juancavallotti commited on
Commit
84b310d
1 Parent(s): a524cc2

Training in progress, epoch 1

Browse files
config.json CHANGED
@@ -1,37 +1,26 @@
1
  {
2
- "_name_or_path": "juancavallotti/distilroberta-base-culinary",
3
- "activation": "gelu",
4
  "architectures": [
5
- "DistilBertForSequenceClassification"
6
  ],
7
- "attention_dropout": 0.1,
8
- "dim": 768,
9
- "dropout": 0.1,
10
- "hidden_dim": 3072,
11
- "id2label": {
12
- "0": "unrelated",
13
- "1": "related"
14
- },
15
  "initializer_range": 0.02,
16
- "label2id": {
17
- "related": [
18
- 1
19
- ],
20
- "unrelated": [
21
- 0
22
- ]
23
- },
24
  "max_position_embeddings": 512,
25
- "model_type": "distilbert",
26
- "n_heads": 12,
27
- "n_layers": 6,
28
  "pad_token_id": 0,
29
- "problem_type": "single_label_classification",
30
- "qa_dropout": 0.1,
31
- "seq_classif_dropout": 0.2,
32
- "sinusoidal_pos_embds": false,
33
- "tie_weights_": true,
34
  "torch_dtype": "float32",
35
  "transformers_version": "4.18.0",
 
 
36
  "vocab_size": 30522
37
  }
 
1
  {
2
+ "_name_or_path": "bert-base-uncased",
 
3
  "architectures": [
4
+ "BertForMaskedLM"
5
  ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
 
 
12
  "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
 
 
 
 
 
 
15
  "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
  "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
 
 
 
 
21
  "torch_dtype": "float32",
22
  "transformers_version": "4.18.0",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
  "vocab_size": 30522
26
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d4fc340213826a36e48235e9e2b19ef78a8816a35d90051fa519f06405f3c9d
3
- size 267854321
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:527c9e31e5f679d2ee22127548966d7450b3eb1c5ccef5a52497263bd4a3883d
3
+ size 438128811
runs/Apr27_23-55-48_074656075aa4/1651103864.333078/events.out.tfevents.1651103864.074656075aa4.96.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a5cc503160e567209bf6814631f1cf8f5fb417fcac72a69386c3fe92fc7986e
3
+ size 4912
runs/Apr27_23-55-48_074656075aa4/events.out.tfevents.1651103864.074656075aa4.96.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bee70674d378cf1cc28b659ed34c993e387c37e654efe48174b797120589c57
3
+ size 26787
tokenizer_config.json CHANGED
@@ -1 +1 @@
1
- {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "juancavallotti/distilroberta-base-culinary", "tokenizer_class": "DistilBertTokenizer"}
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-uncased", "tokenizer_class": "BertTokenizer"}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9bccb82e93e5649e92c2784209a78a0db13ef44306199a3d81b32e87504055af
3
  size 3119
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ec408bab402014fdb2130b50c5baecddadf25e740f611f6e0ec8a400bd66bf4
3
  size 3119