Hugging Face's logo

junaid1993
/
Belief_BERT_MultiClass

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Inference Endpoints
Model card Files Metrics Community
junaid1993 commited on
Commit
a70e1fa
•
1 Parent(s): 565487a

Upload folder using huggingface_hub

Browse files
Files changed (16) hide show
  1. checkpoint-500/config.json +41 -0
  2. checkpoint-500/model.safetensors +3 -0
  3. checkpoint-500/optimizer.pt +3 -0
  4. checkpoint-500/rng_state.pth +3 -0
  5. checkpoint-500/scheduler.pt +3 -0
  6. checkpoint-500/trainer_state.json +28 -0
  7. checkpoint-500/training_args.bin +3 -0
  8. config.json +41 -0
  9. model.safetensors +3 -0
  10. runs/May07_15-35-36_3d05e9e3f9e6/events.out.tfevents.1715096137.3d05e9e3f9e6.316.0 +3 -0
  11. runs/May07_15-39-26_3d05e9e3f9e6/events.out.tfevents.1715096368.3d05e9e3f9e6.1603.0 +3 -0
  12. special_tokens_map.json +37 -0
  13. tokenizer.json +0 -0
  14. tokenizer_config.json +59 -0
  15. training_args.bin +3 -0
  16. vocab.txt +0 -0
checkpoint-500/config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "autoevaluate/multi-class-classification",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "sadness",
13
+ "1": "joy",
14
+ "2": "love",
15
+ "3": "anger",
16
+ "4": "fear",
17
+ "5": "surprise"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "label2id": {
21
+ "anger": 3,
22
+ "fear": 4,
23
+ "joy": 1,
24
+ "love": 2,
25
+ "sadness": 0,
26
+ "surprise": 5
27
+ },
28
+ "max_position_embeddings": 512,
29
+ "model_type": "distilbert",
30
+ "n_heads": 12,
31
+ "n_layers": 6,
32
+ "pad_token_id": 0,
33
+ "problem_type": "single_label_classification",
34
+ "qa_dropout": 0.1,
35
+ "seq_classif_dropout": 0.2,
36
+ "sinusoidal_pos_embds": false,
37
+ "tie_weights_": true,
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.40.2",
40
+ "vocab_size": 30522
41
+ }
checkpoint-500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27ab7756f1d34c8a52284ff63e1858d77dc5aa2eff0d3f89eb5911ed0893f477
3
+ size 267844872
checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd94c4914731915f9e0c2a48898327ee84f616c330e507194d0a59c7b378bfef
3
+ size 535748986
checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d68b868fb6c208c87e20b0824597690ef87b5026eb5cb54f26c1a29fc1c5251
3
+ size 13990
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d54b045d47ce7df65e776acef018f4d966c06eb1118cdc4625371566e69a552
3
+ size 1064
checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.78125,
5
+ "eval_steps": 500,
6
+ "global_step": 500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.78125,
13
+ "grad_norm": 0.030135750770568848,
14
+ "learning_rate": 1.09375e-05,
15
+ "loss": 0.3256,
16
+ "step": 500
17
+ }
18
+ ],
19
+ "logging_steps": 500,
20
+ "max_steps": 640,
21
+ "num_input_tokens_seen": 0,
22
+ "num_train_epochs": 1,
23
+ "save_steps": 500,
24
+ "total_flos": 529907392512000.0,
25
+ "train_batch_size": 8,
26
+ "trial_name": null,
27
+ "trial_params": null
28
+ }
checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b35626207370683125d5efe0aef96e1515bfc8cead73cca1af71269eedbccf8e
3
+ size 4984
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "autoevaluate/multi-class-classification",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "sadness",
13
+ "1": "joy",
14
+ "2": "love",
15
+ "3": "anger",
16
+ "4": "fear",
17
+ "5": "surprise"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "label2id": {
21
+ "anger": 3,
22
+ "fear": 4,
23
+ "joy": 1,
24
+ "love": 2,
25
+ "sadness": 0,
26
+ "surprise": 5
27
+ },
28
+ "max_position_embeddings": 512,
29
+ "model_type": "distilbert",
30
+ "n_heads": 12,
31
+ "n_layers": 6,
32
+ "pad_token_id": 0,
33
+ "problem_type": "single_label_classification",
34
+ "qa_dropout": 0.1,
35
+ "seq_classif_dropout": 0.2,
36
+ "sinusoidal_pos_embds": false,
37
+ "tie_weights_": true,
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.40.2",
40
+ "vocab_size": 30522
41
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e8408013ef0f657602d037b0cf4c1d60101ef82409647564c7d3c289bf3c8a4
3
+ size 267844872
runs/May07_15-35-36_3d05e9e3f9e6/events.out.tfevents.1715096137.3d05e9e3f9e6.316.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6987d3a136c4b2773c1b91acc69b7cecc6346f461a3ae90bec177774465928a3
3
+ size 4184
runs/May07_15-39-26_3d05e9e3f9e6/events.out.tfevents.1715096368.3d05e9e3f9e6.1603.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5e433b36cef5184b08c91ad0dab23d47420cfc10a23db085092e0a37a58d6af
3
+ size 5435
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "max_length": 512,
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "stride": 0,
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "DistilBertTokenizer",
56
+ "truncation_side": "right",
57
+ "truncation_strategy": "longest_first",
58
+ "unk_token": "[UNK]"
59
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b35626207370683125d5efe0aef96e1515bfc8cead73cca1af71269eedbccf8e
3
+ size 4984
vocab.txt ADDED
The diff for this file is too large to render. See raw diff