Hugging Face's logo

SauravMaheshkar
/
rembert-maxseq-384-docstride-135-chaii

Question Answering PyTorch
multilingual kaggle rembert
Model card Files Community
1
SauravMaheshkar commited on
Commit
a12f2d3
•
1 Parent(s): acb3846

Initial Commit

Browse files
Files changed (29) hide show
  1. .gitignore +2 -0
  2. checkpoint-fold-0/config.json +27 -0
  3. checkpoint-fold-0/pytorch_model.bin +3 -0
  4. checkpoint-fold-0/result_dict.json +12 -0
  5. checkpoint-fold-0/sentencepiece.model +3 -0
  6. checkpoint-fold-0/special_tokens_map.json +1 -0
  7. checkpoint-fold-0/tokenizer.json +0 -0
  8. checkpoint-fold-0/tokenizer_config.json +1 -0
  9. checkpoint-fold-1/config.json +27 -0
  10. checkpoint-fold-1/pytorch_model.bin +3 -0
  11. checkpoint-fold-1/result_dict.json +12 -0
  12. checkpoint-fold-1/sentencepiece.model +3 -0
  13. checkpoint-fold-1/special_tokens_map.json +1 -0
  14. checkpoint-fold-1/tokenizer.json +0 -0
  15. checkpoint-fold-1/tokenizer_config.json +1 -0
  16. checkpoint-fold-2/config.json +27 -0
  17. checkpoint-fold-2/pytorch_model.bin +3 -0
  18. checkpoint-fold-2/result_dict.json +12 -0
  19. checkpoint-fold-2/sentencepiece.model +3 -0
  20. checkpoint-fold-2/special_tokens_map.json +1 -0
  21. checkpoint-fold-2/tokenizer.json +0 -0
  22. checkpoint-fold-2/tokenizer_config.json +1 -0
  23. checkpoint-fold-3/config.json +27 -0
  24. checkpoint-fold-3/pytorch_model.bin +3 -0
  25. checkpoint-fold-3/result_dict.json +12 -0
  26. checkpoint-fold-3/sentencepiece.model +3 -0
  27. checkpoint-fold-3/special_tokens_map.json +1 -0
  28. checkpoint-fold-3/tokenizer.json +0 -0
  29. checkpoint-fold-3/tokenizer_config.json +1 -0
.gitignore ADDED
@@ -0,0 +1,2 @@
 
 
1
+ # MacOS Stuff
2
+ **/.DS_Store
checkpoint-fold-0/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/rembert",
3
+ "attention_probs_dropout_prob": 0,
4
+ "bos_token_id": 312,
5
+ "classifier_dropout_prob": 0.1,
6
+ "embedding_dropout_prob": 0,
7
+ "embedding_size": 256,
8
+ "eos_token_id": 313,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0,
11
+ "hidden_size": 1152,
12
+ "initializer_range": 0.02,
13
+ "input_embedding_size": 256,
14
+ "intermediate_size": 4608,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "rembert",
18
+ "num_attention_heads": 18,
19
+ "num_hidden_layers": 32,
20
+ "output_embedding_size": 1664,
21
+ "pad_token_id": 0,
22
+ "tie_word_embeddings": false,
23
+ "transformers_version": "4.11.3",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 250300
27
+ }
checkpoint-fold-0/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e2d7e50e79b9709e208e8a0869ea01c7ac0e6e739af8f98ab680f0f23c0d4ae
3
+ size 2303917083
checkpoint-fold-0/result_dict.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_val_loss": 0.35056131826037973,
3
+ "epoch": [
4
+ 0
5
+ ],
6
+ "train_loss": [
7
+ 0.5945309142361199
8
+ ],
9
+ "val_loss": [
10
+ 0.35056131826037973
11
+ ]
12
+ }
checkpoint-fold-0/sentencepiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67ce12ea4550e57af39217a75686a61695e34edbb1c9892f82f0b861d73a4482
3
+ size 4697711
checkpoint-fold-0/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
checkpoint-fold-0/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
checkpoint-fold-0/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"do_lower_case": false, "remove_space": true, "keep_accents": true, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 256, "special_tokens_map_file": "/root/.cache/huggingface/transformers/d0d5cf448e7367ce69a8cbb48980c788a66b736ec136a0d3061fd26b5c1b25f0.f886166424e457f0fc75f92e81205faabe843b2dbbbef6b25f9d8ec69f64bc7d", "name_or_path": "google/rembert", "tokenizer_class": "RemBertTokenizer"}
checkpoint-fold-1/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/rembert",
3
+ "attention_probs_dropout_prob": 0,
4
+ "bos_token_id": 312,
5
+ "classifier_dropout_prob": 0.1,
6
+ "embedding_dropout_prob": 0,
7
+ "embedding_size": 256,
8
+ "eos_token_id": 313,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0,
11
+ "hidden_size": 1152,
12
+ "initializer_range": 0.02,
13
+ "input_embedding_size": 256,
14
+ "intermediate_size": 4608,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "rembert",
18
+ "num_attention_heads": 18,
19
+ "num_hidden_layers": 32,
20
+ "output_embedding_size": 1664,
21
+ "pad_token_id": 0,
22
+ "tie_word_embeddings": false,
23
+ "transformers_version": "4.11.3",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 250300
27
+ }
checkpoint-fold-1/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:748945294aa92886800f08b9f4fde06bb93d4527817304d7e5f76b5490911ed5
3
+ size 2303917083
checkpoint-fold-1/result_dict.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_val_loss": 0.3837097753951916,
3
+ "epoch": [
4
+ 0
5
+ ],
6
+ "train_loss": [
7
+ 0.6003670649254685
8
+ ],
9
+ "val_loss": [
10
+ 0.3837097753951916
11
+ ]
12
+ }
checkpoint-fold-1/sentencepiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67ce12ea4550e57af39217a75686a61695e34edbb1c9892f82f0b861d73a4482
3
+ size 4697711
checkpoint-fold-1/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
checkpoint-fold-1/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
checkpoint-fold-1/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"do_lower_case": false, "remove_space": true, "keep_accents": true, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 256, "special_tokens_map_file": "/root/.cache/huggingface/transformers/d0d5cf448e7367ce69a8cbb48980c788a66b736ec136a0d3061fd26b5c1b25f0.f886166424e457f0fc75f92e81205faabe843b2dbbbef6b25f9d8ec69f64bc7d", "name_or_path": "google/rembert", "tokenizer_class": "RemBertTokenizer"}
checkpoint-fold-2/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/rembert",
3
+ "attention_probs_dropout_prob": 0,
4
+ "bos_token_id": 312,
5
+ "classifier_dropout_prob": 0.1,
6
+ "embedding_dropout_prob": 0,
7
+ "embedding_size": 256,
8
+ "eos_token_id": 313,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0,
11
+ "hidden_size": 1152,
12
+ "initializer_range": 0.02,
13
+ "input_embedding_size": 256,
14
+ "intermediate_size": 4608,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "rembert",
18
+ "num_attention_heads": 18,
19
+ "num_hidden_layers": 32,
20
+ "output_embedding_size": 1664,
21
+ "pad_token_id": 0,
22
+ "tie_word_embeddings": false,
23
+ "transformers_version": "4.11.3",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 250300
27
+ }
checkpoint-fold-2/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:635ba0ec8c81601e914540bee35b127fa420a0be3a25d5f82cd8999e01e9118f
3
+ size 2303917083
checkpoint-fold-2/result_dict.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_val_loss": 0.3908137973281594,
3
+ "epoch": [
4
+ 0
5
+ ],
6
+ "train_loss": [
7
+ 0.6297821936313961
8
+ ],
9
+ "val_loss": [
10
+ 0.3908137973281594
11
+ ]
12
+ }
checkpoint-fold-2/sentencepiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67ce12ea4550e57af39217a75686a61695e34edbb1c9892f82f0b861d73a4482
3
+ size 4697711
checkpoint-fold-2/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
checkpoint-fold-2/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
checkpoint-fold-2/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"do_lower_case": false, "remove_space": true, "keep_accents": true, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 256, "special_tokens_map_file": "/root/.cache/huggingface/transformers/d0d5cf448e7367ce69a8cbb48980c788a66b736ec136a0d3061fd26b5c1b25f0.f886166424e457f0fc75f92e81205faabe843b2dbbbef6b25f9d8ec69f64bc7d", "name_or_path": "google/rembert", "tokenizer_class": "RemBertTokenizer"}
checkpoint-fold-3/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/rembert",
3
+ "attention_probs_dropout_prob": 0,
4
+ "bos_token_id": 312,
5
+ "classifier_dropout_prob": 0.1,
6
+ "embedding_dropout_prob": 0,
7
+ "embedding_size": 256,
8
+ "eos_token_id": 313,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0,
11
+ "hidden_size": 1152,
12
+ "initializer_range": 0.02,
13
+ "input_embedding_size": 256,
14
+ "intermediate_size": 4608,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "rembert",
18
+ "num_attention_heads": 18,
19
+ "num_hidden_layers": 32,
20
+ "output_embedding_size": 1664,
21
+ "pad_token_id": 0,
22
+ "tie_word_embeddings": false,
23
+ "transformers_version": "4.11.3",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 250300
27
+ }
checkpoint-fold-3/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7b4544c92ff7d2f00e8f663f9da00e12f55347c32592fa1f5c425ca810d206c
3
+ size 2303917083
checkpoint-fold-3/result_dict.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_val_loss": 0.3664754274609202,
3
+ "epoch": [
4
+ 0
5
+ ],
6
+ "train_loss": [
7
+ 0.6167238672575693
8
+ ],
9
+ "val_loss": [
10
+ 0.3664754274609202
11
+ ]
12
+ }
checkpoint-fold-3/sentencepiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67ce12ea4550e57af39217a75686a61695e34edbb1c9892f82f0b861d73a4482
3
+ size 4697711
checkpoint-fold-3/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
checkpoint-fold-3/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
checkpoint-fold-3/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"do_lower_case": false, "remove_space": true, "keep_accents": true, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 256, "special_tokens_map_file": "/root/.cache/huggingface/transformers/d0d5cf448e7367ce69a8cbb48980c788a66b736ec136a0d3061fd26b5c1b25f0.f886166424e457f0fc75f92e81205faabe843b2dbbbef6b25f9d8ec69f64bc7d", "name_or_path": "google/rembert", "tokenizer_class": "RemBertTokenizer"}