mljn commited on
Commit
a71751d
1 Parent(s): 4ce424a

End of training

Browse files
README.md ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: distilbert-base-uncased
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: climate_un2
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
+ # climate_un2
17
+
18
+ This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.0929
21
+ - Accuracy: 0.9860
22
+ - F1 Macro: 0.9804
23
+ - Accuracy Balanced: 0.9856
24
+ - F1 Micro: 0.9860
25
+ - Precision Macro: 0.9755
26
+ - Recall Macro: 0.9856
27
+ - Precision Micro: 0.9860
28
+ - Recall Micro: 0.9860
29
+
30
+ ## Model description
31
+
32
+ More information needed
33
+
34
+ ## Intended uses & limitations
35
+
36
+ More information needed
37
+
38
+ ## Training and evaluation data
39
+
40
+ More information needed
41
+
42
+ ## Training procedure
43
+
44
+ ### Training hyperparameters
45
+
46
+ The following hyperparameters were used during training:
47
+ - learning_rate: 2e-05
48
+ - train_batch_size: 8
49
+ - eval_batch_size: 80
50
+ - seed: 42
51
+ - gradient_accumulation_steps: 2
52
+ - total_train_batch_size: 16
53
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
54
+ - lr_scheduler_type: linear
55
+ - lr_scheduler_warmup_ratio: 0.06
56
+ - num_epochs: 10
57
+
58
+ ### Training results
59
+
60
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | Accuracy Balanced | F1 Micro | Precision Macro | Recall Macro | Precision Micro | Recall Micro |
61
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:-----------------:|:--------:|:---------------:|:------------:|:---------------:|:------------:|
62
+ | No log | 1.0 | 167 | 0.0673 | 0.9851 | 0.9790 | 0.9796 | 0.9851 | 0.9783 | 0.9796 | 0.9851 | 0.9851 |
63
+ | No log | 2.0 | 334 | 0.0732 | 0.9834 | 0.9768 | 0.9839 | 0.9834 | 0.9702 | 0.9839 | 0.9834 | 0.9834 |
64
+ | 0.1178 | 3.0 | 501 | 0.0617 | 0.9860 | 0.9804 | 0.9856 | 0.9860 | 0.9755 | 0.9856 | 0.9860 | 0.9860 |
65
+ | 0.1178 | 4.0 | 668 | 0.0593 | 0.9886 | 0.9840 | 0.9873 | 0.9886 | 0.9809 | 0.9873 | 0.9886 | 0.9886 |
66
+ | 0.1178 | 5.0 | 835 | 0.0822 | 0.9843 | 0.9780 | 0.9844 | 0.9843 | 0.9720 | 0.9844 | 0.9843 | 0.9843 |
67
+ | 0.0088 | 6.0 | 1002 | 0.0810 | 0.9878 | 0.9829 | 0.9880 | 0.9878 | 0.9779 | 0.9880 | 0.9878 | 0.9878 |
68
+ | 0.0088 | 7.0 | 1169 | 0.0904 | 0.9860 | 0.9804 | 0.9856 | 0.9860 | 0.9755 | 0.9856 | 0.9860 | 0.9860 |
69
+ | 0.0088 | 8.0 | 1336 | 0.0927 | 0.9860 | 0.9804 | 0.9856 | 0.9860 | 0.9755 | 0.9856 | 0.9860 | 0.9860 |
70
+ | 0.0006 | 9.0 | 1503 | 0.0936 | 0.9860 | 0.9805 | 0.9869 | 0.9860 | 0.9744 | 0.9869 | 0.9860 | 0.9860 |
71
+ | 0.0006 | 10.0 | 1670 | 0.0929 | 0.9860 | 0.9804 | 0.9856 | 0.9860 | 0.9755 | 0.9856 | 0.9860 | 0.9860 |
72
+
73
+
74
+ ### Framework versions
75
+
76
+ - Transformers 4.35.1
77
+ - Pytorch 2.1.0+cu118
78
+ - Datasets 2.14.7
79
+ - Tokenizers 0.14.1
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "other",
13
+ "1": "climate"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "climate": 1,
18
+ "other": 0
19
+ },
20
+ "max_position_embeddings": 512,
21
+ "model_type": "distilbert",
22
+ "n_heads": 12,
23
+ "n_layers": 6,
24
+ "pad_token_id": 0,
25
+ "problem_type": "single_label_classification",
26
+ "qa_dropout": 0.1,
27
+ "seq_classif_dropout": 0.2,
28
+ "sinusoidal_pos_embds": false,
29
+ "tie_weights_": true,
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.35.1",
32
+ "vocab_size": 30522
33
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53e6b243279d3bd53898e51655a0db098491663c94c75329f870c06545ed8ea0
3
+ size 267832560
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69c6a30cb139c164bbc402dfc7e6c4eb87ff20c0de15553dd14b7fcedcec1d04
3
+ size 4536
vocab.txt ADDED
The diff for this file is too large to render. See raw diff