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
7bbd268
·
1 Parent(s): 53d70c2

Training in progress, epoch 1

Browse files
Files changed (25) hide show
  1. model.safetensors +1 -1
  2. run-4/checkpoint-40/config.json +35 -0
  3. run-4/checkpoint-40/model.safetensors +3 -0
  4. run-4/checkpoint-40/optimizer.pt +3 -0
  5. run-4/checkpoint-40/rng_state.pth +3 -0
  6. run-4/checkpoint-40/scheduler.pt +3 -0
  7. run-4/checkpoint-40/special_tokens_map.json +7 -0
  8. run-4/checkpoint-40/tokenizer.json +0 -0
  9. run-4/checkpoint-40/tokenizer_config.json +55 -0
  10. run-4/checkpoint-40/trainer_state.json +54 -0
  11. run-4/checkpoint-40/training_args.bin +3 -0
  12. run-4/checkpoint-40/vocab.txt +0 -0
  13. run-5/checkpoint-40/config.json +35 -0
  14. run-5/checkpoint-40/model.safetensors +3 -0
  15. run-5/checkpoint-40/optimizer.pt +3 -0
  16. run-5/checkpoint-40/rng_state.pth +3 -0
  17. run-5/checkpoint-40/scheduler.pt +3 -0
  18. run-5/checkpoint-40/special_tokens_map.json +7 -0
  19. run-5/checkpoint-40/tokenizer.json +0 -0
  20. run-5/checkpoint-40/tokenizer_config.json +55 -0
  21. run-5/checkpoint-40/trainer_state.json +39 -0
  22. run-5/checkpoint-40/training_args.bin +3 -0
  23. run-5/checkpoint-40/vocab.txt +0 -0
  24. runs/Nov29_01-02-41_37a4be0f03a9/events.out.tfevents.1701220975.37a4be0f03a9.346.6 +3 -0
  25. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52074229be0c3cda27d7375e7ea3fd51a7dc8d8fb0a3b4df8c8df0adf6b8ec53
3
  size 267835644
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9260c5382c4635eae5c963b770d60a2e20556e777002535a9a4dbf82b63bbb4e
3
  size 267835644
run-4/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-4/checkpoint-40/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14fe57da3ab3373ae804c62a1fac552eff57cff2aa495657d0436d38437b3b51
3
+ size 267835644
run-4/checkpoint-40/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d625515e8b18e3ded9c806a427979bf2e247bafb45307b3033ef6ba2f8981dee
3
+ size 535733434
run-4/checkpoint-40/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1a26cead10a14d250e2b9af6869a870794516310dcba67d51f695c751f51b73
3
+ size 14308
run-4/checkpoint-40/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2efef2247e8a305670e7b2b227d174a308e6014936803fbf808fdb3c471eb02
3
+ size 1064
run-4/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-4/checkpoint-40/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/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-4/checkpoint-40/trainer_state.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.0206553936004639,
3
+ "best_model_checkpoint": "DistilBERT-PD_Books/run-4/checkpoint-40",
4
+ "epoch": 2.0,
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": 0.5793450881612091,
14
+ "eval_loss": 1.0442371368408203,
15
+ "eval_macro-f1": 0.24455077086656038,
16
+ "eval_macro-precision": 0.19335855401429172,
17
+ "eval_macro-recall": 0.33261026753434564,
18
+ "eval_micro-f1": 0.5793450881612091,
19
+ "eval_micro-precision": 0.5793450881612091,
20
+ "eval_micro-recall": 0.5793450881612091,
21
+ "eval_runtime": 15.3439,
22
+ "eval_samples_per_second": 51.747,
23
+ "eval_steps_per_second": 3.259,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_accuracy": 0.5806045340050378,
29
+ "eval_loss": 1.0206553936004639,
30
+ "eval_macro-f1": 0.2448871181938911,
31
+ "eval_macro-precision": 0.19353484466834592,
32
+ "eval_macro-recall": 0.3333333333333333,
33
+ "eval_micro-f1": 0.5806045340050378,
34
+ "eval_micro-precision": 0.5806045340050378,
35
+ "eval_micro-recall": 0.5806045340050378,
36
+ "eval_runtime": 15.8369,
37
+ "eval_samples_per_second": 50.136,
38
+ "eval_steps_per_second": 3.157,
39
+ "step": 40
40
+ }
41
+ ],
42
+ "logging_steps": 500,
43
+ "max_steps": 40,
44
+ "num_train_epochs": 2,
45
+ "save_steps": 500,
46
+ "total_flos": 0,
47
+ "trial_name": null,
48
+ "trial_params": {
49
+ "learning_rate": 3.957544474357403e-06,
50
+ "num_train_epochs": 2,
51
+ "per_device_train_batch_size": 16,
52
+ "seed": 14
53
+ }
54
+ }
run-4/checkpoint-40/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:118de7a442a790d89b1ef2952e72a5f93c03f2d40e1a24c60409ab1518104474
3
+ size 4600
run-4/checkpoint-40/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-5/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-5/checkpoint-40/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9260c5382c4635eae5c963b770d60a2e20556e777002535a9a4dbf82b63bbb4e
3
+ size 267835644
run-5/checkpoint-40/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad54e62357339db3bc0e0ab10fef33da70f92e76ed42759a422023c8756a8a8d
3
+ size 535733434
run-5/checkpoint-40/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e44648f0871f5612323a33d1749d2316dbd1084c4758a7cfcfd968bcdfc33456
3
+ size 14308
run-5/checkpoint-40/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8af36a258cf1c05d1c62202e432c6fc60f7e93b3b61b47a53ccc13b78598837
3
+ size 1064
run-5/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-5/checkpoint-40/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/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-5/checkpoint-40/trainer_state.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4906409680843353,
3
+ "best_model_checkpoint": "DistilBERT-PD_Books/run-5/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": 0.8501259445843828,
14
+ "eval_loss": 0.4906409680843353,
15
+ "eval_macro-f1": 0.8096247291697343,
16
+ "eval_macro-precision": 0.9316091954022988,
17
+ "eval_macro-recall": 0.7524193548387097,
18
+ "eval_micro-f1": 0.8501259445843828,
19
+ "eval_micro-precision": 0.8501259445843828,
20
+ "eval_micro-recall": 0.8501259445843828,
21
+ "eval_runtime": 15.1893,
22
+ "eval_samples_per_second": 52.273,
23
+ "eval_steps_per_second": 3.292,
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": 4.471194115875663e-05,
35
+ "num_train_epochs": 1,
36
+ "per_device_train_batch_size": 8,
37
+ "seed": 26
38
+ }
39
+ }
run-5/checkpoint-40/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09d31d747f15e0b4fbd4283ee52a2f599e96d6683ddd39b8fa6c9a61f4c5aea4
3
+ size 4600
run-5/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.1701220975.37a4be0f03a9.346.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09bad51e83a20da2e2483156c1ae7d9be76c52bc9a9f68b54ccd19b93854cc12
3
+ size 5258
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:118de7a442a790d89b1ef2952e72a5f93c03f2d40e1a24c60409ab1518104474
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09d31d747f15e0b4fbd4283ee52a2f599e96d6683ddd39b8fa6c9a61f4c5aea4
3
  size 4600