ncduy commited on
Commit
609f5df
1 Parent(s): e01bd85

Training in progress, step 500

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
1
+ checkpoint-*/
added_tokens.json ADDED
@@ -0,0 +1 @@
 
1
+ {"<mask>": 64000}
bpe.codes ADDED
The diff for this file is too large to render. See raw diff
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "vinai/phobert-large",
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
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 1024,
14
+ "id2label": {
15
+ "0": "negative",
16
+ "1": "neutral",
17
+ "2": "positive"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 4096,
21
+ "label2id": {
22
+ "negative": 0,
23
+ "neutral": 1,
24
+ "positive": 2
25
+ },
26
+ "layer_norm_eps": 1e-05,
27
+ "max_position_embeddings": 258,
28
+ "model_type": "roberta",
29
+ "num_attention_heads": 16,
30
+ "num_hidden_layers": 24,
31
+ "pad_token_id": 1,
32
+ "position_embedding_type": "absolute",
33
+ "problem_type": "single_label_classification",
34
+ "tokenizer_class": "PhobertTokenizer",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.15.0",
37
+ "type_vocab_size": 1,
38
+ "use_cache": true,
39
+ "vocab_size": 64001
40
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f391efa912ae7c430147515a77f7d94aff974d2664c5ed641f258483cabd0072
3
+ size 1476827437
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 256, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "vinai/phobert-large", "tokenizer_class": "PhobertTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2409af9037a75857a128715364819c5072c7735d2131c0c1803db4b9a9b04c9
3
+ size 2991
vocab.txt ADDED
The diff for this file is too large to render. See raw diff