nmnghia02 commited on
Commit
93651b8
1 Parent(s): d2303fd

Training in progress, epoch 1

Browse files
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-large",
3
+ "architectures": [
4
+ "RobertaForMultipleChoice"
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": 1024,
13
+ "init_device": "cuda",
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 4096,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 514,
18
+ "model_type": "roberta",
19
+ "num_attention_heads": 16,
20
+ "num_hidden_layers": 24,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.36.0.dev0",
25
+ "type_vocab_size": 1,
26
+ "use_cache": false,
27
+ "vocab_size": 50265
28
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:015e6691d4082518d04d92a11db2986113733529e9390391af6d8c20c47a0d71
3
+ size 710769874
runs/Nov29_03-19-08_d1a0b22be37b/events.out.tfevents.1701227956.d1a0b22be37b.1255.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c4bd506df7bf7042afbb4946fdcced50085005102fcb2980f9c9046ceb7fa9f
3
+ size 4287
runs/Nov29_03-35-01_d1a0b22be37b/events.out.tfevents.1701228904.d1a0b22be37b.6863.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b34590d35f1ce7035afe21a3bda936dc2abbc5481cdbcc54f560a54f3ffb114
3
+ size 4791
special_tokens_map.json CHANGED
@@ -1,21 +1,15 @@
1
  {
2
- "bos_token": "[CLS]",
3
- "cls_token": "[CLS]",
4
- "eos_token": "[SEP]",
5
- "mask_token": "[MASK]",
6
- "pad_token": {
7
- "content": "[PAD]",
8
- "lstrip": false,
9
  "normalized": false,
10
  "rstrip": false,
11
  "single_word": false
12
  },
13
- "sep_token": "[SEP]",
14
- "unk_token": {
15
- "content": "[UNK]",
16
- "lstrip": false,
17
- "normalized": true,
18
- "rstrip": false,
19
- "single_word": false
20
- }
21
  }
 
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
@@ -1,58 +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
  "1": {
12
- "content": "[CLS]",
13
  "lstrip": false,
14
- "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
18
  },
19
  "2": {
20
- "content": "[SEP]",
21
  "lstrip": false,
22
- "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  },
27
  "3": {
28
- "content": "[UNK]",
29
  "lstrip": false,
30
  "normalized": true,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
- "128000": {
36
- "content": "[MASK]",
37
- "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
42
  }
43
  },
44
- "bos_token": "[CLS]",
45
  "clean_up_tokenization_spaces": true,
46
- "cls_token": "[CLS]",
47
- "do_lower_case": false,
48
- "eos_token": "[SEP]",
49
- "mask_token": "[MASK]",
50
- "model_max_length": 1000000000000000019884624838656,
51
- "pad_token": "[PAD]",
52
- "sep_token": "[SEP]",
53
- "sp_model_kwargs": {},
54
- "split_by_punct": false,
55
- "tokenizer_class": "DebertaV2Tokenizer",
56
- "unk_token": "[UNK]",
57
- "vocab_type": "spm"
58
  }
 
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:a1bc5559e40d902b971a1bf97fc60717d2f1f1c1e0c70289aef29c4ef2117eee
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6462290aa21dead58a5f6a6360966982c38be9fbad7f348506fb63b04d7df199
3
  size 4664
vocab.json ADDED
The diff for this file is too large to render. See raw diff