Hugging Face's logo

mpreda
/
test_dir_model3

Text Classification
Transformers
Safetensors
roberta
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
mpreda commited on
Commit
ee7e279
·
verified ·
1 Parent(s): b013205

best_model_model_3_weighted_loss

Browse files
Files changed (9) hide show
  1. README.md +76 -0
  2. config.json +40 -0
  3. merges.txt +0 -0
  4. model.safetensors +3 -0
  5. special_tokens_map.json +51 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +58 -0
  8. training_args.bin +3 -0
  9. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model: cardiffnlp/twitter-roberta-base-hate
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ - f1
9
+ - precision
10
+ - recall
11
+ model-index:
12
+ - name: test_dir_model3
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # test_dir_model3
20
+
21
+ This model is a fine-tuned version of [cardiffnlp/twitter-roberta-base-hate](https://huggingface.co/cardiffnlp/twitter-roberta-base-hate) on the None dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 2.2679
24
+ - Accuracy: 0.8783
25
+ - F1: 0.6997
26
+ - Precision: 0.8118
27
+ - Recall: 0.6915
28
+
29
+ ## Model description
30
+
31
+ More information needed
32
+
33
+ ## Intended uses & limitations
34
+
35
+ More information needed
36
+
37
+ ## Training and evaluation data
38
+
39
+ More information needed
40
+
41
+ ## Training procedure
42
+
43
+ ### Training hyperparameters
44
+
45
+ The following hyperparameters were used during training:
46
+ - learning_rate: 2e-05
47
+ - train_batch_size: 64
48
+ - eval_batch_size: 64
49
+ - seed: 42
50
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
51
+ - lr_scheduler_type: cosine
52
+ - num_epochs: 10
53
+ - label_smoothing_factor: 0.1
54
+
55
+ ### Training results
56
+
57
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
58
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
59
+ | No log | 1.0 | 35 | 1.1935 | 0.7304 | 0.3920 | 0.3732 | 0.4740 |
60
+ | No log | 2.0 | 70 | 1.2142 | 0.8348 | 0.6136 | 0.6065 | 0.6625 |
61
+ | 0.9237 | 3.0 | 105 | 1.3719 | 0.8783 | 0.7167 | 0.7802 | 0.7244 |
62
+ | 0.9237 | 4.0 | 140 | 1.5517 | 0.8696 | 0.7135 | 0.7685 | 0.7367 |
63
+ | 0.9237 | 5.0 | 175 | 1.9028 | 0.8870 | 0.7282 | 0.7874 | 0.7423 |
64
+ | 0.3387 | 6.0 | 210 | 2.0006 | 0.8696 | 0.6333 | 0.775 | 0.6708 |
65
+ | 0.3387 | 7.0 | 245 | 2.1684 | 0.8783 | 0.6997 | 0.8118 | 0.6915 |
66
+ | 0.3387 | 8.0 | 280 | 2.1672 | 0.8696 | 0.6958 | 0.7972 | 0.7038 |
67
+ | 0.119 | 9.0 | 315 | 2.2526 | 0.8783 | 0.6997 | 0.8118 | 0.6915 |
68
+ | 0.119 | 10.0 | 350 | 2.2679 | 0.8783 | 0.6997 | 0.8118 | 0.6915 |
69
+
70
+
71
+ ### Framework versions
72
+
73
+ - Transformers 4.57.3
74
+ - Pytorch 2.9.0+cu126
75
+ - Datasets 4.0.0
76
+ - Tokenizers 0.22.1
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "dtype": "float32",
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "-",
16
+ "1": "DIRECT",
17
+ "2": "JUDGEMENTAL",
18
+ "3": "REPORTED"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "-": 0,
24
+ "DIRECT": 1,
25
+ "JUDGEMENTAL": 2,
26
+ "REPORTED": 3
27
+ },
28
+ "layer_norm_eps": 1e-05,
29
+ "max_position_embeddings": 514,
30
+ "model_type": "roberta",
31
+ "num_attention_heads": 12,
32
+ "num_hidden_layers": 12,
33
+ "pad_token_id": 1,
34
+ "position_embedding_type": "absolute",
35
+ "problem_type": "single_label_classification",
36
+ "transformers_version": "4.57.3",
37
+ "type_vocab_size": 1,
38
+ "use_cache": true,
39
+ "vocab_size": 50265
40
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfd27eb4e63ec2e4ae3384f8b6916a5a65326a9db7ef14e1441eca7200030248
3
+ size 498618976
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "extra_special_tokens": {},
51
+ "mask_token": "<mask>",
52
+ "model_max_length": 1000000000000000019884624838656,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": "<unk>"
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef181450ebc5e84370d37c28e2e2e476b5ccf62c8fa62ebb574f29733ebbfa93
3
+ size 5841
vocab.json ADDED
The diff for this file is too large to render. See raw diff