dianamihalache27 commited on
Commit
040ed98
1 Parent(s): b528961

End of training

Browse files
README.md ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: cardiffnlp/twitter-roberta-base-irony
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ - precision
8
+ - recall
9
+ - f1
10
+ model-index:
11
+ - name: Twroberta-baseB_15epoch
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
+ # Twroberta-baseB_15epoch
19
+
20
+ This model is a fine-tuned version of [cardiffnlp/twitter-roberta-base-irony](https://huggingface.co/cardiffnlp/twitter-roberta-base-irony) on an unknown dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.1971
23
+ - Accuracy: 0.7686
24
+ - Precision: 0.2328
25
+ - Recall: 0.3210
26
+ - F1: 0.2693
27
+
28
+ ## Model description
29
+
30
+ More information needed
31
+
32
+ ## Intended uses & limitations
33
+
34
+ More information needed
35
+
36
+ ## Training and evaluation data
37
+
38
+ More information needed
39
+
40
+ ## Training procedure
41
+
42
+ ### Training hyperparameters
43
+
44
+ The following hyperparameters were used during training:
45
+ - learning_rate: 5e-05
46
+ - train_batch_size: 16
47
+ - eval_batch_size: 16
48
+ - seed: 42
49
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
+ - lr_scheduler_type: linear
51
+ - num_epochs: 15
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
56
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
57
+ | No log | 1.0 | 217 | 0.1248 | 0.8571 | 0.0 | 0.0 | 0.0 |
58
+ | No log | 2.0 | 434 | 0.1250 | 0.8679 | 0.5258 | 0.0701 | 0.1237 |
59
+ | 0.1617 | 3.0 | 651 | 0.1225 | 0.825 | 0.2771 | 0.2657 | 0.2712 |
60
+ | 0.1617 | 4.0 | 868 | 0.1325 | 0.8079 | 0.3164 | 0.2583 | 0.2554 |
61
+ | 0.0885 | 5.0 | 1085 | 0.1553 | 0.7707 | 0.2169 | 0.2694 | 0.2391 |
62
+ | 0.0885 | 6.0 | 1302 | 0.1680 | 0.7507 | 0.2112 | 0.3358 | 0.2592 |
63
+ | 0.0392 | 7.0 | 1519 | 0.2129 | 0.7093 | 0.1936 | 0.3875 | 0.2575 |
64
+ | 0.0392 | 8.0 | 1736 | 0.1717 | 0.7764 | 0.2316 | 0.2841 | 0.2528 |
65
+ | 0.0392 | 9.0 | 1953 | 0.1915 | 0.7507 | 0.2287 | 0.3321 | 0.2671 |
66
+ | 0.0178 | 10.0 | 2170 | 0.1987 | 0.7586 | 0.2294 | 0.3653 | 0.2809 |
67
+ | 0.0178 | 11.0 | 2387 | 0.1923 | 0.7564 | 0.2287 | 0.3358 | 0.2710 |
68
+ | 0.0108 | 12.0 | 2604 | 0.1925 | 0.7586 | 0.2317 | 0.3358 | 0.2729 |
69
+ | 0.0108 | 13.0 | 2821 | 0.1965 | 0.775 | 0.2356 | 0.3284 | 0.2743 |
70
+ | 0.0078 | 14.0 | 3038 | 0.1964 | 0.7621 | 0.2326 | 0.3284 | 0.2712 |
71
+ | 0.0078 | 15.0 | 3255 | 0.1971 | 0.7686 | 0.2328 | 0.3210 | 0.2693 |
72
+
73
+
74
+ ### Framework versions
75
+
76
+ - Transformers 4.41.2
77
+ - Pytorch 2.3.0+cu121
78
+ - Datasets 2.19.2
79
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cardiffnlp/twitter-roberta-base-irony",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
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": "LABEL_0",
16
+ "1": "LABEL_1",
17
+ "2": "LABEL_2",
18
+ "3": "LABEL_3",
19
+ "4": "LABEL_4",
20
+ "5": "LABEL_5"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "LABEL_0": 0,
26
+ "LABEL_1": 1,
27
+ "LABEL_2": 2,
28
+ "LABEL_3": 3,
29
+ "LABEL_4": 4,
30
+ "LABEL_5": 5
31
+ },
32
+ "layer_norm_eps": 1e-05,
33
+ "max_position_embeddings": 514,
34
+ "model_type": "roberta",
35
+ "num_attention_heads": 12,
36
+ "num_hidden_layers": 12,
37
+ "pad_token_id": 1,
38
+ "position_embedding_type": "absolute",
39
+ "problem_type": "multi_label_classification",
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.41.2",
42
+ "type_vocab_size": 1,
43
+ "use_cache": true,
44
+ "vocab_size": 50265
45
+ }
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:b30a9ddc30b3c762b836eca072eb3a79f6f83b0bd35cf66d92293dcb56dcafbe
3
+ size 498625128
runs/Jun06_12-40-59_b9092328a211/events.out.tfevents.1717677660.b9092328a211.7542.24 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f31e6006291388fa298b4f5c3c1c079c561e3aafe2e34ad56d737b09f154b8e
3
+ size 13880
runs/Jun06_12-40-59_b9092328a211/events.out.tfevents.1717678358.b9092328a211.7542.25 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e45a114ff4db7df39ddbed353025e009e6672110ef88d221684933758c8cab19
3
+ size 560
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 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b86085f00dab5d3c4db75db35ec6381dc854cf55d027b6fc50789048fecc9ea
3
+ size 5112
vocab.json ADDED
The diff for this file is too large to render. See raw diff