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
06bef05
·
verified ·
1 Parent(s): eeae61e

Training in progress, epoch 1

Browse files
Files changed (26) hide show
  1. model.safetensors +1 -1
  2. run-8/checkpoint-81/config.json +25 -0
  3. run-8/checkpoint-81/model.safetensors +3 -0
  4. run-8/checkpoint-81/optimizer.pt +3 -0
  5. run-8/checkpoint-81/rng_state.pth +3 -0
  6. run-8/checkpoint-81/scheduler.pt +3 -0
  7. run-8/checkpoint-81/special_tokens_map.json +7 -0
  8. run-8/checkpoint-81/tokenizer.json +0 -0
  9. run-8/checkpoint-81/tokenizer_config.json +55 -0
  10. run-8/checkpoint-81/trainer_state.json +53 -0
  11. run-8/checkpoint-81/training_args.bin +3 -0
  12. run-8/checkpoint-81/vocab.txt +0 -0
  13. run-9/checkpoint-14/config.json +25 -0
  14. run-9/checkpoint-14/model.safetensors +3 -0
  15. run-9/checkpoint-14/optimizer.pt +3 -0
  16. run-9/checkpoint-14/rng_state.pth +3 -0
  17. run-9/checkpoint-14/scheduler.pt +3 -0
  18. run-9/checkpoint-14/special_tokens_map.json +7 -0
  19. run-9/checkpoint-14/tokenizer.json +0 -0
  20. run-9/checkpoint-14/tokenizer_config.json +55 -0
  21. run-9/checkpoint-14/trainer_state.json +35 -0
  22. run-9/checkpoint-14/training_args.bin +3 -0
  23. run-9/checkpoint-14/vocab.txt +0 -0
  24. runs/Jan26_08-04-50_7ac5f092fd85/events.out.tfevents.1706288100.7ac5f092fd85.1710.12 +2 -2
  25. runs/Jan26_08-04-50_7ac5f092fd85/events.out.tfevents.1706288849.7ac5f092fd85.1710.13 +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:a5060dd0cbf8ada160bdfcce277c8e9de718cf2c697736d7057bc151612c130e
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6ed8f5c038bf84fb800d1adbc98252cb6f228181a9ca388406686f2196469cc
3
  size 267832560
run-8/checkpoint-81/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": "4.37.1",
24
+ "vocab_size": 30522
25
+ }
run-8/checkpoint-81/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cafd2a0a09809254add5e3602f45220e669760c03c1878ff8b137a4f3c474b82
3
+ size 267832560
run-8/checkpoint-81/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e02ca2dac57140d43d99a60a15d3d6ae5066c97df95cacad63eaf48a4fbcdc0d
3
+ size 535724410
run-8/checkpoint-81/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9272ab2d3d2ef0169bc1eb3ec0721d9f9adb8793f6bcc59053643da152d1f0c3
3
+ size 13990
run-8/checkpoint-81/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8768e66caad8620c1fb37580098ffaa5bbf9a2bba255175cd12f61d72b49e67
3
+ size 1064
run-8/checkpoint-81/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-8/checkpoint-81/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-81/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-8/checkpoint-81/trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/checkpoint-27",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 81,
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": 0.622236967086792,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 31.9371,
16
+ "eval_samples_per_second": 32.658,
17
+ "eval_steps_per_second": 2.067,
18
+ "step": 27
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6126815676689148,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 50.6552,
25
+ "eval_samples_per_second": 20.59,
26
+ "eval_steps_per_second": 1.303,
27
+ "step": 54
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.6096475720405579,
32
+ "eval_matthews_correlation": 0.0,
33
+ "eval_runtime": 48.1176,
34
+ "eval_samples_per_second": 21.676,
35
+ "eval_steps_per_second": 1.372,
36
+ "step": 81
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 108,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 4,
43
+ "save_steps": 500,
44
+ "total_flos": 0,
45
+ "train_batch_size": 32,
46
+ "trial_name": null,
47
+ "trial_params": {
48
+ "learning_rate": 7.025432167792355e-06,
49
+ "num_train_epochs": 4,
50
+ "per_device_train_batch_size": 32,
51
+ "seed": 6
52
+ }
53
+ }
run-8/checkpoint-81/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:692eacbd67898c3493bf506fda6014d3ca41265ad43b7b6a751a76178e23aa5b
3
+ size 4792
run-8/checkpoint-81/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-14/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": "4.37.1",
24
+ "vocab_size": 30522
25
+ }
run-9/checkpoint-14/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6ed8f5c038bf84fb800d1adbc98252cb6f228181a9ca388406686f2196469cc
3
+ size 267832560
run-9/checkpoint-14/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0aeacf70426ebd63ecf268b74e7ce78f84b8d271b2df76834843a1552c9094f1
3
+ size 535724410
run-9/checkpoint-14/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa65a62afb8fd9e7c2d5296bdea6fd26c1bac0be2b3215fa50a27707a88c4595
3
+ size 13990
run-9/checkpoint-14/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c284db7428d1bed345030bbde0b2d93726bf1036c46a37c8c87133bc6858884
3
+ size 1064
run-9/checkpoint-14/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-9/checkpoint-14/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-14/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-9/checkpoint-14/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.007635862540786124,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-9/checkpoint-14",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 14,
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": 0.6803035736083984,
14
+ "eval_matthews_correlation": 0.007635862540786124,
15
+ "eval_runtime": 31.4206,
16
+ "eval_samples_per_second": 33.195,
17
+ "eval_steps_per_second": 2.101,
18
+ "step": 14
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 42,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 3,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 64,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 2.43272801886851e-06,
31
+ "num_train_epochs": 3,
32
+ "per_device_train_batch_size": 64,
33
+ "seed": 2
34
+ }
35
+ }
run-9/checkpoint-14/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:312880702a4494ca30d4aa54bfc2850db558d72738cd0271d982f5d5e30696cf
3
+ size 4792
run-9/checkpoint-14/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Jan26_08-04-50_7ac5f092fd85/events.out.tfevents.1706288100.7ac5f092fd85.1710.12 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de4ee374597b674e1dcede4203adc71a004f5ca8f29697350b3af6648dab4130
3
- size 4988
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a33194ad8a27499f052c50863b452c4490cede3aacf93c5d10fb431e8c3286e6
3
+ size 5646
runs/Jan26_08-04-50_7ac5f092fd85/events.out.tfevents.1706288849.7ac5f092fd85.1710.13 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f46c005269460f558c3c780e6a0f028de71939820cabde443879c23b731a0e74
3
+ size 4987
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:692eacbd67898c3493bf506fda6014d3ca41265ad43b7b6a751a76178e23aa5b
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:312880702a4494ca30d4aa54bfc2850db558d72738cd0271d982f5d5e30696cf
3
  size 4792