dstefa commited on
Commit
3102e25
1 Parent(s): a37a8cd

End of training

Browse files
README.md CHANGED
@@ -1,3 +1,71 @@
1
  ---
2
  license: mit
 
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: mit
3
+ base_model: roberta-base
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ - f1
9
+ - precision
10
+ - recall
11
+ model-index:
12
+ - name: roberta-base_topic_classification_nyt_news
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
+ # roberta-base_topic_classification_nyt_news
20
+
21
+ This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.3797
24
+ - Accuracy: 0.9094
25
+ - F1: 0.9092
26
+ - Precision: 0.9098
27
+ - Recall: 0.9094
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: 5e-05
47
+ - train_batch_size: 8
48
+ - eval_batch_size: 8
49
+ - seed: 42
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: linear
52
+ - lr_scheduler_warmup_steps: 500
53
+ - num_epochs: 5
54
+
55
+ ### Training results
56
+
57
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
58
+ |:-------------:|:-----:|:------:|:---------------:|:--------:|:------:|:---------:|:------:|
59
+ | 0.3192 | 1.0 | 20480 | 0.4078 | 0.8865 | 0.8859 | 0.8892 | 0.8865 |
60
+ | 0.2863 | 2.0 | 40960 | 0.4271 | 0.8972 | 0.8970 | 0.8982 | 0.8972 |
61
+ | 0.1979 | 3.0 | 61440 | 0.3797 | 0.9094 | 0.9092 | 0.9098 | 0.9094 |
62
+ | 0.1239 | 4.0 | 81920 | 0.3981 | 0.9117 | 0.9113 | 0.9114 | 0.9117 |
63
+ | 0.1472 | 5.0 | 102400 | 0.4033 | 0.9137 | 0.9135 | 0.9134 | 0.9137 |
64
+
65
+
66
+ ### Framework versions
67
+
68
+ - Transformers 4.32.1
69
+ - Pytorch 2.1.0+cu121
70
+ - Datasets 2.12.0
71
+ - Tokenizers 0.13.2
config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-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
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "Sports",
15
+ "1": "Arts, Culture, and Entertainment",
16
+ "2": "Business and Finance",
17
+ "3": "Health and Wellness",
18
+ "4": "Lifestyle and Fashion",
19
+ "5": "Science and Technology",
20
+ "6": "Politics",
21
+ "7": "Crime"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "LABEL_0": 0,
27
+ "LABEL_1": 1,
28
+ "LABEL_2": 2,
29
+ "LABEL_3": 3,
30
+ "LABEL_4": 4,
31
+ "LABEL_5": 5,
32
+ "LABEL_6": 6,
33
+ "LABEL_7": 7
34
+ },
35
+ "layer_norm_eps": 1e-05,
36
+ "max_position_embeddings": 514,
37
+ "model_type": "roberta",
38
+ "num_attention_heads": 12,
39
+ "num_hidden_layers": 12,
40
+ "pad_token_id": 1,
41
+ "position_embedding_type": "absolute",
42
+ "problem_type": "single_label_classification",
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.32.1",
45
+ "type_vocab_size": 1,
46
+ "use_cache": true,
47
+ "vocab_size": 50265
48
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4eee92fbc6cbc4ffa4af88de3ae832177477678172b4b3ce5a5f6570373424c
3
+ size 498676526
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
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "cls_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "errors": "replace",
8
+ "mask_token": "<mask>",
9
+ "max_length": 512,
10
+ "model_max_length": 512,
11
+ "pad_to_multiple_of": null,
12
+ "pad_token": "<pad>",
13
+ "pad_token_type_id": 0,
14
+ "padding_side": "right",
15
+ "sep_token": "</s>",
16
+ "stride": 0,
17
+ "tokenizer_class": "RobertaTokenizer",
18
+ "trim_offsets": true,
19
+ "truncation_side": "right",
20
+ "truncation_strategy": "longest_first",
21
+ "unk_token": "<unk>"
22
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e634b15fce4d55ea8cc8787cb28202df1913f7d700c642c7d835594210f201e
3
+ size 4600
vocab.json ADDED
The diff for this file is too large to render. See raw diff