amanda-cristina commited on
Commit
762f452
1 Parent(s): 8a0e0de

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "kiddothe2b/longformer-mini-1024",
3
+ "architectures": [
4
+ "LongformerForSequenceClassification"
5
+ ],
6
+ "attention_mode": "longformer",
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "attention_window": [
9
+ 128,
10
+ 128,
11
+ 128,
12
+ 128,
13
+ 128,
14
+ 128
15
+ ],
16
+ "bos_token_id": null,
17
+ "classifier_dropout": null,
18
+ "cls_token_id": 101,
19
+ "eos_token_id": null,
20
+ "gradient_checkpointing": false,
21
+ "hidden_act": "gelu",
22
+ "hidden_dropout_prob": 0.1,
23
+ "hidden_size": 256,
24
+ "id2label": {
25
+ "0": "NEGATIVE",
26
+ "1": "POSITIVE"
27
+ },
28
+ "ignore_attention_mask": false,
29
+ "initializer_range": 0.02,
30
+ "intermediate_size": 1024,
31
+ "label2id": {
32
+ "NEGATIVE": 0,
33
+ "POSITIVE": 1
34
+ },
35
+ "layer_norm_eps": 1e-05,
36
+ "max_position_embeddings": 1026,
37
+ "max_sentence_length": 128,
38
+ "max_sentence_size": 128,
39
+ "max_sentences": 8,
40
+ "model_max_length": 1024,
41
+ "model_type": "longformer",
42
+ "num_attention_heads": 4,
43
+ "num_hidden_layers": 6,
44
+ "onnx_export": false,
45
+ "pad_token_id": 0,
46
+ "position_embedding_type": "absolute",
47
+ "problem_type": "single_label_classification",
48
+ "sep_token_id": 102,
49
+ "torch_dtype": "float32",
50
+ "transformers_version": "4.29.2",
51
+ "type_vocab_size": 2,
52
+ "use_cache": true,
53
+ "vocab_size": 30522
54
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d204ba38b53d7fd09155636b10a4756c1b77e17cd4d7d8bf623b3fc75e9460db
3
+ size 56314625
runs/May25_23-20-25_ee15c6846e48/1685056832.7386537/events.out.tfevents.1685056832.ee15c6846e48.13460.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77682ab42723d9ff539d42dee7f1b49e0c984e12a07c8f703a1ab6049fd61e73
3
+ size 5964
runs/May25_23-20-25_ee15c6846e48/events.out.tfevents.1685056832.ee15c6846e48.13460.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9f746cc8806bc6eda5b055bd07114cb13220779881f741230a3112da49b6e1f
3
+ size 5134
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 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": true,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 1024,
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef46101174a160ff0e99a9099dc0fa04644dd28fa5758a72d1f6a8a82a0759f3
3
+ size 3963
vocab.txt ADDED
The diff for this file is too large to render. See raw diff