Hugging Face's logo

MikeGreen2710
/
pretrained_checkpoints

Safetensors
Model card Files
xet
 Community
MikeGreen2710 commited on
Commit
921b8da
·
verified ·
1 Parent(s): 084c7fa

Upload DAPT checkpoint: Fsoft-AIC__videberta-base

Browse files
Files changed (7) hide show
  1. Fsoft-AIC__videberta-base/.ipynb_checkpoints/pretrain_metadata-checkpoint.json +10 -0
  2. Fsoft-AIC__videberta-base/config.json +40 -0
  3. Fsoft-AIC__videberta-base/model.safetensors +3 -0
  4. Fsoft-AIC__videberta-base/pretrain_metadata.json +10 -0
  5. Fsoft-AIC__videberta-base/tokenizer.json +0 -0
  6. Fsoft-AIC__videberta-base/tokenizer_config.json +20 -0
  7. Fsoft-AIC__videberta-base/training_args.bin +3 -0
Fsoft-AIC__videberta-base/.ipynb_checkpoints/pretrain_metadata-checkpoint.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_name": "Fsoft-AIC/videberta-base",
3
+ "perplexity": 2.8372,
4
+ "eval_loss": 1.042816,
5
+ "mlm_probability": 0.15,
6
+ "whole_word_masking": false,
7
+ "max_steps": 500000,
8
+ "learning_rate": 2e-05,
9
+ "pretrained_at": "2026-05-15 09:57:22"
10
+ }
Fsoft-AIC__videberta-base/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DebertaV2ForMaskedLM"
4
+ ],
5
+ "attention_head_size": 64,
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": null,
8
+ "dtype": "float32",
9
+ "eos_token_id": null,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-07,
16
+ "legacy": true,
17
+ "max_position_embeddings": 512,
18
+ "max_relative_positions": -1,
19
+ "model_type": "deberta-v2",
20
+ "norm_rel_ebd": "layer_norm",
21
+ "num_attention_heads": 12,
22
+ "num_hidden_layers": 12,
23
+ "pad_token_id": 0,
24
+ "pooler_dropout": 0.0,
25
+ "pooler_hidden_act": "gelu",
26
+ "pooler_hidden_size": 768,
27
+ "pos_att_type": [
28
+ "p2c",
29
+ "c2p"
30
+ ],
31
+ "position_biased_input": false,
32
+ "position_buckets": 256,
33
+ "relative_attention": true,
34
+ "share_att_key": true,
35
+ "tie_word_embeddings": true,
36
+ "transformers_version": "5.8.0",
37
+ "type_vocab_size": 0,
38
+ "use_cache": false,
39
+ "vocab_size": 128000
40
+ }
Fsoft-AIC__videberta-base/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9956baf55d9d3e5f793bef68dd449bc41ee97dbb9ca8d4459659c207229d5cb
3
+ size 737924256
Fsoft-AIC__videberta-base/pretrain_metadata.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_name": "Fsoft-AIC/videberta-base",
3
+ "perplexity": 2.8372,
4
+ "eval_loss": 1.042816,
5
+ "mlm_probability": 0.15,
6
+ "whole_word_masking": false,
7
+ "max_steps": 500000,
8
+ "learning_rate": 2e-05,
9
+ "pretrained_at": "2026-05-15 09:57:22"
10
+ }
Fsoft-AIC__videberta-base/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
Fsoft-AIC__videberta-base/tokenizer_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "bos_token": "[CLS]",
5
+ "cls_token": "[CLS]",
6
+ "do_lower_case": false,
7
+ "eos_token": "[SEP]",
8
+ "is_local": false,
9
+ "local_files_only": false,
10
+ "mask_token": "[MASK]",
11
+ "model_max_length": 1000000000000000019884624838656,
12
+ "pad_token": "[PAD]",
13
+ "sep_token": "[SEP]",
14
+ "sp_model_kwargs": {},
15
+ "split_by_punct": false,
16
+ "tokenizer_class": "DebertaV2Tokenizer",
17
+ "unk_id": 3,
18
+ "unk_token": "[UNK]",
19
+ "vocab_type": "spm"
20
+ }
Fsoft-AIC__videberta-base/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9389243dbf7fcc95a280d47b0331a96e11d3aead152fe1769d52dee590c11663
3
+ size 4856