lenatr99 commited on
Commit
5ff43a1
1 Parent(s): 5230405

loha_fine_tuned_copa_sloberta

Browse files
README.md ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-sa-4.0
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ base_model: EMBEDDIA/sloberta
7
+ metrics:
8
+ - accuracy
9
+ - f1
10
+ model-index:
11
+ - name: loha_fine_tuned_copa_sloberta
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # loha_fine_tuned_copa_sloberta
19
+
20
+ This model is a fine-tuned version of [EMBEDDIA/sloberta](https://huggingface.co/EMBEDDIA/sloberta) on an unknown dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.6929
23
+ - Accuracy: 0.51
24
+ - F1: 0.5104
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
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
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: linear
49
+ - training_steps: 400
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
54
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
55
+ | 0.7001 | 1.0 | 50 | 0.6935 | 0.47 | 0.4711 |
56
+ | 0.6932 | 2.0 | 100 | 0.6931 | 0.48 | 0.48 |
57
+ | 0.6913 | 3.0 | 150 | 0.6928 | 0.51 | 0.5112 |
58
+ | 0.7055 | 4.0 | 200 | 0.6927 | 0.48 | 0.48 |
59
+ | 0.6902 | 5.0 | 250 | 0.6926 | 0.5 | 0.4988 |
60
+ | 0.6981 | 6.0 | 300 | 0.6930 | 0.47 | 0.4694 |
61
+ | 0.7011 | 7.0 | 350 | 0.6930 | 0.5 | 0.4988 |
62
+ | 0.6894 | 8.0 | 400 | 0.6929 | 0.51 | 0.5104 |
63
+
64
+
65
+ ### Framework versions
66
+
67
+ - PEFT 0.11.1
68
+ - Transformers 4.41.0
69
+ - Pytorch 2.3.0+cu121
70
+ - Datasets 2.19.1
71
+ - Tokenizers 0.19.1
adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha": 32,
3
+ "alpha_pattern": {},
4
+ "auto_mapping": null,
5
+ "base_model_name_or_path": "EMBEDDIA/sloberta",
6
+ "inference_mode": true,
7
+ "init_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "module_dropout": 0.0,
11
+ "modules_to_save": [
12
+ "classifier",
13
+ "score"
14
+ ],
15
+ "peft_type": "LOHA",
16
+ "r": 16,
17
+ "rank_dropout": 0.0,
18
+ "rank_pattern": {},
19
+ "revision": null,
20
+ "target_modules": [
21
+ "query",
22
+ "value"
23
+ ],
24
+ "task_type": "SEQ_CLS",
25
+ "use_effective_conv2d": false
26
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:655545c2c100cd67335fe7c20d7d2a91332f2766fa497471de5c5a31aef0bd7b
3
+ size 4735300
runs/May23_19-48-47_df80bf88bf22/events.out.tfevents.1716493728.df80bf88bf22.431.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e043b1d4a26c54c6a4ba88a5673e3b4bbfc13b49f2c4b397ca628f59edd31a3e
3
+ size 9866
runs/May23_19-48-47_df80bf88bf22/events.out.tfevents.1716493754.df80bf88bf22.431.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5790272ca1c478021b9af478144ddcf8b0087db8c7ff651f6331012c568dd3f9
3
+ size 457
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34b589385a2320549143ab23b0ccf82cc99a82685701cdabe0fad847bd0479ff
3
+ size 800013
special_tokens_map.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s>NOTUSED",
4
+ "</s>NOTUSED"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<s>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "cls_token": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "eos_token": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "mask_token": {
28
+ "content": "<mask>",
29
+ "lstrip": true,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "pad_token": {
35
+ "content": "<pad>",
36
+ "lstrip": false,
37
+ "normalized": false,
38
+ "rstrip": false,
39
+ "single_word": false
40
+ },
41
+ "sep_token": {
42
+ "content": "</s>",
43
+ "lstrip": false,
44
+ "normalized": false,
45
+ "rstrip": false,
46
+ "single_word": false
47
+ },
48
+ "unk_token": {
49
+ "content": "<unk>",
50
+ "lstrip": false,
51
+ "normalized": false,
52
+ "rstrip": false,
53
+ "single_word": false
54
+ }
55
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>NOTUSED",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>NOTUSED",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "5": {
36
+ "content": "<s>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "6": {
44
+ "content": "</s>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "32004": {
52
+ "content": "<mask>",
53
+ "lstrip": true,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ }
59
+ },
60
+ "additional_special_tokens": [
61
+ "<s>NOTUSED",
62
+ "</s>NOTUSED"
63
+ ],
64
+ "bos_token": "<s>",
65
+ "clean_up_tokenization_spaces": true,
66
+ "cls_token": "<s>",
67
+ "do_lower_case": false,
68
+ "eos_token": "</s>",
69
+ "mask_token": "<mask>",
70
+ "model_max_length": 512,
71
+ "pad_token": "<pad>",
72
+ "sep_token": "</s>",
73
+ "sp_model_kwargs": {},
74
+ "tokenizer_class": "CamembertTokenizer",
75
+ "unk_token": "<unk>"
76
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8fcbaa4e5483bf35e2ea2683b14a220db1a144b8b582ae1e334e34ce0a5eb99
3
+ size 5112