dianamihalache27 commited on
Commit
6902c3c
1 Parent(s): f183c6b

End of training

Browse files
README.md ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: vinai/bertweet-base
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ - f1
8
+ - precision
9
+ - recall
10
+ model-index:
11
+ - name: bertweet-base_3epoch7
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
+ # bertweet-base_3epoch7
19
+
20
+ This model is a fine-tuned version of [vinai/bertweet-base](https://huggingface.co/vinai/bertweet-base) on an unknown dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 1.3665
23
+ - Accuracy: 0.7493
24
+ - F1: 0.4562
25
+ - Precision: 0.6033
26
+ - Recall: 0.3668
27
+ - Precision Sarcastic: 0.6033
28
+ - Recall Sarcastic: 0.3668
29
+ - F1 Sarcastic: 0.4562
30
+
31
+ ## Model description
32
+
33
+ More information needed
34
+
35
+ ## Intended uses & limitations
36
+
37
+ More information needed
38
+
39
+ ## Training and evaluation data
40
+
41
+ More information needed
42
+
43
+ ## Training procedure
44
+
45
+ ### Training hyperparameters
46
+
47
+ The following hyperparameters were used during training:
48
+ - learning_rate: 5e-05
49
+ - train_batch_size: 16
50
+ - eval_batch_size: 16
51
+ - seed: 42
52
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
+ - lr_scheduler_type: linear
54
+ - num_epochs: 7
55
+
56
+ ### Training results
57
+
58
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Precision Sarcastic | Recall Sarcastic | F1 Sarcastic |
59
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|:-------------------:|:----------------:|:------------:|
60
+ | No log | 1.0 | 174 | 0.9738 | 0.7378 | 0.2541 | 0.6889 | 0.1558 | 0.6889 | 0.1558 | 0.2541 |
61
+ | No log | 2.0 | 348 | 1.0669 | 0.7565 | 0.4459 | 0.6415 | 0.3417 | 0.6415 | 0.3417 | 0.4459 |
62
+ | 0.1251 | 3.0 | 522 | 1.2051 | 0.7493 | 0.4082 | 0.6316 | 0.3015 | 0.6316 | 0.3015 | 0.4082 |
63
+ | 0.1251 | 4.0 | 696 | 1.2494 | 0.7507 | 0.4401 | 0.6182 | 0.3417 | 0.6182 | 0.3417 | 0.4401 |
64
+ | 0.1251 | 5.0 | 870 | 1.3273 | 0.7507 | 0.4677 | 0.6032 | 0.3819 | 0.6032 | 0.3819 | 0.4677 |
65
+ | 0.0458 | 6.0 | 1044 | 1.3478 | 0.7493 | 0.4759 | 0.5940 | 0.3970 | 0.5940 | 0.3970 | 0.4759 |
66
+ | 0.0458 | 7.0 | 1218 | 1.3665 | 0.7493 | 0.4562 | 0.6033 | 0.3668 | 0.6033 | 0.3668 | 0.4562 |
67
+
68
+
69
+ ### Framework versions
70
+
71
+ - Transformers 4.41.2
72
+ - Pytorch 2.3.0+cu121
73
+ - Datasets 2.19.1
74
+ - Tokenizers 0.19.1
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<mask>": 64000
3
+ }
bpe.codes ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "vinai/bertweet-base",
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
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 130,
18
+ "model_type": "roberta",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "problem_type": "single_label_classification",
24
+ "tokenizer_class": "BertweetTokenizer",
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.41.2",
27
+ "type_vocab_size": 1,
28
+ "use_cache": true,
29
+ "vocab_size": 64001
30
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8545dd8d0b62f2da82764cb8bce901f772294fe910287351a2af1fc5640068b1
3
+ size 539630168
runs/May31_16-36-27_e05c0a46fc41/events.out.tfevents.1717173387.e05c0a46fc41.1080.52 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c3eebc9f026afa03acda9104d5d161b6587d675fb8c0b5b2d82da88393f8ff3
3
+ size 10339
runs/May31_16-36-27_e05c0a46fc41/events.out.tfevents.1717173643.e05c0a46fc41.1080.53 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e230cdf0520626677501ca37f0b2406c70e617a984a4e3f56a6b81edd29bfb0d
3
+ size 739
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": "<mask>",
6
+ "pad_token": "<pad>",
7
+ "sep_token": "</s>",
8
+ "unk_token": "<unk>"
9
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "64000": {
36
+ "content": "<mask>",
37
+ "lstrip": false,
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": 1000000000000000019884624838656,
50
+ "normalization": false,
51
+ "pad_token": "<pad>",
52
+ "sep_token": "</s>",
53
+ "tokenizer_class": "BertweetTokenizer",
54
+ "unk_token": "<unk>"
55
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8c34c27dcf3e1eebcb8e775da30bdc620c4c30e5c9ec4b7e14d086ac6e744fa
3
+ size 5112
vocab.txt ADDED
The diff for this file is too large to render. See raw diff