Hugging Face's logo

antalvdb
/
distilbert-base-uncased-finetuned-cola

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
antalvdb commited on
Commit
89a4467
·
verified ·
1 Parent(s): ecff29c

Training in progress, epoch 1

Browse files
Files changed (26) hide show
  1. model.safetensors +1 -1
  2. run-5/checkpoint-108/config.json +25 -0
  3. run-5/checkpoint-108/model.safetensors +3 -0
  4. run-5/checkpoint-108/optimizer.pt +3 -0
  5. run-5/checkpoint-108/rng_state.pth +3 -0
  6. run-5/checkpoint-108/scheduler.pt +3 -0
  7. run-5/checkpoint-108/special_tokens_map.json +7 -0
  8. run-5/checkpoint-108/tokenizer.json +0 -0
  9. run-5/checkpoint-108/tokenizer_config.json +55 -0
  10. run-5/checkpoint-108/trainer_state.json +44 -0
  11. run-5/checkpoint-108/training_args.bin +3 -0
  12. run-5/checkpoint-108/vocab.txt +0 -0
  13. run-7/checkpoint-27/config.json +25 -0
  14. run-7/checkpoint-27/model.safetensors +3 -0
  15. run-7/checkpoint-27/optimizer.pt +3 -0
  16. run-7/checkpoint-27/rng_state.pth +3 -0
  17. run-7/checkpoint-27/scheduler.pt +3 -0
  18. run-7/checkpoint-27/special_tokens_map.json +7 -0
  19. run-7/checkpoint-27/tokenizer.json +0 -0
  20. run-7/checkpoint-27/tokenizer_config.json +55 -0
  21. run-7/checkpoint-27/trainer_state.json +35 -0
  22. run-7/checkpoint-27/training_args.bin +3 -0
  23. run-7/checkpoint-27/vocab.txt +0 -0
  24. runs/Feb23_10-35-48_ec6659c07f12/events.out.tfevents.1708685188.ec6659c07f12.1051.8 +3 -0
  25. runs/Feb23_10-35-48_ec6659c07f12/events.out.tfevents.1708685191.ec6659c07f12.1051.9 +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 sha256:22b883449c19a6d9e914daeb970fd6499cefc3048f5720f1a5a067086c3bbb39
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aec41c06410822efe0d1cceabc14e18037e38f1ce94122d4ed867e47a5975d1d
3
  size 267832560
run-5/checkpoint-108/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": "4.38.1",
24
+ "vocab_size": 30522
25
+ }
run-5/checkpoint-108/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d86afa7f3e7ba0efb28f9c1c2b6df2cad7b87c282dd42bf401fc596d2d66aeb4
3
+ size 267832560
run-5/checkpoint-108/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bc2702af7263ac1d2314192186e3d300a878588d8059547fbfc261f00297395
3
+ size 535727290
run-5/checkpoint-108/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23053574e8f214aa238faa2f765a8018b9ed53e6f5aa51f5ce125eaab151d9b3
3
+ size 14244
run-5/checkpoint-108/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47ef76d49466e3922b2efe0f3737e8e5cacb27dc661c48bd6fc1ba9e0e8f0260
3
+ size 1064
run-5/checkpoint-108/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-108/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-108/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-108/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.3138772949391258,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-108",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 108,
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": 0.566685676574707,
14
+ "eval_matthews_correlation": 0.0928457264044978,
15
+ "eval_runtime": 0.4852,
16
+ "eval_samples_per_second": 2149.743,
17
+ "eval_steps_per_second": 136.034,
18
+ "step": 54
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6035006046295166,
23
+ "eval_matthews_correlation": 0.3138772949391258,
24
+ "eval_runtime": 0.4823,
25
+ "eval_samples_per_second": 2162.447,
26
+ "eval_steps_per_second": 136.838,
27
+ "step": 108
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 108,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 2,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 16,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 5.710392540206621e-05,
40
+ "num_train_epochs": 2,
41
+ "per_device_train_batch_size": 16,
42
+ "seed": 18
43
+ }
44
+ }
run-5/checkpoint-108/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ad1fef1939082239593889150a2d97a7a6391f997be90b7eb656629366da7fd
3
+ size 4984
run-5/checkpoint-108/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-27/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": "4.38.1",
24
+ "vocab_size": 30522
25
+ }
run-7/checkpoint-27/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aec41c06410822efe0d1cceabc14e18037e38f1ce94122d4ed867e47a5975d1d
3
+ size 267832560
run-7/checkpoint-27/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51a6f1d44bc9dd1b34cafc8eb399fd30b06b9b68b04e6e2b3225027117030c62
3
+ size 535727290
run-7/checkpoint-27/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99733960c4cdefbca5404dbbb3b1c3048aee8e76743a883e33e0a1408532f596
3
+ size 14244
run-7/checkpoint-27/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1655a7c109d2c6b22e73320efe8a7dba1c8d960f87aa7364e58e8095120b3279
3
+ size 1064
run-7/checkpoint-27/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-7/checkpoint-27/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-27/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-7/checkpoint-27/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-27",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 27,
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": 0.5920080542564392,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.4805,
16
+ "eval_samples_per_second": 2170.813,
17
+ "eval_steps_per_second": 137.367,
18
+ "step": 27
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 27,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 1,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 32,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 4.5205828927679235e-05,
31
+ "num_train_epochs": 1,
32
+ "per_device_train_batch_size": 32,
33
+ "seed": 30
34
+ }
35
+ }
run-7/checkpoint-27/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a50a685198f26eae14f5a354156c245a895e2f4a69a4ef06f7692ec99269431f
3
+ size 4984
run-7/checkpoint-27/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Feb23_10-35-48_ec6659c07f12/events.out.tfevents.1708685188.ec6659c07f12.1051.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1de3fabc06bef7b322d2172ac63a07bb61f1208c850a35302e64326e156b6b4f
3
+ size 4872
runs/Feb23_10-35-48_ec6659c07f12/events.out.tfevents.1708685191.ec6659c07f12.1051.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3172e9c26dc53eb0aea63e35b14dc52d2a302ae85fea1a09efd9a02abf0e147
3
+ size 5220
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ad1fef1939082239593889150a2d97a7a6391f997be90b7eb656629366da7fd
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a50a685198f26eae14f5a354156c245a895e2f4a69a4ef06f7692ec99269431f
3
  size 4984