QuimBallester commited on
Commit
6889d16
·
verified ·
1 Parent(s): 52d7668

Training in progress, epoch 1

Browse files
config.json CHANGED
@@ -1,49 +1,36 @@
1
  {
2
- "_num_labels": 3,
3
- "activation_dropout": 0.0,
4
- "activation_function": "gelu",
5
- "add_final_layer_norm": false,
6
  "architectures": [
7
- "BartForSequenceClassification"
8
  ],
9
- "attention_dropout": 0.0,
10
  "bos_token_id": 0,
11
- "classif_dropout": 0.0,
12
- "classifier_dropout": 0.0,
13
- "d_model": 1024,
14
- "decoder_attention_heads": 16,
15
- "decoder_ffn_dim": 4096,
16
- "decoder_layerdrop": 0.0,
17
- "decoder_layers": 12,
18
- "decoder_start_token_id": 2,
19
- "dropout": 0.1,
20
- "encoder_attention_heads": 16,
21
- "encoder_ffn_dim": 4096,
22
- "encoder_layerdrop": 0.0,
23
- "encoder_layers": 12,
24
  "eos_token_id": 2,
25
- "forced_eos_token_id": 2,
26
  "gradient_checkpointing": false,
 
 
 
27
  "id2label": {
28
  "0": "concrete",
29
  "1": "general"
30
  },
31
- "init_std": 0.02,
32
- "is_encoder_decoder": true,
33
  "label2id": {
34
  "concrete": 0,
35
  "general": 1
36
  },
37
- "max_position_embeddings": 1024,
38
- "model_type": "bart",
39
- "normalize_before": false,
 
40
  "num_hidden_layers": 12,
41
- "output_past": false,
42
  "pad_token_id": 1,
 
43
  "problem_type": "single_label_classification",
44
- "scale_embedding": false,
45
  "torch_dtype": "float32",
46
  "transformers_version": "4.52.3",
 
47
  "use_cache": true,
48
- "vocab_size": 50265
49
  }
 
1
  {
 
 
 
 
2
  "architectures": [
3
+ "RobertaForSequenceClassification"
4
  ],
5
+ "attention_probs_dropout_prob": 0.0,
6
  "bos_token_id": 0,
7
+ "classifier_dropout": null,
 
 
 
 
 
 
 
 
 
 
 
 
8
  "eos_token_id": 2,
 
9
  "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.0,
12
+ "hidden_size": 768,
13
  "id2label": {
14
  "0": "concrete",
15
  "1": "general"
16
  },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
  "label2id": {
20
  "concrete": 0,
21
  "general": 1
22
  },
23
+ "layer_norm_eps": 1e-05,
24
+ "max_position_embeddings": 514,
25
+ "model_type": "roberta",
26
+ "num_attention_heads": 12,
27
  "num_hidden_layers": 12,
 
28
  "pad_token_id": 1,
29
+ "position_embedding_type": "absolute",
30
  "problem_type": "single_label_classification",
 
31
  "torch_dtype": "float32",
32
  "transformers_version": "4.52.3",
33
+ "type_vocab_size": 1,
34
  "use_cache": true,
35
+ "vocab_size": 50262
36
  }
merges.txt CHANGED
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 sha256:701f37720dce70bca9a902bc20f84275fea74c90d60ae3d14ed92e1a7ca48ac3
3
- size 1629432864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:179804b0ddd716bb1854307485ffcdf1b1a0260acad4a3d6783a1410c7cdb03b
3
+ size 498603608
special_tokens_map.json CHANGED
@@ -1,7 +1,25 @@
1
  {
2
- "bos_token": "<s>",
3
- "cls_token": "<s>",
4
- "eos_token": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "mask_token": {
6
  "content": "<mask>",
7
  "lstrip": true,
@@ -9,7 +27,25 @@
9
  "rstrip": false,
10
  "single_word": false
11
  },
12
- "pad_token": "<pad>",
13
- "sep_token": "</s>",
14
- "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
  "mask_token": {
24
  "content": "<mask>",
25
  "lstrip": true,
 
27
  "rstrip": false,
28
  "single_word": false
29
  },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -33,7 +33,7 @@
33
  "single_word": false,
34
  "special": true
35
  },
36
- "50264": {
37
  "content": "<mask>",
38
  "lstrip": true,
39
  "normalized": true,
@@ -49,10 +49,11 @@
49
  "errors": "replace",
50
  "extra_special_tokens": {},
51
  "mask_token": "<mask>",
52
- "model_max_length": 1024,
 
53
  "pad_token": "<pad>",
54
  "sep_token": "</s>",
55
- "tokenizer_class": "BartTokenizer",
56
  "trim_offsets": true,
57
  "unk_token": "<unk>"
58
  }
 
33
  "single_word": false,
34
  "special": true
35
  },
36
+ "4": {
37
  "content": "<mask>",
38
  "lstrip": true,
39
  "normalized": true,
 
49
  "errors": "replace",
50
  "extra_special_tokens": {},
51
  "mask_token": "<mask>",
52
+ "max_len": 512,
53
+ "model_max_length": 512,
54
  "pad_token": "<pad>",
55
  "sep_token": "</s>",
56
+ "tokenizer_class": "RobertaTokenizer",
57
  "trim_offsets": true,
58
  "unk_token": "<unk>"
59
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1fa43ed8d6f60616f5ba486ea02a88f3120c74d254376330ea7905b833f90496
3
  size 5649
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80a707fe0e0fcf713f4592a0307cf26821ee3d6c93e07d5dbf45f55234821120
3
  size 5649
vocab.json CHANGED
The diff for this file is too large to render. See raw diff