J4Q8 commited on
Commit
6305214
1 Parent(s): 7ed7ec2

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "J4Q8/my_awesome_cosmos_model",
3
+ "architectures": [
4
+ "BertForMultipleChoice"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.28.0",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4933482480db2106292508cec4584dcb0db681ad0ec98784de2d478b8667b750
3
+ size 438004853
runs/May22_09-40-46_deb4efbd2d88/1684748456.1725414/events.out.tfevents.1684748456.deb4efbd2d88.849.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:756459b9303ad8b5cf7974f8a55b79f59bb63076f0399a8c9b97227f558420ea
3
+ size 5918
runs/May22_09-40-46_deb4efbd2d88/events.out.tfevents.1684748456.deb4efbd2d88.849.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b5ff54a29c5a6128f6168dd9e42db38ae6ac6c943ea7a24fcdd2eda9301767d
3
+ size 4234
runs/May22_09-42-40_deb4efbd2d88/1684748563.1067514/events.out.tfevents.1684748563.deb4efbd2d88.849.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:013acd46ffe7f9930de07f9728f2505691626ea86c9089d924c87960b253f63d
3
+ size 5918
runs/May22_09-42-40_deb4efbd2d88/events.out.tfevents.1684748563.deb4efbd2d88.849.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:add869563de1d1bacbc72fff9498d07f1d64c7c069ea489f2d5becc11e3aedbc
3
+ size 5342
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 512,
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "strip_accents": null,
10
+ "tokenize_chinese_chars": true,
11
+ "tokenizer_class": "BertTokenizer",
12
+ "unk_token": "[UNK]"
13
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1003138185930e77de14d2a54838cb1b89b871b8f8fdc26c13df0ff63e344fe
3
+ size 3643
vocab.txt ADDED
The diff for this file is too large to render. See raw diff