eric-mc2 commited on
Commit
66a59ce
1 Parent(s): 8274d5b

End of training

Browse files
README.md ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: distilbert-foundation-category-funders
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
+ # distilbert-foundation-category-funders
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: 0.0042
21
+ - Accuracy: 1.0
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 2e-05
41
+ - train_batch_size: 16
42
+ - eval_batch_size: 16
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 5
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | No log | 1.0 | 40 | 0.0571 | 1.0 |
53
+ | No log | 2.0 | 80 | 0.0104 | 1.0 |
54
+ | No log | 3.0 | 120 | 0.0059 | 1.0 |
55
+ | No log | 4.0 | 160 | 0.0046 | 1.0 |
56
+ | No log | 5.0 | 200 | 0.0042 | 1.0 |
57
+
58
+
59
+ ### Framework versions
60
+
61
+ - Transformers 4.35.2
62
+ - Pytorch 2.1.0+cu118
63
+ - Datasets 2.15.0
64
+ - Tokenizers 0.15.0
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "Social Service Foundations",
13
+ "1": "Corporate Foundations",
14
+ "2": "Private Foundations",
15
+ "3": "Issue-Based Foundations",
16
+ "4": "Community Foundations",
17
+ "5": "Unknown"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "label2id": {
21
+ "Community Foundations": 4,
22
+ "Corporate Foundations": 1,
23
+ "Issue-Based Foundations": 3,
24
+ "Private Foundations": 2,
25
+ "Social Service Foundations": 0,
26
+ "Unknown": 5
27
+ },
28
+ "max_position_embeddings": 512,
29
+ "model_type": "distilbert",
30
+ "n_heads": 12,
31
+ "n_layers": 6,
32
+ "pad_token_id": 0,
33
+ "problem_type": "single_label_classification",
34
+ "qa_dropout": 0.1,
35
+ "seq_classif_dropout": 0.2,
36
+ "sinusoidal_pos_embds": false,
37
+ "tie_weights_": true,
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.35.2",
40
+ "vocab_size": 30522
41
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa74dec120dfea68539a27912dd25dc504d5697795fd39bdeb0805d7f55a620e
3
+ size 267844872
runs/Dec08_22-42-22_b49c0dd5db0f/events.out.tfevents.1702075375.b49c0dd5db0f.52584.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5edd86ed7b3ff1c7ef9d0d75e27e1ebae93d054756c8fb9ddfc3960bc5628d9
3
+ size 6528
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:e2cf4b69cbb9006ce34373052c3c958cde903ea75451b5ad2cf56fde556df335
3
+ size 4600
vocab.txt ADDED
The diff for this file is too large to render. See raw diff