handraise-dev commited on
Commit
d8d4da3
·
verified ·
1 Parent(s): 5ec8089

Training in progress, epoch 1

Browse files
config.json CHANGED
@@ -1,32 +1,51 @@
1
  {
2
- "activation": "gelu",
3
  "architectures": [
4
- "DistilBertForSequenceClassification"
5
  ],
6
- "attention_dropout": 0.1,
7
- "dim": 768,
8
- "dropout": 0.1,
9
- "hidden_dim": 3072,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  "id2label": {
11
  "0": "NOT RELEVANT",
12
  "1": "RELEVANT"
13
  },
 
14
  "initializer_range": 0.02,
 
15
  "label2id": {
16
  "NOT RELEVANT": 0,
17
  "RELEVANT": 1
18
  },
19
- "max_position_embeddings": 512,
20
- "model_type": "distilbert",
21
- "n_heads": 12,
22
- "n_layers": 6,
23
- "pad_token_id": 0,
 
 
24
  "problem_type": "single_label_classification",
25
- "qa_dropout": 0.1,
26
- "seq_classif_dropout": 0.2,
27
- "sinusoidal_pos_embds": false,
28
- "tie_weights_": true,
29
  "torch_dtype": "float32",
30
  "transformers_version": "4.52.4",
31
- "vocab_size": 30522
 
32
  }
 
1
  {
 
2
  "architectures": [
3
+ "LongformerForSequenceClassification"
4
  ],
5
+ "attention_mode": "longformer",
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "attention_window": [
8
+ 512,
9
+ 512,
10
+ 512,
11
+ 512,
12
+ 512,
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512
20
+ ],
21
+ "bos_token_id": 0,
22
+ "eos_token_id": 2,
23
+ "gradient_checkpointing": false,
24
+ "hidden_act": "gelu",
25
+ "hidden_dropout_prob": 0.1,
26
+ "hidden_size": 768,
27
  "id2label": {
28
  "0": "NOT RELEVANT",
29
  "1": "RELEVANT"
30
  },
31
+ "ignore_attention_mask": false,
32
  "initializer_range": 0.02,
33
+ "intermediate_size": 3072,
34
  "label2id": {
35
  "NOT RELEVANT": 0,
36
  "RELEVANT": 1
37
  },
38
+ "layer_norm_eps": 1e-05,
39
+ "max_position_embeddings": 4098,
40
+ "model_type": "longformer",
41
+ "num_attention_heads": 12,
42
+ "num_hidden_layers": 12,
43
+ "onnx_export": false,
44
+ "pad_token_id": 1,
45
  "problem_type": "single_label_classification",
46
+ "sep_token_id": 2,
 
 
 
47
  "torch_dtype": "float32",
48
  "transformers_version": "4.52.4",
49
+ "type_vocab_size": 1,
50
+ "vocab_size": 50265
51
  }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:34012d9e4116a250580af21dbb18a3908eebd17655a9220ec6d981648f9ad8e7
3
- size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eec84a2546004a1e7ebd478216f50bb8bcc13662c73a3c08436e0b647d92759b
3
+ size 594678184
runs/Jun09_18-26-19_Wess-MacBook-Pro.local/events.out.tfevents.1749511579.Wess-MacBook-Pro.local CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c4aa7404ac938d8b34c18306def6fdb066333d0f7a834cec04dc2c6b697ce9ca
3
- size 7858
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd80445219c8416693f8101be8679c505be4aa9bfcb29a7504ec3a373b3f1f0c
3
+ size 8684
runs/Jun09_18-26-19_Wess-MacBook-Pro.local/events.out.tfevents.1749512028.Wess-MacBook-Pro.local ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e7e44603474c174248817db4132d9dbdc1b9f49b086cf4034dea11d0ab81d2b
3
+ size 512
runs/Jun09_18-36-25_Wess-MacBook-Pro.local/events.out.tfevents.1749512185.Wess-MacBook-Pro.local ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54ebe80fccabb8028ff7ab5dccf6786d55f12bc24c85f994e002754d971834be
3
+ size 5141
runs/Jun09_18-42-39_Wess-MacBook-Pro.local/events.out.tfevents.1749512560.Wess-MacBook-Pro.local ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7612e77f2d60a67ea44e7ec89400b6b8722858f5b49f0c24134a06ba55a4b60b
3
+ size 5141
special_tokens_map.json CHANGED
@@ -1,7 +1,15 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
7
  }
 
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 CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,56 +1,58 @@
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": false,
45
- "cls_token": "[CLS]",
46
- "do_lower_case": true,
 
47
  "extra_special_tokens": {},
48
- "mask_token": "[MASK]",
49
- "model_max_length": 512,
50
- "pad_token": "[PAD]",
51
- "sep_token": "[SEP]",
52
- "strip_accents": null,
53
- "tokenize_chinese_chars": true,
54
- "tokenizer_class": "DistilBertTokenizer",
55
- "unk_token": "[UNK]"
56
  }
 
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": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
  "extra_special_tokens": {},
51
+ "mask_token": "<mask>",
52
+ "model_max_length": 1000000000000000019884624838656,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "LongformerTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": "<unk>"
 
58
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f8f1521bdc7de404c88caa0ed919648cc8de52a2f92d23a150882120b088f2db
3
  size 5713
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:064e4c0438f3204753c7f7cf448c99f4e3a065dc569819c53142ff954dccc485
3
  size 5713
vocab.json ADDED
The diff for this file is too large to render. See raw diff