Hugging Face's logo

RPygramar
/
admilson

TensorBoard
Safetensors
gpt2
Model card Files
xet
 Metrics Community
RPygramar commited on
Commit
9fe0997
·
verified ·
1 Parent(s): 899e70d

Training in progress, step 2121

Browse files
Files changed (9) hide show
  1. config.json +3 -3
  2. merges.txt +0 -0
  3. model.safetensors +2 -2
  4. runs/Apr16_12-52-41_82cd2a48c9a0/events.out.tfevents.1744807962.82cd2a48c9a0.492.6 +3 -0
  5. special_tokens_map.json +43 -4
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +53 -8
  8. training_args.bin +1 -1
  9. vocab.json +0 -0
config.json CHANGED
@@ -4,9 +4,9 @@
4
  "GPT2LMHeadModel"
5
  ],
6
  "attn_pdrop": 0.1,
7
- "bos_token_id": 50256,
8
  "embd_pdrop": 0.1,
9
- "eos_token_id": 50256,
10
  "initializer_range": 0.02,
11
  "layer_norm_epsilon": 1e-05,
12
  "model_type": "gpt2",
@@ -34,5 +34,5 @@
34
  "torch_dtype": "float32",
35
  "transformers_version": "4.51.1",
36
  "use_cache": true,
37
- "vocab_size": 50257
38
  }
 
4
  "GPT2LMHeadModel"
5
  ],
6
  "attn_pdrop": 0.1,
7
+ "bos_token_id": 0,
8
  "embd_pdrop": 0.1,
9
+ "eos_token_id": 2,
10
  "initializer_range": 0.02,
11
  "layer_norm_epsilon": 1e-05,
12
  "model_type": "gpt2",
 
34
  "torch_dtype": "float32",
35
  "transformers_version": "4.51.1",
36
  "use_cache": true,
37
+ "vocab_size": 30000
38
  }
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 sha256:6c6cebafbd51d29e8260e3c3f28a14d216026d1bd3b83f3fa9b5d4ff2cd89a72
3
- size 497774208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9cc75f19cff72cd33948c937754658103c7b39d50f2eb0651c75c91188872a9
3
+ size 435544704
runs/Apr16_12-52-41_82cd2a48c9a0/events.out.tfevents.1744807962.82cd2a48c9a0.492.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0628bf6c86ccd0310b40bf0f7bb1e876a5f73f36b155d225ec214ddc1629c8b9
3
+ size 5525
special_tokens_map.json CHANGED
@@ -1,6 +1,45 @@
1
  {
2
- "bos_token": "<|endoftext|>",
3
- "eos_token": "<|endoftext|>",
4
- "pad_token": "<|endoftext|>",
5
- "unk_token": "<|endoftext|>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  }
 
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,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": "</s>",
31
+ "sep_token": {
32
+ "content": "</s>",
33
+ "lstrip": false,
34
+ "normalized": true,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ "unk_token": {
39
+ "content": "<unk>",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ }
45
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,21 +1,66 @@
1
  {
2
  "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
- "50256": {
5
- "content": "<|endoftext|>",
6
  "lstrip": false,
7
  "normalized": true,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  }
12
  },
13
- "bos_token": "<|endoftext|>",
14
  "clean_up_tokenization_spaces": false,
15
- "eos_token": "<|endoftext|>",
 
 
16
  "extra_special_tokens": {},
17
- "model_max_length": 1024,
18
- "pad_token": "<|endoftext|>",
19
- "tokenizer_class": "GPT2Tokenizer",
20
- "unk_token": "<|endoftext|>"
 
 
 
 
 
 
 
 
 
 
 
21
  }
 
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
+ "4": {
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": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
  "extra_special_tokens": {},
51
+ "mask_token": "<mask>",
52
+ "max_len": 512,
53
+ "max_length": 512,
54
+ "model_max_length": 512,
55
+ "pad_to_multiple_of": null,
56
+ "pad_token": "</s>",
57
+ "pad_token_type_id": 0,
58
+ "padding_side": "right",
59
+ "sep_token": "</s>",
60
+ "stride": 0,
61
+ "tokenizer_class": "RobertaTokenizer",
62
+ "trim_offsets": true,
63
+ "truncation_side": "right",
64
+ "truncation_strategy": "longest_first",
65
+ "unk_token": "<unk>"
66
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c6ab52c98b6f72b83499a27577608c7a12496aa7ee0227d88df66df1e348ae4
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a614b33909039c42dd64a3c17a29293379425355533cb5cf1a195d5c1e61296b
3
  size 5304
vocab.json CHANGED
The diff for this file is too large to render. See raw diff