Hugging Face's logo

ensr
/
distilbert-base-uncased-finetuned-cola

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
ensr commited on
Commit
9eccd8b
•
1 Parent(s): 4ce60e0

Training in progress, epoch 2

Browse files
Files changed (26) hide show
  1. model.safetensors +1 -1
  2. run-6/checkpoint-134/config.json +25 -0
  3. run-6/checkpoint-134/model.safetensors +3 -0
  4. run-6/checkpoint-134/optimizer.pt +3 -0
  5. run-6/checkpoint-134/rng_state.pth +3 -0
  6. run-6/checkpoint-134/scheduler.pt +3 -0
  7. run-6/checkpoint-134/special_tokens_map.json +7 -0
  8. run-6/checkpoint-134/tokenizer.json +0 -0
  9. run-6/checkpoint-134/tokenizer_config.json +55 -0
  10. run-6/checkpoint-134/trainer_state.json +35 -0
  11. run-6/checkpoint-134/training_args.bin +3 -0
  12. run-6/checkpoint-134/vocab.txt +0 -0
  13. run-6/checkpoint-268/config.json +25 -0
  14. run-6/checkpoint-268/model.safetensors +3 -0
  15. run-6/checkpoint-268/optimizer.pt +3 -0
  16. run-6/checkpoint-268/rng_state.pth +3 -0
  17. run-6/checkpoint-268/scheduler.pt +3 -0
  18. run-6/checkpoint-268/special_tokens_map.json +7 -0
  19. run-6/checkpoint-268/tokenizer.json +0 -0
  20. run-6/checkpoint-268/tokenizer_config.json +55 -0
  21. run-6/checkpoint-268/trainer_state.json +44 -0
  22. run-6/checkpoint-268/training_args.bin +3 -0
  23. run-6/checkpoint-268/vocab.txt +0 -0
  24. runs/Dec12_14-52-17_DESKTOP-UUVDD26/events.out.tfevents.1702387263.DESKTOP-UUVDD26.9476.7 +3 -0
  25. runs/Dec12_14-52-17_DESKTOP-UUVDD26/events.out.tfevents.1702387940.DESKTOP-UUVDD26.9476.8 +3 -0
  26. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e291c47e7d9d5a05d2c7760597db9b7aa7570086ca78ef91651159ece4e1b91c
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed2644251368c65495b2c1007eb70c81466c27ef7763fe41e6c24481cb71cbff
3
  size 267832560
run-6/checkpoint-134/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.36.0",
24
+ "vocab_size": 30522
25
+ }
run-6/checkpoint-134/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a91e6cebfeb077a5268885dcc2b53125a35f2a37e612ced00203553bf989025
3
+ size 267832560
run-6/checkpoint-134/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd8dc9a621470a15d21d079e600cc5babdb2d1a39bcf4b1abf16b8fb598113fe
3
+ size 535724410
run-6/checkpoint-134/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b15194ba4b33c4c2db42114381f954762268030b4e9517c62bec17342faf6e09
3
+ size 14054
run-6/checkpoint-134/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb9c06788da951f5b63b66c9d4c56f966ea2377df90b8e09fec6f5f7da827ca3
3
+ size 1064
run-6/checkpoint-134/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-6/checkpoint-134/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-134/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-6/checkpoint-134/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.443580024837866,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola\\run-6\\checkpoint-134",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 134,
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_loss": 0.4850870668888092,
14
+ "eval_matthews_correlation": 0.443580024837866,
15
+ "eval_runtime": 6.0007,
16
+ "eval_samples_per_second": 173.814,
17
+ "eval_steps_per_second": 10.999,
18
+ "step": 134
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 536,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 4,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 64,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 8.066575947187145e-05,
31
+ "num_train_epochs": 4,
32
+ "per_device_train_batch_size": 64,
33
+ "seed": 17
34
+ }
35
+ }
run-6/checkpoint-134/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ded1b6b1f60b9546c0024cc791ec548ec898fc70ad8e812f4ae3d3a5f1c1d50
3
+ size 4792
run-6/checkpoint-134/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-268/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.36.0",
24
+ "vocab_size": 30522
25
+ }
run-6/checkpoint-268/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed2644251368c65495b2c1007eb70c81466c27ef7763fe41e6c24481cb71cbff
3
+ size 267832560
run-6/checkpoint-268/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06542c3aca353fc421c961a411d9d18f07f4820b0efb7c750a092758de3bea79
3
+ size 535724410
run-6/checkpoint-268/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:caaa42704313bea5b0f7424f057c06b5f659bd92651033c3855a827ad6272625
3
+ size 14054
run-6/checkpoint-268/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fdfb0a1e7e613f096f0dfa7434ab6dc31e443ede3770e76d2fbce500cd0895d
3
+ size 1064
run-6/checkpoint-268/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-6/checkpoint-268/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-268/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-6/checkpoint-268/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5255827322697563,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola\\run-6\\checkpoint-268",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 268,
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_loss": 0.4850870668888092,
14
+ "eval_matthews_correlation": 0.443580024837866,
15
+ "eval_runtime": 6.0007,
16
+ "eval_samples_per_second": 173.814,
17
+ "eval_steps_per_second": 10.999,
18
+ "step": 134
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.4454311728477478,
23
+ "eval_matthews_correlation": 0.5255827322697563,
24
+ "eval_runtime": 6.8111,
25
+ "eval_samples_per_second": 153.132,
26
+ "eval_steps_per_second": 9.69,
27
+ "step": 268
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 536,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 4,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 64,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 8.066575947187145e-05,
40
+ "num_train_epochs": 4,
41
+ "per_device_train_batch_size": 64,
42
+ "seed": 17
43
+ }
44
+ }
run-6/checkpoint-268/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ded1b6b1f60b9546c0024cc791ec548ec898fc70ad8e812f4ae3d3a5f1c1d50
3
+ size 4792
run-6/checkpoint-268/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Dec12_14-52-17_DESKTOP-UUVDD26/events.out.tfevents.1702387263.DESKTOP-UUVDD26.9476.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68036afea6c6582486615ed3dae8c3f6eaeb29a93be32f2febbadbad991f4f56
3
+ size 5298
runs/Dec12_14-52-17_DESKTOP-UUVDD26/events.out.tfevents.1702387940.DESKTOP-UUVDD26.9476.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cafda37a18b3c2357e276fc762b23b8e26b23cbe9bc2d96603f9a317d586302
3
+ size 5006
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:286ee074d165e0e383ffaa7595ee0c7093832221ee96e7ed3f9a6dcd9c5b653b
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ded1b6b1f60b9546c0024cc791ec548ec898fc70ad8e812f4ae3d3a5f1c1d50
3
  size 4792