Hugging Face's logo

diogopaes10
/
014-microsoft-deberta-v3-base-finetuned-yahoo-80_20

Text Classification
Transformers
PyTorch
TensorBoard
deberta-v2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
diogopaes10 commited on
Commit
9da7035
•
1 Parent(s): 71e9a97

Training in progress, epoch 1

Browse files
Files changed (21) hide show
  1. added_tokens.json +3 -0
  2. checkpoint-10/added_tokens.json +3 -0
  3. checkpoint-10/config.json +59 -0
  4. checkpoint-10/optimizer.pt +3 -0
  5. checkpoint-10/pytorch_model.bin +3 -0
  6. checkpoint-10/rng_state.pth +3 -0
  7. checkpoint-10/scheduler.pt +3 -0
  8. checkpoint-10/special_tokens_map.json +9 -0
  9. checkpoint-10/spm.model +3 -0
  10. checkpoint-10/tokenizer.json +0 -0
  11. checkpoint-10/tokenizer_config.json +16 -0
  12. checkpoint-10/trainer_state.json +22 -0
  13. checkpoint-10/training_args.bin +3 -0
  14. config.json +59 -0
  15. pytorch_model.bin +3 -0
  16. runs/Jul22_22-00-48_9cc823f43576/events.out.tfevents.1690063253.9cc823f43576.282.1 +3 -0
  17. special_tokens_map.json +9 -0
  18. spm.model +3 -0
  19. tokenizer.json +0 -0
  20. tokenizer_config.json +16 -0
  21. training_args.bin +3 -0
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
checkpoint-10/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
checkpoint-10/config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/deberta-v3-base",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "Society & Culture",
12
+ "1": "Science & Mathematics",
13
+ "2": "Health",
14
+ "3": "Education & Reference",
15
+ "4": "Computers & Internet",
16
+ "5": "Sports",
17
+ "6": "Business & Finance",
18
+ "7": "Entertainment & Music",
19
+ "8": "Family & Relationships",
20
+ "9": "Politics & Government"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "Business & Finance": 6,
26
+ "Computers & Internet": 4,
27
+ "Education & Reference": 3,
28
+ "Entertainment & Music": 7,
29
+ "Family & Relationships": 8,
30
+ "Health": 2,
31
+ "Politics & Government": 9,
32
+ "Science & Mathematics": 1,
33
+ "Society & Culture": 0,
34
+ "Sports": 5
35
+ },
36
+ "layer_norm_eps": 1e-07,
37
+ "max_position_embeddings": 512,
38
+ "max_relative_positions": -1,
39
+ "model_type": "deberta-v2",
40
+ "norm_rel_ebd": "layer_norm",
41
+ "num_attention_heads": 12,
42
+ "num_hidden_layers": 12,
43
+ "pad_token_id": 0,
44
+ "pooler_dropout": 0,
45
+ "pooler_hidden_act": "gelu",
46
+ "pooler_hidden_size": 768,
47
+ "pos_att_type": [
48
+ "p2c",
49
+ "c2p"
50
+ ],
51
+ "position_biased_input": false,
52
+ "position_buckets": 256,
53
+ "relative_attention": true,
54
+ "share_att_key": true,
55
+ "torch_dtype": "float32",
56
+ "transformers_version": "4.31.0",
57
+ "type_vocab_size": 0,
58
+ "vocab_size": 128100
59
+ }
checkpoint-10/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ddd3e5abfbea210bdff5ffc513bf5cd11cee3915b8f20820c4b99ff3c5c26fb
3
+ size 1475556869
checkpoint-10/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:144a9252d450e745c11caa9137b2c5bc187e8e0bc0482eccbbd38a12202d2dfd
3
+ size 737788917
checkpoint-10/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a07826ecb3d305dee85ddb09d20f37cb125119a3a51760bb09cad121ba84811
3
+ size 14575
checkpoint-10/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce6c15499abb77f9f1b81ed5e5c7dc50ca0dce12f1ad588db62e7032d0b32f2f
3
+ size 627
checkpoint-10/special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": "[UNK]"
9
+ }
checkpoint-10/spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
checkpoint-10/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-10/tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "do_lower_case": false,
6
+ "eos_token": "[SEP]",
7
+ "mask_token": "[MASK]",
8
+ "model_max_length": 1000000000000000019884624838656,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "sp_model_kwargs": {},
12
+ "split_by_punct": false,
13
+ "tokenizer_class": "DebertaV2Tokenizer",
14
+ "unk_token": "[UNK]",
15
+ "vocab_type": "spm"
16
+ }
checkpoint-10/trainer_state.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "global_step": 10,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.1,
12
+ "learning_rate": 1.9960000000000002e-05,
13
+ "loss": 2.314,
14
+ "step": 1
15
+ }
16
+ ],
17
+ "max_steps": 500,
18
+ "num_train_epochs": 50,
19
+ "total_flos": 3354967079424.0,
20
+ "trial_name": null,
21
+ "trial_params": null
22
+ }
checkpoint-10/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47900edd0b53679608a0ede66451399bbfa5cd566fbc3709079b0e0cd194e43b
3
+ size 4091
config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/deberta-v3-base",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "Society & Culture",
12
+ "1": "Science & Mathematics",
13
+ "2": "Health",
14
+ "3": "Education & Reference",
15
+ "4": "Computers & Internet",
16
+ "5": "Sports",
17
+ "6": "Business & Finance",
18
+ "7": "Entertainment & Music",
19
+ "8": "Family & Relationships",
20
+ "9": "Politics & Government"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "Business & Finance": 6,
26
+ "Computers & Internet": 4,
27
+ "Education & Reference": 3,
28
+ "Entertainment & Music": 7,
29
+ "Family & Relationships": 8,
30
+ "Health": 2,
31
+ "Politics & Government": 9,
32
+ "Science & Mathematics": 1,
33
+ "Society & Culture": 0,
34
+ "Sports": 5
35
+ },
36
+ "layer_norm_eps": 1e-07,
37
+ "max_position_embeddings": 512,
38
+ "max_relative_positions": -1,
39
+ "model_type": "deberta-v2",
40
+ "norm_rel_ebd": "layer_norm",
41
+ "num_attention_heads": 12,
42
+ "num_hidden_layers": 12,
43
+ "pad_token_id": 0,
44
+ "pooler_dropout": 0,
45
+ "pooler_hidden_act": "gelu",
46
+ "pooler_hidden_size": 768,
47
+ "pos_att_type": [
48
+ "p2c",
49
+ "c2p"
50
+ ],
51
+ "position_biased_input": false,
52
+ "position_buckets": 256,
53
+ "relative_attention": true,
54
+ "share_att_key": true,
55
+ "torch_dtype": "float32",
56
+ "transformers_version": "4.31.0",
57
+ "type_vocab_size": 0,
58
+ "vocab_size": 128100
59
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:144a9252d450e745c11caa9137b2c5bc187e8e0bc0482eccbbd38a12202d2dfd
3
+ size 737788917
runs/Jul22_22-00-48_9cc823f43576/events.out.tfevents.1690063253.9cc823f43576.282.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2797f8edc5d9722856fcabefdd286bdea0e8fd032b85d737efcd5a44578bb15
3
+ size 5104
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": "[UNK]"
9
+ }
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "do_lower_case": false,
6
+ "eos_token": "[SEP]",
7
+ "mask_token": "[MASK]",
8
+ "model_max_length": 1000000000000000019884624838656,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "sp_model_kwargs": {},
12
+ "split_by_punct": false,
13
+ "tokenizer_class": "DebertaV2Tokenizer",
14
+ "unk_token": "[UNK]",
15
+ "vocab_type": "spm"
16
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47900edd0b53679608a0ede66451399bbfa5cd566fbc3709079b0e0cd194e43b
3
+ size 4091