SauravMaheshkar
commited on
Commit
•
fa0de67
1
Parent(s):
94ad056
Initial Commit
Browse files- .gitignore +2 -0
- checkpoint-fold-0/config.json +27 -0
- checkpoint-fold-0/pytorch_model.bin +3 -0
- checkpoint-fold-0/result_dict.json +12 -0
- checkpoint-fold-0/sentencepiece.model +3 -0
- checkpoint-fold-0/special_tokens_map.json +1 -0
- checkpoint-fold-0/tokenizer.json +0 -0
- checkpoint-fold-0/tokenizer_config.json +1 -0
- checkpoint-fold-1/config.json +27 -0
- checkpoint-fold-1/pytorch_model.bin +3 -0
- checkpoint-fold-1/result_dict.json +12 -0
- checkpoint-fold-1/sentencepiece.model +3 -0
- checkpoint-fold-1/special_tokens_map.json +1 -0
- checkpoint-fold-1/tokenizer.json +0 -0
- checkpoint-fold-1/tokenizer_config.json +1 -0
- checkpoint-fold-2/config.json +27 -0
- checkpoint-fold-2/pytorch_model.bin +3 -0
- checkpoint-fold-2/result_dict.json +12 -0
- checkpoint-fold-2/sentencepiece.model +3 -0
- checkpoint-fold-2/special_tokens_map.json +1 -0
- checkpoint-fold-2/tokenizer.json +0 -0
- checkpoint-fold-2/tokenizer_config.json +1 -0
- checkpoint-fold-3/config.json +27 -0
- checkpoint-fold-3/pytorch_model.bin +3 -0
- checkpoint-fold-3/result_dict.json +12 -0
- checkpoint-fold-3/sentencepiece.model +3 -0
- checkpoint-fold-3/special_tokens_map.json +1 -0
- checkpoint-fold-3/tokenizer.json +0 -0
- 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 sha256:7fcb92758edef9494ef4b17dbf4d52e7860be2c10dbcd930846ba1728786dfca
|
3 |
+
size 2303917083
|
checkpoint-fold-0/result_dict.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_val_loss": 0.3688944876321237,
|
3 |
+
"epoch": [
|
4 |
+
0
|
5 |
+
],
|
6 |
+
"train_loss": [
|
7 |
+
0.6384444586051864
|
8 |
+
],
|
9 |
+
"val_loss": [
|
10 |
+
0.3688944876321237
|
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-400-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:a5bebe8218d688a44431f40f01191b688c58283a1ccf75aef5d62c2e33990433
|
3 |
+
size 2303917083
|
checkpoint-fold-1/result_dict.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_val_loss": 0.4056796637166171,
|
3 |
+
"epoch": [
|
4 |
+
0
|
5 |
+
],
|
6 |
+
"train_loss": [
|
7 |
+
0.6327483699313406
|
8 |
+
],
|
9 |
+
"val_loss": [
|
10 |
+
0.4056796637166171
|
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-400-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 sha256:7c7412abeba8e554f906c5f7769cd77e3a20f4a47ac087e85e198648c2af7f8f
|
3 |
+
size 2303917083
|
checkpoint-fold-2/result_dict.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_val_loss": 0.41891026493140116,
|
3 |
+
"epoch": [
|
4 |
+
0
|
5 |
+
],
|
6 |
+
"train_loss": [
|
7 |
+
0.6153255529510426
|
8 |
+
],
|
9 |
+
"val_loss": [
|
10 |
+
0.41891026493140116
|
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-400-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:b378437677b9f418070ce20bf93b95f694cb5cc126aa36cdc5af07911998a31e
|
3 |
+
size 2303917083
|
checkpoint-fold-3/result_dict.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_val_loss": 0.4171063236170767,
|
3 |
+
"epoch": [
|
4 |
+
0
|
5 |
+
],
|
6 |
+
"train_loss": [
|
7 |
+
0.6352067099583916
|
8 |
+
],
|
9 |
+
"val_loss": [
|
10 |
+
0.4171063236170767
|
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-400-docstride-128-chaii/checkpoint-fold-3/special_tokens_map.json", "name_or_path": "google/rembert", "tokenizer_class": "RemBertTokenizer"}
|