sakren commited on
Commit
490175c
1 Parent(s): d40c500

Training in progress, step 500

Browse files
config.json CHANGED
@@ -1,13 +1,15 @@
1
  {
2
- "_name_or_path": "microsoft/MiniLM-L12-H384-uncased",
3
  "architectures": [
4
- "BertForSequenceClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
 
7
  "classifier_dropout": null,
 
8
  "hidden_act": "gelu",
9
  "hidden_dropout_prob": 0.1,
10
- "hidden_size": 384,
11
  "id2label": {
12
  "0": "sadness",
13
  "1": "joy",
@@ -17,7 +19,7 @@
17
  "5": "neutral"
18
  },
19
  "initializer_range": 0.02,
20
- "intermediate_size": 1536,
21
  "label2id": {
22
  "anger": 2,
23
  "fear": 3,
@@ -26,17 +28,17 @@
26
  "sad": 0,
27
  "surprise": 4
28
  },
29
- "layer_norm_eps": 1e-12,
30
- "max_position_embeddings": 512,
31
- "model_type": "bert",
32
  "num_attention_heads": 12,
33
  "num_hidden_layers": 12,
34
- "pad_token_id": 0,
35
  "position_embedding_type": "absolute",
36
  "problem_type": "single_label_classification",
37
  "torch_dtype": "float32",
38
  "transformers_version": "4.39.3",
39
- "type_vocab_size": 2,
40
  "use_cache": true,
41
- "vocab_size": 30522
42
  }
 
1
  {
2
+ "_name_or_path": "roberta-base",
3
  "architectures": [
4
+ "RobertaForSequenceClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
  "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
  "hidden_act": "gelu",
11
  "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
  "id2label": {
14
  "0": "sadness",
15
  "1": "joy",
 
19
  "5": "neutral"
20
  },
21
  "initializer_range": 0.02,
22
+ "intermediate_size": 3072,
23
  "label2id": {
24
  "anger": 2,
25
  "fear": 3,
 
28
  "sad": 0,
29
  "surprise": 4
30
  },
31
+ "layer_norm_eps": 1e-05,
32
+ "max_position_embeddings": 514,
33
+ "model_type": "roberta",
34
  "num_attention_heads": 12,
35
  "num_hidden_layers": 12,
36
+ "pad_token_id": 1,
37
  "position_embedding_type": "absolute",
38
  "problem_type": "single_label_classification",
39
  "torch_dtype": "float32",
40
  "transformers_version": "4.39.3",
41
+ "type_vocab_size": 1,
42
  "use_cache": true,
43
+ "vocab_size": 50265
44
  }
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 sha256:074d51a0e727e1443291a5c36f7808cea74343e647b864098c8bae11940a74f5
3
- size 133472536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a066e8339a0a8c26c047ce02b8b71eb1c014f93f9457ec3e9d57fcb66254e259
3
+ size 498625128
runs/May15_18-26-18_95a092faa389/events.out.tfevents.1715797601.95a092faa389.35.11 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:191ea2daacfea6cbbb68a2ba80d4b3bf14cb284314ef39ce1453731f03f87ee2
3
- size 13662
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a17235a5d91f2d5beac2d133eb210e7ed88f4558f32613423a35d6bc968e7ff0
3
+ size 15382
runs/May15_18-26-18_95a092faa389/events.out.tfevents.1715797753.95a092faa389.35.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38cb4beedb46c16e229cad8d8ebfd4a2b844d93f6c2f28d49362e982c6201fd9
3
+ size 560
runs/May15_18-29-49_95a092faa389/events.out.tfevents.1715797816.95a092faa389.35.13 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efd8e62c61128ef384e01ba9ed4bc47a664b8028743d8e22fc2ccd4c70d3a35d
3
+ size 8956
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
@@ -1,57 +1,57 @@
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_basic_tokenize": true,
47
- "do_lower_case": true,
48
- "mask_token": "[MASK]",
49
- "model_max_length": 1000000000000000019884624838656,
50
- "never_split": null,
51
- "pad_token": "[PAD]",
52
- "sep_token": "[SEP]",
53
- "strip_accents": null,
54
- "tokenize_chinese_chars": true,
55
- "tokenizer_class": "BertTokenizer",
56
- "unk_token": "[UNK]"
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": 512,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
 
 
57
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:771005c0f379c25345fdfac10ebf21dbc3b4d08bad979706ac2cc2e77318ac48
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8354cb4a911c1c77d4d19eb9669fdf856e11d1fbecf7223922aec710cca7b59
3
  size 4920
vocab.json ADDED
The diff for this file is too large to render. See raw diff