haturusinghe commited on
Commit
f452204
1 Parent(s): c3e3314

End of training

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: xlm-roberta-base
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: XLM-R-BASE-VanillaFT-5E-spring-feather-1-D-08-03-T-08-15
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # XLM-R-BASE-VanillaFT-5E-spring-feather-1-D-08-03-T-08-15
17
+
18
+ This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.4196
21
+ - Precision 0: 0.8318
22
+ - Precision 1: 0.7503
23
+ - Recall 0: 0.8119
24
+ - Recall 1: 0.7767
25
+ - F1 0: 0.8217
26
+ - F1 1: 0.7633
27
+ - Precision Weighted: 0.7987
28
+ - Recall Weighted: 0.7976
29
+ - F1 Weighted: 0.7980
30
+ - Accuracy: 0.7976
31
+ - F1 Macro: 0.7925
32
+
33
+ ## Model description
34
+
35
+ More information needed
36
+
37
+ ## Intended uses & limitations
38
+
39
+ More information needed
40
+
41
+ ## Training and evaluation data
42
+
43
+ More information needed
44
+
45
+ ## Training procedure
46
+
47
+ ### Training hyperparameters
48
+
49
+ The following hyperparameters were used during training:
50
+ - learning_rate: 2e-05
51
+ - train_batch_size: 16
52
+ - eval_batch_size: 16
53
+ - seed: 402
54
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
55
+ - lr_scheduler_type: linear
56
+ - lr_scheduler_warmup_ratio: 0.1
57
+ - num_epochs: 5
58
+
59
+ ### Training results
60
+
61
+ | Training Loss | Epoch | Step | Validation Loss | Precision 0 | Precision 1 | Recall 0 | Recall 1 | F1 0 | F1 1 | Precision Weighted | Recall Weighted | F1 Weighted | Accuracy | F1 Macro |
62
+ |:-------------:|:-----:|:----:|:---------------:|:-----------:|:-----------:|:--------:|:--------:|:------:|:------:|:------------------:|:---------------:|:-----------:|:--------:|:--------:|
63
+ | 0.5481 | 1.0 | 469 | 0.4437 | 0.7838 | 0.7441 | 0.8226 | 0.6900 | 0.8028 | 0.7161 | 0.7677 | 0.7688 | 0.7676 | 0.7688 | 0.7594 |
64
+ | 0.4178 | 2.0 | 938 | 0.4403 | 0.8529 | 0.6988 | 0.7519 | 0.8211 | 0.7994 | 0.7553 | 0.7904 | 0.7800 | 0.7815 | 0.7800 | 0.7773 |
65
+ | 0.3416 | 3.0 | 1407 | 0.4196 | 0.8318 | 0.7503 | 0.8119 | 0.7767 | 0.8217 | 0.7633 | 0.7987 | 0.7976 | 0.7980 | 0.7976 | 0.7925 |
66
+ | 0.2757 | 4.0 | 1876 | 0.4393 | 0.8430 | 0.7153 | 0.7735 | 0.8024 | 0.8068 | 0.7565 | 0.7912 | 0.7852 | 0.7864 | 0.7852 | 0.7816 |
67
+ | 0.2231 | 5.0 | 2345 | 0.4908 | 0.8343 | 0.7418 | 0.8031 | 0.7827 | 0.8184 | 0.7617 | 0.7968 | 0.7948 | 0.7954 | 0.7948 | 0.7901 |
68
+
69
+
70
+ ### Framework versions
71
+
72
+ - Transformers 4.43.3
73
+ - Pytorch 2.3.1+cu121
74
+ - Datasets 2.20.0
75
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-base",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "NOT",
15
+ "1": "OFF"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "NOT": 0,
21
+ "OFF": 1
22
+ },
23
+ "layer_norm_eps": 1e-05,
24
+ "max_position_embeddings": 514,
25
+ "model_type": "xlm-roberta",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "output_past": true,
29
+ "pad_token_id": 1,
30
+ "position_embedding_type": "absolute",
31
+ "problem_type": "single_label_classification",
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.43.3",
34
+ "type_vocab_size": 1,
35
+ "use_cache": true,
36
+ "vocab_size": 250002
37
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09b02919e172a69f12cc641d1d03d62b351a64df5a633f3ae8f54dd20a8e72d9
3
+ size 1112205008
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ffb37461c391f096759f4a9bbbc329da0f36952f88bab061fcf84940c022e98
3
+ size 17082999
tokenizer_config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
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>",
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
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 512,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "tokenizer_class": "XLMRobertaTokenizer",
53
+ "unk_token": "<unk>"
54
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9172fd6f2a043081cba8fa08b1cfa8f2e70e35807bcf641d43bc0ead58cd75b6
3
+ size 5240