Hugging Face's logo

AryaSuprana
/
BRATA_RoBERTaBali

Fill-Mask
Transformers
PyTorch
TensorBoard
Balinese
roberta
Inference Endpoints
Model card Files Metrics Community
AryaSuprana commited on
Commit
66f2d9e
•
1 Parent(s): d0d2fc8

First Commit

Browse files
Files changed (20) hide show
  1. checkpoint-680000/config.json +26 -0
  2. checkpoint-680000/pytorch_model.bin +3 -0
  3. checkpoint-680000/rng_state.pth +3 -0
  4. checkpoint-680000/scheduler.pt +3 -0
  5. checkpoint-680000/trainer_state.json +0 -0
  6. checkpoint-680000/training_args.bin +3 -0
  7. checkpoint-690000/config.json +26 -0
  8. checkpoint-690000/optimizer.pt +3 -0
  9. checkpoint-690000/pytorch_model.bin +3 -0
  10. checkpoint-690000/rng_state.pth +3 -0
  11. checkpoint-690000/scheduler.pt +3 -0
  12. checkpoint-690000/trainer_state.json +0 -0
  13. checkpoint-690000/training_args.bin +3 -0
  14. config.json +26 -0
  15. merges.txt +0 -0
  16. pytorch_model.bin +3 -0
  17. runs/Jun05_23-50-41_3eb1a733f0f3/1654473063.833254/events.out.tfevents.1654473063.3eb1a733f0f3.81.1 +3 -0
  18. runs/Jun05_23-50-41_3eb1a733f0f3/events.out.tfevents.1654473063.3eb1a733f0f3.81.0 +3 -0
  19. training_args.bin +3 -0
  20. vocab.json +0 -0
checkpoint-680000/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
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": 514,
16
+ "model_type": "roberta",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 6,
19
+ "pad_token_id": 1,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.20.0.dev0",
23
+ "type_vocab_size": 1,
24
+ "use_cache": true,
25
+ "vocab_size": 52000
26
+ }
checkpoint-680000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39223301362b64aa41f7c63bfe659109efc8654c9e179af51d5b18d43d434c46
3
+ size 334056939
checkpoint-680000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7627ac381a7a2b1ffa494a8c9e33d4bef40bfa0b6ac079641a642dfaa7b636a6
3
+ size 14503
checkpoint-680000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98b6c27691f048f1c622a36218de5f94b61436f19fefb475ee58e39cc6339088
3
+ size 623
checkpoint-680000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-680000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c330d92484b7284933d752fca457354879fb35019eb40621587ae6ad29f482ac
3
+ size 3183
checkpoint-690000/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
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": 514,
16
+ "model_type": "roberta",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 6,
19
+ "pad_token_id": 1,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.20.0.dev0",
23
+ "type_vocab_size": 1,
24
+ "use_cache": true,
25
+ "vocab_size": 52000
26
+ }
checkpoint-690000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42fcf60da00cf93021baa4cba8956c65ad62e40b49102fce8f0fc8cf5f05714b
3
+ size 668096665
checkpoint-690000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8c5b6c3d15c7950f367c21b90769ec6c8abdb674bbc46fbaa4e608b4bc0f6ce
3
+ size 334056939
checkpoint-690000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa36c3e0fd98761f6cab8d88eee00161a8dc4c6fc2a98a4f3f78dd444b93d8ad
3
+ size 14503
checkpoint-690000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:035e3f8d1c1a58f5ee7758a28737a2bff38bb6f7f45d57c74539269efa6384bc
3
+ size 623
checkpoint-690000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-690000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c330d92484b7284933d752fca457354879fb35019eb40621587ae6ad29f482ac
3
+ size 3183
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
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": 514,
16
+ "model_type": "roberta",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 6,
19
+ "pad_token_id": 1,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.20.0.dev0",
23
+ "type_vocab_size": 1,
24
+ "use_cache": true,
25
+ "vocab_size": 52000
26
+ }
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 sha256:79c30cbdc9d7cbcfe6a3106619c181dc8e11d588cc500f0361e9b8a36b221221
3
+ size 334056939
runs/Jun05_23-50-41_3eb1a733f0f3/1654473063.833254/events.out.tfevents.1654473063.3eb1a733f0f3.81.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52520b560b7203a24149994721bae62b58cbcad92ba9b4d6531931a424dd291a
3
+ size 5170
runs/Jun05_23-50-41_3eb1a733f0f3/events.out.tfevents.1654473063.3eb1a733f0f3.81.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d25d9f7febd2647dc5992aad4567b05041a42c1209d9fe6a9b2b05b69547b761
3
+ size 224484
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c330d92484b7284933d752fca457354879fb35019eb40621587ae6ad29f482ac
3
+ size 3183
vocab.json ADDED
The diff for this file is too large to render. See raw diff