Hugging Face's logo

Gaxys
/
DistilBERT-PD_Books

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
text-embeddings-inference
Model card Files
xet
Metrics Community
Gaxys commited on
Commit
c1d8ff5
·
1 Parent(s): 00ec4c3

Training in progress, epoch 1

Browse files
Files changed (20) hide show
  1. config.json +35 -0
  2. model.safetensors +3 -0
  3. run-0/checkpoint-40/config.json +35 -0
  4. run-0/checkpoint-40/model.safetensors +3 -0
  5. run-0/checkpoint-40/optimizer.pt +3 -0
  6. run-0/checkpoint-40/rng_state.pth +3 -0
  7. run-0/checkpoint-40/scheduler.pt +3 -0
  8. run-0/checkpoint-40/special_tokens_map.json +7 -0
  9. run-0/checkpoint-40/tokenizer.json +0 -0
  10. run-0/checkpoint-40/tokenizer_config.json +55 -0
  11. run-0/checkpoint-40/trainer_state.json +39 -0
  12. run-0/checkpoint-40/training_args.bin +3 -0
  13. run-0/checkpoint-40/vocab.txt +0 -0
  14. runs/Nov29_01-02-41_37a4be0f03a9/events.out.tfevents.1701219771.37a4be0f03a9.346.0 +3 -0
  15. runs/Nov29_01-02-41_37a4be0f03a9/events.out.tfevents.1701220434.37a4be0f03a9.346.1 +3 -0
  16. special_tokens_map.json +7 -0
  17. tokenizer.json +0 -0
  18. tokenizer_config.json +55 -0
  19. training_args.bin +3 -0
  20. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
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": "CAROLL",
13
+ "1": "DICKENS",
14
+ "2": "DOYLE"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "CAROLL": 0,
19
+ "DICKENS": 1,
20
+ "DOYLE": 2
21
+ },
22
+ "max_position_embeddings": 512,
23
+ "model_type": "distilbert",
24
+ "n_heads": 12,
25
+ "n_layers": 6,
26
+ "pad_token_id": 0,
27
+ "problem_type": "single_label_classification",
28
+ "qa_dropout": 0.1,
29
+ "seq_classif_dropout": 0.2,
30
+ "sinusoidal_pos_embds": false,
31
+ "tie_weights_": true,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.35.2",
34
+ "vocab_size": 30522
35
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e20c8f88e8d41543d8c729c178b45d847dbc04c7cf96d3177c90444061f869df
3
+ size 267835644
run-0/checkpoint-40/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
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": "CAROLL",
13
+ "1": "DICKENS",
14
+ "2": "DOYLE"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "CAROLL": 0,
19
+ "DICKENS": 1,
20
+ "DOYLE": 2
21
+ },
22
+ "max_position_embeddings": 512,
23
+ "model_type": "distilbert",
24
+ "n_heads": 12,
25
+ "n_layers": 6,
26
+ "pad_token_id": 0,
27
+ "problem_type": "single_label_classification",
28
+ "qa_dropout": 0.1,
29
+ "seq_classif_dropout": 0.2,
30
+ "sinusoidal_pos_embds": false,
31
+ "tie_weights_": true,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.35.2",
34
+ "vocab_size": 30522
35
+ }
run-0/checkpoint-40/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e20c8f88e8d41543d8c729c178b45d847dbc04c7cf96d3177c90444061f869df
3
+ size 267835644
run-0/checkpoint-40/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2050e43490f4cb958a5087400230f02b07be993c3bdbde7f2667c7e4cd033080
3
+ size 535733434
run-0/checkpoint-40/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01be77cdfecdc21b4d6c86a19ff68a064cf7cf042ebced8dac666c9efbfed844
3
+ size 14308
run-0/checkpoint-40/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e6e209206b647d613b19aeadf8c43c48c3f456ffb89c508f6202965dd4735ab
3
+ size 1064
run-0/checkpoint-40/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
+ }
run-0/checkpoint-40/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-40/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-0/checkpoint-40/trainer_state.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6509983539581299,
3
+ "best_model_checkpoint": "DistilBERT-PD_Books/run-0/checkpoint-40",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 40,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.7670025188916877,
14
+ "eval_loss": 0.6509983539581299,
15
+ "eval_macro-f1": 0.5270807467897716,
16
+ "eval_macro-precision": 0.542500245170148,
17
+ "eval_macro-recall": 0.5384682667413058,
18
+ "eval_micro-f1": 0.7670025188916877,
19
+ "eval_micro-precision": 0.7670025188916877,
20
+ "eval_micro-recall": 0.7670025188916877,
21
+ "eval_runtime": 15.5812,
22
+ "eval_samples_per_second": 50.959,
23
+ "eval_steps_per_second": 3.209,
24
+ "step": 40
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 40,
29
+ "num_train_epochs": 1,
30
+ "save_steps": 500,
31
+ "total_flos": 0,
32
+ "trial_name": null,
33
+ "trial_params": {
34
+ "learning_rate": 3.259055737199275e-05,
35
+ "num_train_epochs": 1,
36
+ "per_device_train_batch_size": 8,
37
+ "seed": 14
38
+ }
39
+ }
run-0/checkpoint-40/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2dc1986db770be354e8a8d2f540ffd5dae2b6492c3e0296072f43b11a1be16d
3
+ size 4600
run-0/checkpoint-40/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Nov29_01-02-41_37a4be0f03a9/events.out.tfevents.1701219771.37a4be0f03a9.346.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a12fc2b5692c82375b5b9e783b977c6fa0a3d1216d0ec8d7d1f51ea8d5ece008
3
+ size 4266
runs/Nov29_01-02-41_37a4be0f03a9/events.out.tfevents.1701220434.37a4be0f03a9.346.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8672517d7a2d2fba3ed376da9ac05cb92e54bc33c17c685228ad9426e21f4e3e
3
+ size 9437
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 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2dc1986db770be354e8a8d2f540ffd5dae2b6492c3e0296072f43b11a1be16d
3
+ size 4600
vocab.txt ADDED
The diff for this file is too large to render. See raw diff