Hugging Face's logo

dafqi
/
GPT2-Rating-Prediction

Text Classification
Transformers
TensorBoard
Safetensors
gpt2
text-generation-inference
Model card Files
xet
Metrics Community
dafqi commited on
Commit
0c741a6
·
verified ·
1 Parent(s): 3673f08

Training in progress, step 93

Browse files
Files changed (10) hide show
  1. config.json +1 -7
  2. merges.txt +0 -0
  3. model.safetensors +1 -1
  4. runs/Mar12_19-51-10_843c610b4f8b/events.out.tfevents.1710273073.843c610b4f8b.104.2 +2 -2
  5. runs/Mar12_20-02-30_843c610b4f8b/events.out.tfevents.1710273757.843c610b4f8b.104.3 +3 -0
  6. special_tokens_map.json +21 -3
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +5 -2
  9. training_args.bin +1 -1
  10. vocab.json +0 -0
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "openai-community/gpt2",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPT2ForSequenceClassification"
@@ -42,12 +42,6 @@
42
  "summary_proj_to_labels": true,
43
  "summary_type": "cls_index",
44
  "summary_use_proj": true,
45
- "task_specific_params": {
46
- "text-generation": {
47
- "do_sample": true,
48
- "max_length": 50
49
- }
50
- },
51
  "torch_dtype": "float32",
52
  "transformers_version": "4.38.1",
53
  "use_cache": true,
 
1
  {
2
+ "_name_or_path": "cahya/gpt2-small-indonesian-522M",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPT2ForSequenceClassification"
 
42
  "summary_proj_to_labels": true,
43
  "summary_type": "cls_index",
44
  "summary_use_proj": true,
 
 
 
 
 
 
45
  "torch_dtype": "float32",
46
  "transformers_version": "4.38.1",
47
  "use_cache": true,
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:c73546a92687040a8383613ad054243024ef7f22803bc48fd6a7645c446928dc
3
  size 497789648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:900ac1cb4ff368a52aa3482b4195a0f7f9bb67751536304d5a5ae2eee5163b2a
3
  size 497789648
runs/Mar12_19-51-10_843c610b4f8b/events.out.tfevents.1710273073.843c610b4f8b.104.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8698ba3f0ffcef4fe5fec61b1416f47b71decf6560e182eda8c2706f127cec2f
3
- size 95930
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f21dd834c5bd8effa04aded31f81897835c4c287b69b04983f48e800ae446af8
3
+ size 104091
runs/Mar12_20-02-30_843c610b4f8b/events.out.tfevents.1710273757.843c610b4f8b.104.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:722733eb2291baf0376c11228c4c7a812183c9094a9af2dbf32c0c2500db838d
3
+ size 14869
special_tokens_map.json CHANGED
@@ -1,6 +1,24 @@
1
  {
2
- "bos_token": "<|endoftext|>",
3
- "eos_token": "<|endoftext|>",
 
 
 
 
 
 
 
 
 
 
 
 
4
  "pad_token": "<|endoftext|>",
5
- "unk_token": "<|endoftext|>"
 
 
 
 
 
 
6
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
  "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,7 +1,8 @@
1
  {
 
2
  "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
- "50256": {
5
  "content": "<|endoftext|>",
6
  "lstrip": false,
7
  "normalized": true,
@@ -13,7 +14,9 @@
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|>"
 
1
  {
2
+ "add_bos_token": false,
3
  "add_prefix_space": false,
4
  "added_tokens_decoder": {
5
+ "0": {
6
  "content": "<|endoftext|>",
7
  "lstrip": false,
8
  "normalized": true,
 
14
  "bos_token": "<|endoftext|>",
15
  "clean_up_tokenization_spaces": true,
16
  "eos_token": "<|endoftext|>",
17
+ "errors": "replace",
18
+ "max_len": 512,
19
+ "model_max_length": 512,
20
  "pad_token": "<|endoftext|>",
21
  "tokenizer_class": "GPT2Tokenizer",
22
  "unk_token": "<|endoftext|>"
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d44a77e82a579cd88e35855b1582a6d58f18cce2e1bb35ce820e759f7cf98c1
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f16d61299382f844ffc596831f498a8f0544a822fdb608587cf9e62f8b6d163c
3
  size 4920
vocab.json CHANGED
The diff for this file is too large to render. See raw diff