Hugging Face's logo

binhquoc
/
vi_deberta_base

Fill-Mask
Transformers
PyTorch
deberta-v2
Inference Endpoints
Model card Files Community
1
binhquoc commited on
Commit
7a7852f
•
1 Parent(s): 06602f4

commit files to HF hub

Browse files
Files changed (11) hide show
  1. config.json +30 -0
  2. deberta_result.log +23 -0
  3. dict.txt +0 -0
  4. pytorch_model.bin +3 -0
  5. sentencepiece.bpe.model +3 -0
  6. special_tokens_map.json +15 -0
  7. tokenizer_config.json +21 -0
  8. vi_deberta_base_checkpoint_1.pt +3 -0
  9. vi_deberta_base_checkpoint_2.pt +3 -0
  10. vi_deberta_base_checkpoint_3.pt +3 -0
  11. vi_deberta_base_checkpoint_4.pt +3 -0
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DebertaV2ForMaskedLM"
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-07,
14
+ "max_position_embeddings": 512,
15
+ "max_relative_positions": -1,
16
+ "model_type": "deberta-v2",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 1,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 768,
23
+ "pos_att_type": null,
24
+ "position_biased_input": true,
25
+ "relative_attention": false,
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.21.2",
28
+ "type_vocab_size": 0,
29
+ "vocab_size": 40030
30
+ }
deberta_result.log ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Before load dataset, RAM used: 0.36 GB | Avaiable: 200.44 GB | Left: 200.08 GB
2
+ After load dataset, RAM used: 0.61 GB | Avaiable: 200.42 GB | Left: 199.80 GB
3
+ After Prepare Dataloader, RAM used: 6.94 GB | Avaiable: 203.21 GB | Left: 196.27 GB
4
+ After epoch 1, RAM used: 27.96 GB | Avaiable: 206.69 GB | Left: 178.73 GB
5
+
6
+ >>> Epoch 1: Perplexity: 8.71756492102604 Loss: 1.987068991905017
7
+ Loss improved inf -> 1.987068991905017
8
+ Saved training checkpoint
9
+ After epoch 2, RAM used: 32.61 GB | Avaiable: 217.10 GB | Left: 184.49 GB
10
+
11
+ >>> Epoch 2: Perplexity: 6.334900481327126 Loss: 1.7609998571673966
12
+ Loss improved 1.987068991905017 -> 1.7609998571673966
13
+ Saved training checkpoint
14
+ After epoch 3, RAM used: 32.60 GB | Avaiable: 220.86 GB | Left: 188.26 GB
15
+
16
+ >>> Epoch 3: Perplexity: 5.783759349968259 Loss: 1.714263437903529
17
+ Loss improved 1.7609998571673966 -> 1.714263437903529
18
+ Saved training checkpoint
19
+ After epoch 4, RAM used: 32.33 GB | Avaiable: 192.09 GB | Left: 159.77 GB
20
+
21
+ >>> Epoch 4: Perplexity: 4.530374708434244 Loss: 1.5004713556098934
22
+ Loss improved 1.714263437903529 -> 1.5004713556098934
23
+ Saved training checkpoint
dict.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 sha256:4055da3ac6a0a8e5518e75bf98eb16ed89392f54dbf0e284405431f62c3d1276
3
+ size 467369837
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "__type": "AddedToken",
7
+ "content": "<mask>",
8
+ "lstrip": true,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "model_max_length": 1024,
14
+ "name_or_path": "vinai/bartpho-syllable",
15
+ "pad_token": "<pad>",
16
+ "sep_token": "</s>",
17
+ "sp_model_kwargs": {},
18
+ "special_tokens_map_file": null,
19
+ "tokenizer_class": "BartphoTokenizer",
20
+ "unk_token": "<unk>"
21
+ }
vi_deberta_base_checkpoint_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b95eb38bd4284fe8e903d597f9ee4ed4dd3727e7f72d1d7d47f465eecc6670d6
3
+ size 467404461
vi_deberta_base_checkpoint_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4db46a06d68e91dae13800e2fa2c9040bf6328f683c5c996cf10f60397c4337
3
+ size 467404525
vi_deberta_base_checkpoint_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3c1bf31db23b9de01ee09b25f9e1deb0412725236e06adc20283254790a0b46
3
+ size 467404525
vi_deberta_base_checkpoint_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8fe8ce12c371a2f3a9b5d14452cc50c2c86138f2f7004339e3e67a61c53ee8a
3
+ size 467404525