prajwalJumde commited on
Commit
e5a9fe7
1 Parent(s): cd6e270

Training in progress, epoch 1

Browse files
README.md ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: allenai/longformer-base-4096
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: classification_test_14Dec
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
+ # classification_test_14Dec
17
+
18
+ This model is a fine-tuned version of [allenai/longformer-base-4096](https://huggingface.co/allenai/longformer-base-4096) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.2892
21
+ - Accuracy: 0.9508
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: 2
42
+ - eval_batch_size: 2
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
+ | 0.5775 | 1.0 | 3750 | 0.6166 | 0.902 |
53
+ | 0.3579 | 2.0 | 7500 | 0.4535 | 0.9228 |
54
+ | 0.2818 | 3.0 | 11250 | 0.4030 | 0.9336 |
55
+ | 0.1849 | 4.0 | 15000 | 0.3642 | 0.9408 |
56
+ | 0.0957 | 5.0 | 18750 | 0.2892 | 0.9508 |
57
+
58
+
59
+ ### Framework versions
60
+
61
+ - Transformers 4.35.2
62
+ - Pytorch 2.1.1+cu118
63
+ - Datasets 2.15.0
64
+ - Tokenizers 0.15.0
config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "allenai/longformer-base-4096",
3
+ "architectures": [
4
+ "LongformerForSequenceClassification"
5
+ ],
6
+ "attention_mode": "longformer",
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "attention_window": [
9
+ 512,
10
+ 512,
11
+ 512,
12
+ 512,
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512,
20
+ 512
21
+ ],
22
+ "bos_token_id": 0,
23
+ "eos_token_id": 2,
24
+ "gradient_checkpointing": false,
25
+ "hidden_act": "gelu",
26
+ "hidden_dropout_prob": 0.1,
27
+ "hidden_size": 768,
28
+ "id2label": {
29
+ "0": "Office Visit",
30
+ "1": "Emergency Dept",
31
+ "2": "Diagnostics",
32
+ "3": "Lab Reports",
33
+ "4": "Operative Report",
34
+ "5": "Physical Therapy (PT/OT)",
35
+ "6": "Billing",
36
+ "7": "Subpoena",
37
+ "8": "Other"
38
+ },
39
+ "ignore_attention_mask": false,
40
+ "initializer_range": 0.02,
41
+ "intermediate_size": 3072,
42
+ "label2id": {
43
+ "Billing": 6,
44
+ "Diagnostics": 2,
45
+ "Emergency Dept": 1,
46
+ "Lab Reports": 3,
47
+ "Office Visit": 0.0,
48
+ "Operative Report": 4,
49
+ "Other": 8,
50
+ "Physical Therapy (PT/OT)": 5,
51
+ "Subpoena": 7
52
+ },
53
+ "layer_norm_eps": 1e-05,
54
+ "max_position_embeddings": 4098,
55
+ "model_type": "longformer",
56
+ "num_attention_heads": 12,
57
+ "num_hidden_layers": 12,
58
+ "onnx_export": false,
59
+ "pad_token_id": 1,
60
+ "problem_type": "single_label_classification",
61
+ "sep_token_id": 2,
62
+ "torch_dtype": "float32",
63
+ "transformers_version": "4.35.2",
64
+ "type_vocab_size": 1,
65
+ "vocab_size": 50265
66
+ }
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:e9d99524809f62972f4ece7f785ce2354dc01ed997ebf922ba32713bdcd58c0f
3
+ size 594699716
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 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 4096,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "LongformerTokenizer",
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 sha256:75bc7632344b8752359aff94a5c9aaddb3494b03809ec5ffbc956346f01de548
3
+ size 4600
vocab.json ADDED
The diff for this file is too large to render. See raw diff