SauravMaheshkar commited on
Commit
4a30723
1 Parent(s): 8be7713

Initial Commit

Browse files
.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:f557117dc2d9456600767f89484e9c3c513ad34cc7675aafba96ce572af474a4
3
+ size 2303917083
checkpoint-fold-0/result_dict.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_val_loss": 0.3669051616245515,
3
+ "epoch": [
4
+ 0
5
+ ],
6
+ "train_loss": [
7
+ 0.6209910749581079
8
+ ],
9
+ "val_loss": [
10
+ 0.3669051616245515
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": "SauravMaheshkar/rembert-maxseq-384-docstride-128-chaii/checkpoint-fold-0/special_tokens_map.json", "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:bf90effc3f23c83dcb11397febd97be5a623fb075ae199c1dd725f984c6885a4
3
+ size 2303917083
checkpoint-fold-1/result_dict.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_val_loss": 0.38460480150028975,
3
+ "epoch": [
4
+ 0
5
+ ],
6
+ "train_loss": [
7
+ 0.6068687927800378
8
+ ],
9
+ "val_loss": [
10
+ 0.38460480150028975
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": "SauravMaheshkar/rembert-maxseq-384-docstride-128-chaii/checkpoint-fold-1/special_tokens_map.json", "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:ecc48f240be46a2824a28e6060ffc06a560e9d028f292a34a0d89a57935c72c3
3
+ size 2303917083
checkpoint-fold-2/result_dict.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_val_loss": 0.37014211892720533,
3
+ "epoch": [
4
+ 0
5
+ ],
6
+ "train_loss": [
7
+ 0.6895470289407112
8
+ ],
9
+ "val_loss": [
10
+ 0.37014211892720533
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": "SauravMaheshkar/rembert-maxseq-384-docstride-128-chaii/checkpoint-fold-2/special_tokens_map.json", "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 sha256:4dec3c34977219501b558c0306273564c6fcf862f15ffdcd33c3a3ba2f67110a
3
+ size 2303917083
checkpoint-fold-3/result_dict.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_val_loss": 0.3932758030970136,
3
+ "epoch": [
4
+ 0
5
+ ],
6
+ "train_loss": [
7
+ 0.6031655376991026
8
+ ],
9
+ "val_loss": [
10
+ 0.3932758030970136
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": "SauravMaheshkar/rembert-maxseq-384-docstride-128-chaii/checkpoint-fold-3/special_tokens_map.json", "name_or_path": "google/rembert", "tokenizer_class": "RemBertTokenizer"}