Hugging Face's logo

SjardiWillems
/
distilbert-base-uncased-finetuned-cola

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
SjardiWillems commited on
Commit
7217196
•
1 Parent(s): 9df15df

Training in progress, epoch 1

Browse files
Files changed (27) hide show
  1. model.safetensors +1 -1
  2. run-4/checkpoint-28/config.json +25 -0
  3. run-4/checkpoint-28/model.safetensors +3 -0
  4. run-4/checkpoint-28/optimizer.pt +3 -0
  5. run-4/checkpoint-28/rng_state.pth +3 -0
  6. run-4/checkpoint-28/scheduler.pt +3 -0
  7. run-4/checkpoint-28/special_tokens_map.json +7 -0
  8. run-4/checkpoint-28/tokenizer.json +0 -0
  9. run-4/checkpoint-28/tokenizer_config.json +55 -0
  10. run-4/checkpoint-28/trainer_state.json +44 -0
  11. run-4/checkpoint-28/training_args.bin +3 -0
  12. run-4/checkpoint-28/vocab.txt +0 -0
  13. run-7/checkpoint-214/config.json +25 -0
  14. run-7/checkpoint-214/model.safetensors +3 -0
  15. run-7/checkpoint-214/optimizer.pt +3 -0
  16. run-7/checkpoint-214/rng_state.pth +3 -0
  17. run-7/checkpoint-214/scheduler.pt +3 -0
  18. run-7/checkpoint-214/special_tokens_map.json +7 -0
  19. run-7/checkpoint-214/tokenizer.json +0 -0
  20. run-7/checkpoint-214/tokenizer_config.json +55 -0
  21. run-7/checkpoint-214/trainer_state.json +35 -0
  22. run-7/checkpoint-214/training_args.bin +3 -0
  23. run-7/checkpoint-214/vocab.txt +0 -0
  24. runs/Mar03_12-09-14_d132a4f4eb3e/events.out.tfevents.1709468163.d132a4f4eb3e.547.7 +3 -0
  25. runs/Mar03_12-09-14_d132a4f4eb3e/events.out.tfevents.1709468165.d132a4f4eb3e.547.8 +3 -0
  26. runs/Mar03_12-09-14_d132a4f4eb3e/events.out.tfevents.1709468168.d132a4f4eb3e.547.9 +3 -0
  27. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:277e869931432944b230640c18d6f80856a865ae6e6d176aabfdaef3544d4792
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ce053085dba606f02c99f5a26489e2408e8e7ef3bf4ee7d38f42add1c26ae45
3
  size 267832560
run-4/checkpoint-28/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": "4.38.2",
24
+ "vocab_size": 30522
25
+ }
run-4/checkpoint-28/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b38f3f108b688e85145e94b5b56a28c00f9561110ded714c3d71987fe8f0b4c
3
+ size 267832560
run-4/checkpoint-28/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19eebd242c4f4c63f900985a41c9d65e824eccbf34e3e8ae3ee3d9b967b2201f
3
+ size 535727290
run-4/checkpoint-28/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0271999a8810dd52694b83db2238813229da6d77696350886a6251a48fcf498
3
+ size 14244
run-4/checkpoint-28/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c4bd2dc9fbe87657ae6126fbf1791044201ea88bf50f33bc11e6c4201643f66
3
+ size 1064
run-4/checkpoint-28/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-28/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-28/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-28/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-28",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 28,
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": 0.6748577952384949,
14
+ "eval_matthews_correlation": -0.02339059069282274,
15
+ "eval_runtime": 0.5175,
16
+ "eval_samples_per_second": 2015.397,
17
+ "eval_steps_per_second": 127.532,
18
+ "step": 14
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6442534923553467,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 0.5351,
25
+ "eval_samples_per_second": 1949.087,
26
+ "eval_steps_per_second": 123.336,
27
+ "step": 28
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 28,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 2,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 64,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 9.275459477508523e-06,
40
+ "num_train_epochs": 2,
41
+ "per_device_train_batch_size": 64,
42
+ "seed": 19
43
+ }
44
+ }
run-4/checkpoint-28/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f215b8d0a2d3f4dfd3304f2a727dab785e1a5bd6316594447c1595a03c7703c
3
+ size 4984
run-4/checkpoint-28/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-214/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": "4.38.2",
24
+ "vocab_size": 30522
25
+ }
run-7/checkpoint-214/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ce053085dba606f02c99f5a26489e2408e8e7ef3bf4ee7d38f42add1c26ae45
3
+ size 267832560
run-7/checkpoint-214/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:678268cf7e0dece0ba15de5009d7c602194a59d1c467aa8148f5c16f88997118
3
+ size 535727290
run-7/checkpoint-214/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0df95744af71f976e7e85af4867a6ab394f1c284bf316b69ce7b0b0a878125bc
3
+ size 14308
run-7/checkpoint-214/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78041563af539037fce64505e87bbea66c5ce671d07975fb041bcd61c5986c8b
3
+ size 1064
run-7/checkpoint-214/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-214/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-214/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-214/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-214",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 214,
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": 0.5881524085998535,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.5145,
16
+ "eval_samples_per_second": 2027.266,
17
+ "eval_steps_per_second": 128.283,
18
+ "step": 214
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 1070,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 5,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 4,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 1.1749374614377834e-05,
31
+ "num_train_epochs": 5,
32
+ "per_device_train_batch_size": 4,
33
+ "seed": 24
34
+ }
35
+ }
run-7/checkpoint-214/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9fcb7249a5efa5afe771702791f5160b4a2945d2ff42557241bfc280f53e9e0
3
+ size 4984
run-7/checkpoint-214/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Mar03_12-09-14_d132a4f4eb3e/events.out.tfevents.1709468163.d132a4f4eb3e.547.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dbc10621fc0522208291678a54a93b3c6ca81883310235d1976343d1d4c95e0
3
+ size 4871
runs/Mar03_12-09-14_d132a4f4eb3e/events.out.tfevents.1709468165.d132a4f4eb3e.547.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e229263264bca276cdadb0180404c463e187e35dc948c80c877e034c1a2c2957
3
+ size 4872
runs/Mar03_12-09-14_d132a4f4eb3e/events.out.tfevents.1709468168.d132a4f4eb3e.547.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c185ff30b8d8efdccaf9087f8f26c77846ca4172cb84102758e2d9989ef1f34b
3
+ size 6993
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f215b8d0a2d3f4dfd3304f2a727dab785e1a5bd6316594447c1595a03c7703c
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9fcb7249a5efa5afe771702791f5160b4a2945d2ff42557241bfc280f53e9e0
3
  size 4984