Hugging Face's logo

bitsanlp
/
simcse_finetuned_100k_128batch

Text Classification
Transformers
PyTorch
TensorBoard
roberta
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
bitsanlp commited on
Commit
3ddeebd
•
1 Parent(s): 15b8cca

Training in progress, step 500

Browse files
Files changed (8) hide show
  1. config.json +1 -1
  2. merges.txt +1 -1
  3. pytorch_model.bin +1 -1
  4. runs/Apr29_07-25-01_592736d17fc2/1682753205.267094/events.out.tfevents.1682753205.592736d17fc2.577.1 +3 -0
  5. runs/Apr29_07-25-01_592736d17fc2/events.out.tfevents.1682753205.592736d17fc2.577.0 +3 -0
  6. tokenizer.json +1 -0
  7. tokenizer_config.json +1 -2
  8. training_args.bin +2 -2
config.json CHANGED
@@ -21,7 +21,7 @@
21
  "position_embedding_type": "absolute",
22
  "problem_type": "single_label_classification",
23
  "torch_dtype": "float32",
24
- "transformers_version": "4.25.1",
25
  "type_vocab_size": 1,
26
  "use_cache": true,
27
  "vocab_size": 50265
 
21
  "position_embedding_type": "absolute",
22
  "problem_type": "single_label_classification",
23
  "torch_dtype": "float32",
24
+ "transformers_version": "4.28.1",
25
  "type_vocab_size": 1,
26
  "use_cache": true,
27
  "vocab_size": 50265
merges.txt CHANGED
@@ -1,4 +1,4 @@
1
- #version: 0.2 - Trained by `huggingface/tokenizers`
2
  Ġ t
3
  Ġ a
4
  h e
 
1
+ #version: 0.2
2
  Ġ t
3
  Ġ a
4
  h e
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2804c76a90000233d615017c02985e2796b5c09ac0cc9b3a8cc40b42ac96f824
3
  size 498662069
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:012201123d500dec536a9dd607f4eabfb4305e537e2aacdebd6369ae300d4d03
3
  size 498662069
runs/Apr29_07-25-01_592736d17fc2/1682753205.267094/events.out.tfevents.1682753205.592736d17fc2.577.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09c4dccdd6d3936b2f6c4f9e6e58548170afba289795b847130fd60c54f289fd
3
+ size 5913
runs/Apr29_07-25-01_592736d17fc2/events.out.tfevents.1682753205.592736d17fc2.577.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1939d35054c905bc241b93792f41ae212b91599d91b3a50052a647c976a47e3d
3
+ size 4250
tokenizer.json CHANGED
@@ -87,6 +87,7 @@
87
  "continuing_subword_prefix": "",
88
  "end_of_word_suffix": "",
89
  "fuse_unk": false,
 
90
  "vocab": {
91
  "<s>": 0,
92
  "<pad>": 1,
 
87
  "continuing_subword_prefix": "",
88
  "end_of_word_suffix": "",
89
  "fuse_unk": false,
90
+ "byte_fallback": false,
91
  "vocab": {
92
  "<s>": 0,
93
  "<pad>": 1,
tokenizer_config.json CHANGED
@@ -1,15 +1,14 @@
1
  {
2
  "add_prefix_space": false,
3
  "bos_token": "<s>",
 
4
  "cls_token": "<s>",
5
  "eos_token": "</s>",
6
  "errors": "replace",
7
  "mask_token": "<mask>",
8
  "model_max_length": 512,
9
- "name_or_path": "bitsanlp/simcse_retrain_edos_100k_128batch",
10
  "pad_token": "<pad>",
11
  "sep_token": "</s>",
12
- "special_tokens_map_file": null,
13
  "tokenizer_class": "RobertaTokenizer",
14
  "trim_offsets": true,
15
  "unk_token": "<unk>"
 
1
  {
2
  "add_prefix_space": false,
3
  "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": true,
5
  "cls_token": "<s>",
6
  "eos_token": "</s>",
7
  "errors": "replace",
8
  "mask_token": "<mask>",
9
  "model_max_length": 512,
 
10
  "pad_token": "<pad>",
11
  "sep_token": "</s>",
 
12
  "tokenizer_class": "RobertaTokenizer",
13
  "trim_offsets": true,
14
  "unk_token": "<unk>"
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55615de62184f5880d3757807375ff5d041b95b9556d0d050197ce0b6978d99d
3
- size 3451
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5d42312830cdad53377e7994b8cd51d01342e90a7a89e0267e09f85852b84a2
3
+ size 3643