DESKTOP-22QTFDR.20468.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d675d73881e277dbd8e04fea3dd7e9e4307ffc29aa87a6d637eeb7008c022675
3
+ size 457
runs/May22_19-32-12_DESKTOP-22QTFDR/events.out.tfevents.1716399133.DESKTOP-22QTFDR.20468.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54bfafaa915a81a6cf807ef817429d70d6693f3ceada0506236faf4d5d7dc765
3
+ size 9649
runs/May22_19-32-12_DESKTOP-22QTFDR/events.out.tfevents.1716399162.DESKTOP-22QTFDR.20468.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97b6663034d7d7a6d5ce0e79b9aa15efde75fd5934a5557c714fd21c5069fc73
3
+ size 457
runs/May22_19-33-01_DESKTOP-22QTFDR/events.out.tfevents.1716399183.DESKTOP-22QTFDR.20468.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4217e6228482168a85c9976bb066bf56cf15e285604b51cb35dba0d8222557f2
3
+ size 9650
runs/May22_19-33-01_DESKTOP-22QTFDR/events.out.tfevents.1716399211.DESKTOP-22QTFDR.20468.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a3f9db404b544a35528877736852af5d9d979219a6f22e7756eb565077e08a9
3
+ size 457
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 sha256:58ed512d179cc8044a0d296a60097d4f4b947ccca545d18ce6cf1fe8110ce86c
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:315e8b231b1617a3f8918bf73d32e920869588b82b4e8c7d93f3c2cd5fb30a11
3
  size 5048