Hugging Face's logo

diogopaes10
/
019-microsoft-MiniLM-finetuned-yahoo-80000_20000

Text Classification
Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
diogopaes10 commited on
Commit
62de353
•
1 Parent(s): 5d2767d

Training in progress, step 500

Browse files
Files changed (19) hide show
  1. checkpoint-500/config.json +50 -0
  2. checkpoint-500/optimizer.pt +3 -0
  3. checkpoint-500/pytorch_model.bin +3 -0
  4. checkpoint-500/rng_state.pth +3 -0
  5. checkpoint-500/scheduler.pt +3 -0
  6. checkpoint-500/special_tokens_map.json +7 -0
  7. checkpoint-500/tokenizer.json +0 -0
  8. checkpoint-500/tokenizer_config.json +15 -0
  9. checkpoint-500/trainer_state.json +22 -0
  10. checkpoint-500/training_args.bin +3 -0
  11. checkpoint-500/vocab.txt +0 -0
  12. config.json +50 -0
  13. pytorch_model.bin +3 -0
  14. runs/Jul23_01-08-06_df8adf32a670/events.out.tfevents.1690074496.df8adf32a670.1420.0 +3 -0
  15. special_tokens_map.json +7 -0
  16. tokenizer.json +0 -0
  17. tokenizer_config.json +15 -0
  18. training_args.bin +3 -0
  19. vocab.txt +0 -0
checkpoint-500/config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/MiniLM-L12-H384-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 384,
11
+ "id2label": {
12
+ "0": "Society & Culture",
13
+ "1": "Science & Mathematics",
14
+ "2": "Health",
15
+ "3": "Education & Reference",
16
+ "4": "Computers & Internet",
17
+ "5": "Sports",
18
+ "6": "Business & Finance",
19
+ "7": "Entertainment & Music",
20
+ "8": "Family & Relationships",
21
+ "9": "Politics & Government"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 1536,
25
+ "label2id": {
26
+ "Business & Finance": 6,
27
+ "Computers & Internet": 4,
28
+ "Education & Reference": 3,
29
+ "Entertainment & Music": 7,
30
+ "Family & Relationships": 8,
31
+ "Health": 2,
32
+ "Politics & Government": 9,
33
+ "Science & Mathematics": 1,
34
+ "Society & Culture": 0,
35
+ "Sports": 5
36
+ },
37
+ "layer_norm_eps": 1e-12,
38
+ "max_position_embeddings": 512,
39
+ "model_type": "bert",
40
+ "num_attention_heads": 12,
41
+ "num_hidden_layers": 12,
42
+ "pad_token_id": 0,
43
+ "position_embedding_type": "absolute",
44
+ "problem_type": "single_label_classification",
45
+ "torch_dtype": "float32",
46
+ "transformers_version": "4.31.0",
47
+ "type_vocab_size": 2,
48
+ "use_cache": true,
49
+ "vocab_size": 30522
50
+ }
checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62fe6a7ec913e32dd351ab2b4125671bcd254f4c931a43f9e3a150dda8233106
3
+ size 267028677
checkpoint-500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76504688b159d327d90fda70f926d5a4789f66906c332fd65d0a6f8c4d98c0dd
3
+ size 133523761
checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4272af17bf56340ed09122567f5c481873e5730c6ece5188bc48641292fc04c
3
+ size 14575
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f78d67aadb730bf32141bbb25c281dc3564f044f8b8486314e5e5c7e8350b36
3
+ size 627
checkpoint-500/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
checkpoint-500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-500/tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": true,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 1000000000000000019884624838656,
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.2,
5
+ "global_step": 500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 1.99984e-05,
13
+ "loss": 2.3075,
14
+ "step": 1
15
+ }
16
+ ],
17
+ "max_steps": 12500,
18
+ "num_train_epochs": 5,
19
+ "total_flos": 252625264733184.0,
20
+ "trial_name": null,
21
+ "trial_params": null
22
+ }
checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4856ce4bc7a3b9a50464d3e12d6b58a0fcddfe9bfd910688b04cf70984b818d
3
+ size 4091
checkpoint-500/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/MiniLM-L12-H384-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 384,
11
+ "id2label": {
12
+ "0": "Society & Culture",
13
+ "1": "Science & Mathematics",
14
+ "2": "Health",
15
+ "3": "Education & Reference",
16
+ "4": "Computers & Internet",
17
+ "5": "Sports",
18
+ "6": "Business & Finance",
19
+ "7": "Entertainment & Music",
20
+ "8": "Family & Relationships",
21
+ "9": "Politics & Government"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 1536,
25
+ "label2id": {
26
+ "Business & Finance": 6,
27
+ "Computers & Internet": 4,
28
+ "Education & Reference": 3,
29
+ "Entertainment & Music": 7,
30
+ "Family & Relationships": 8,
31
+ "Health": 2,
32
+ "Politics & Government": 9,
33
+ "Science & Mathematics": 1,
34
+ "Society & Culture": 0,
35
+ "Sports": 5
36
+ },
37
+ "layer_norm_eps": 1e-12,
38
+ "max_position_embeddings": 512,
39
+ "model_type": "bert",
40
+ "num_attention_heads": 12,
41
+ "num_hidden_layers": 12,
42
+ "pad_token_id": 0,
43
+ "position_embedding_type": "absolute",
44
+ "problem_type": "single_label_classification",
45
+ "torch_dtype": "float32",
46
+ "transformers_version": "4.31.0",
47
+ "type_vocab_size": 2,
48
+ "use_cache": true,
49
+ "vocab_size": 30522
50
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76504688b159d327d90fda70f926d5a4789f66906c332fd65d0a6f8c4d98c0dd
3
+ size 133523761
runs/Jul23_01-08-06_df8adf32a670/events.out.tfevents.1690074496.df8adf32a670.1420.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfe3e2a2d781672aa5c1c981d562f70f07264ac4d07b9fa7a2796a82ef35b0af
3
+ size 4882
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": true,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 1000000000000000019884624838656,
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4856ce4bc7a3b9a50464d3e12d6b58a0fcddfe9bfd910688b04cf70984b818d
3
+ size 4091
vocab.txt ADDED
The diff for this file is too large to render. See raw diff