Hugging Face's logo

galkowskim
/
no_global_attention_longformer-base-512-text-classification-emotion-adamw-att_win_size_32

Text Classification
Transformers
TensorBoard
Safetensors
longformer
Inference Endpoints
Model card Files Metrics Community
galkowskim commited on
Commit
7953ed3
•
1 Parent(s): be31d2c

Training in progress, epoch 2

Browse files
Files changed (9) hide show
  1. config.json +52 -0
  2. merges.txt +0 -0
  3. model.safetensors +3 -0
  4. runs/Jun07_21-58-03_dgx-4.eden/events.out.tfevents.1717790284.dgx-4.eden.1193788.10 +3 -0
  5. special_tokens_map.json +15 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +57 -0
  8. training_args.bin +3 -0
  9. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ 32,
10
+ 32,
11
+ 32,
12
+ 32,
13
+ 32,
14
+ 32,
15
+ 32,
16
+ 32,
17
+ 32,
18
+ 32,
19
+ 32,
20
+ 32
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": "SADNESS",
30
+ "1": "JOY"
31
+ },
32
+ "ignore_attention_mask": false,
33
+ "initializer_range": 0.02,
34
+ "intermediate_size": 3072,
35
+ "label2id": {
36
+ "JOY": 1,
37
+ "SADNESS": 0
38
+ },
39
+ "layer_norm_eps": 1e-05,
40
+ "max_position_embeddings": 514,
41
+ "model_type": "longformer",
42
+ "num_attention_heads": 12,
43
+ "num_hidden_layers": 12,
44
+ "onnx_export": false,
45
+ "pad_token_id": 1,
46
+ "problem_type": "single_label_classification",
47
+ "sep_token_id": 2,
48
+ "torch_dtype": "float32",
49
+ "transformers_version": "4.40.0",
50
+ "type_vocab_size": 1,
51
+ "vocab_size": 50265
52
+ }
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 sha256:5464af9633faa90af3cbab3c2d2e8cf8c3a2456c82afe1c21916289251087a6e
3
+ size 498613416
runs/Jun07_21-58-03_dgx-4.eden/events.out.tfevents.1717790284.dgx-4.eden.1193788.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24e3be5effdf8cee7f04b81618320f13f18873e092337ec807f1bff653db2c33
3
+ size 19748
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": 1000000000000000019884624838656,
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 sha256:2e2b227ef8062efb5dc91dde9735c14d147b07ff79dce448bb129ff4062601b7
3
+ size 5112
vocab.json ADDED
The diff for this file is too large to render. See raw diff