Hugging Face's logo

burcucan
/
codeparrot-ds

Text Generation
Transformers
TensorBoard
Safetensors
opt
text-generation-inference
Model card Files
xet
 Metrics Community
burcucan commited on
Commit
f158f38
·
verified ·
1 Parent(s): 0a4bd06

Training in progress, step 5000

Browse files
Files changed (12) hide show
  1. config.json +1 -1
  2. model.safetensors +1 -1
  3. runs/May01_14-28-49_a92bf2eb7ffa/events.out.tfevents.1714573729.a92bf2eb7ffa.2200.0 +3 -0
  4. runs/May01_14-36-08_a92bf2eb7ffa/events.out.tfevents.1714574169.a92bf2eb7ffa.4577.0 +3 -0
  5. runs/May01_14-40-59_a92bf2eb7ffa/events.out.tfevents.1714574459.a92bf2eb7ffa.5886.0 +3 -0
  6. runs/May01_14-41-08_a92bf2eb7ffa/events.out.tfevents.1714574468.a92bf2eb7ffa.5886.1 +3 -0
  7. runs/May01_14-48-08_a92bf2eb7ffa/events.out.tfevents.1714574888.a92bf2eb7ffa.5886.2 +3 -0
  8. special_tokens_map.json +5 -4
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +45 -10
  11. training_args.bin +2 -2
  12. vocab.txt +0 -0
config.json CHANGED
@@ -21,7 +21,7 @@
21
  "num_hidden_layers": 4,
22
  "pad_token_id": 1,
23
  "torch_dtype": "float32",
24
- "transformers_version": "4.39.3",
25
  "use_cache": true,
26
  "vocab_size": 50272,
27
  "word_embed_proj_dim": 768
 
21
  "num_hidden_layers": 4,
22
  "pad_token_id": 1,
23
  "torch_dtype": "float32",
24
+ "transformers_version": "4.40.1",
25
  "use_cache": true,
26
  "vocab_size": 50272,
27
  "word_embed_proj_dim": 768
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f663c891a8870fbf25c25890ca26b14b495e602671913b72770c58cb1df2afc6
3
  size 161757984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:384b6e7e3983c9631856ea5b9fc35e5caccd2bfe6e7d8c944957e561643ecda0
3
  size 161757984
runs/May01_14-28-49_a92bf2eb7ffa/events.out.tfevents.1714573729.a92bf2eb7ffa.2200.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae238be4d23fa4933cdc16d972956b6ead903748635896631d2ea9f0671e13b7
3
+ size 4600
runs/May01_14-36-08_a92bf2eb7ffa/events.out.tfevents.1714574169.a92bf2eb7ffa.4577.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:110e0ebcf5958804b92fe13a3d3a22b819662aeb55664c2bae98fd2e0e401098
3
+ size 4600
runs/May01_14-40-59_a92bf2eb7ffa/events.out.tfevents.1714574459.a92bf2eb7ffa.5886.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b141768bc709530755e924bc5a095617dbd19f1cb8a942e01948739dfd6cc46
3
+ size 4600
runs/May01_14-41-08_a92bf2eb7ffa/events.out.tfevents.1714574468.a92bf2eb7ffa.5886.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c565c09ad2813a6cc3f0ec42804f24b0f9bbf15e03907ab5980884822388c18
3
+ size 4600
runs/May01_14-48-08_a92bf2eb7ffa/events.out.tfevents.1714574888.a92bf2eb7ffa.5886.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9f811c24d4e41d3eab4fef4ca53aa4e44db5201e7b4c1acbf96bac40a0aa533
3
+ size 5082
special_tokens_map.json CHANGED
@@ -1,6 +1,7 @@
1
  {
2
- "bos_token": "<|endoftext|>",
3
- "eos_token": "<|endoftext|>",
4
- "pad_token": "<|endoftext|>",
5
- "unk_token": "<|endoftext|>"
 
6
  }
 
1
  {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,20 +1,55 @@
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": true,
15
- "eos_token": "<|endoftext|>",
16
- "model_max_length": 1024,
17
- "pad_token": "<|endoftext|>",
18
- "tokenizer_class": "GPT2Tokenizer",
19
- "unk_token": "<|endoftext|>"
 
 
 
 
 
20
  }
 
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
42
  }
43
  },
 
44
  "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c95ed6701116ee7b8a8b7a245b0e5735fc6fa102fbb496a7484a4146c747ed8
3
- size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51f2255d4932b7c335148f25556352c80872b7bc035c4fd097b6953e4d8ed174
3
+ size 4984
vocab.txt ADDED
The diff for this file is too large to render. See raw diff