Kalindu commited on
Commit
0532617
1 Parent(s): eca4fbf

SinBerto initial Commit

Browse files
checkpoint-300000/config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 514,
15
+ "model_type": "roberta",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 6,
18
+ "pad_token_id": 1,
19
+ "type_vocab_size": 1,
20
+ "vocab_size": 52000
21
+ }
checkpoint-300000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6d4fb3e887c3f9940c43152adc35409ad487b7987053cf1a077aa586e6d51b2
3
+ size 668101711
checkpoint-300000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3191b05955e2eb5e46dcb4c85eb23fd3f6c650782628c4afb9605a6046d5afd3
3
+ size 336425999
checkpoint-300000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54be9e19e2fe9545d210e41adaa6597eaed98d8812de29d2eb41c956fac7e052
3
+ size 623
checkpoint-300000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9c9584f260fb3cad859574e97347a6d93a69de6d8a1196541b5b551833e78fd
3
+ size 1263
checkpoint-310000/config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 514,
15
+ "model_type": "roberta",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 6,
18
+ "pad_token_id": 1,
19
+ "type_vocab_size": 1,
20
+ "vocab_size": 52000
21
+ }
checkpoint-310000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f9d739bfe9dc3aba341e481d94a5baf42db4496f55747fea2ca51c9f9f7d228
3
+ size 668101711
checkpoint-310000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48f754ad8021b170d828bdac74c9c2e3f9bbffda914b80fbc924804704962681
3
+ size 336425999
checkpoint-310000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91acfc327680b8651495f0d82a80253885248165bef61c58329a9b2360ad686e
3
+ size 623
checkpoint-310000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9c9584f260fb3cad859574e97347a6d93a69de6d8a1196541b5b551833e78fd
3
+ size 1263
config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 514,
15
+ "model_type": "roberta",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 6,
18
+ "pad_token_id": 1,
19
+ "type_vocab_size": 1,
20
+ "vocab_size": 52000
21
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32c2ffbd77e2567477450661d953f633fe1a969fc4836b5d1f1c9cbb2d73a04f
3
+ size 336425999
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9c9584f260fb3cad859574e97347a6d93a69de6d8a1196541b5b551833e78fd
3
+ size 1263
vocab.json ADDED
The diff for this file is too large to render. See raw diff