Hugging Face's logo

diogopaes10
/
008-microsoft-deberta-v3-base-finetuned-yahoo-800_200

Text Classification
Transformers
PyTorch
TensorBoard
deberta-v2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
diogopaes10 commited on
Commit
cbf5494
•
1 Parent(s): 93d603e

Training in progress, epoch 1

Browse files
Files changed (21) hide show
  1. added_tokens.json +3 -0
  2. checkpoint-25/added_tokens.json +3 -0
  3. checkpoint-25/config.json +59 -0
  4. checkpoint-25/optimizer.pt +3 -0
  5. checkpoint-25/pytorch_model.bin +3 -0
  6. checkpoint-25/rng_state.pth +3 -0
  7. checkpoint-25/scheduler.pt +3 -0
  8. checkpoint-25/special_tokens_map.json +9 -0
  9. checkpoint-25/spm.model +3 -0
  10. checkpoint-25/tokenizer.json +0 -0
  11. checkpoint-25/tokenizer_config.json +16 -0
  12. checkpoint-25/trainer_state.json +48 -0
  13. checkpoint-25/training_args.bin +3 -0
  14. config.json +59 -0
  15. pytorch_model.bin +3 -0
  16. runs/Jul22_09-14-20_549e78cb1c68/events.out.tfevents.1690017269.549e78cb1c68.4107.0 +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-25/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
checkpoint-25/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-25/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5234bcf02ba94563d8c46023c7ed93ffa23247e131baf03d9b56bc2eab5ff3bb
3
+ size 1475556869
checkpoint-25/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:018fc808d5941a688c9c9e4f06e58a0814b48180f8430b328b90be99c15622a0
3
+ size 737788917
checkpoint-25/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3acef221ac140539d08c3e34b90e2817f8ef37ce8780d4ba3a802620d305bc64
3
+ size 14575
checkpoint-25/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c3880c86866d0a084be2906ed68f5bf131cffaddd088f0e77e3c69af757e737
3
+ size 627
checkpoint-25/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-25/spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
checkpoint-25/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-25/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-25/trainer_state.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "global_step": 25,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.04,
12
+ "learning_rate": 1.9920000000000002e-05,
13
+ "loss": 2.3122,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.52,
18
+ "learning_rate": 1.896e-05,
19
+ "loss": 2.2992,
20
+ "step": 13
21
+ },
22
+ {
23
+ "epoch": 0.52,
24
+ "eval_accuracy": 0.1,
25
+ "eval_disk_space_total": 78.1898422241211,
26
+ "eval_disk_space_used": 24.785266876220703,
27
+ "eval_f1": 0.018181818181818184,
28
+ "eval_gpu_ram_allocated": 2.091515064239502,
29
+ "eval_gpu_ram_cached": 24.6484375,
30
+ "eval_gpu_ram_total": 39.56402587890625,
31
+ "eval_gpu_utilization": 50,
32
+ "eval_loss": 2.303118944168091,
33
+ "eval_precision": 0.01,
34
+ "eval_recall": 0.1,
35
+ "eval_runtime": 0.3632,
36
+ "eval_samples_per_second": 550.672,
37
+ "eval_steps_per_second": 19.274,
38
+ "eval_system_ram_total": 83.48074722290039,
39
+ "eval_system_ram_used": 3.9340057373046875,
40
+ "step": 13
41
+ }
42
+ ],
43
+ "max_steps": 250,
44
+ "num_train_epochs": 10,
45
+ "total_flos": 54485323206528.0,
46
+ "trial_name": null,
47
+ "trial_params": null
48
+ }
checkpoint-25/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2418b115209f2e4ba6e7e8442936bab7815c05be91f0380b9d3b20748a2ca41f
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 sha256:018fc808d5941a688c9c9e4f06e58a0814b48180f8430b328b90be99c15622a0
3
+ size 737788917
runs/Jul22_09-14-20_549e78cb1c68/events.out.tfevents.1690017269.549e78cb1c68.4107.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c710d47f4d2c6ff93aec4144002f777fda3459044926dfb0be215f7be30bb017
3
+ size 6194
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 sha256:2418b115209f2e4ba6e7e8442936bab7815c05be91f0380b9d3b20748a2ca41f
3
+ size 4091