Hugging Face's logo

ArtoriasXV
/
distilbert-base-uncased-finetuned-cola

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Model card Files Metrics Community
ArtoriasXV commited on
Commit
b83701f
·
verified ·
1 Parent(s): db1c5c7

Training in progress, epoch 1

Browse files
Files changed (26) hide show
  1. model.safetensors +1 -1
  2. run-5/checkpoint-28/config.json +25 -0
  3. run-5/checkpoint-28/model.safetensors +3 -0
  4. run-5/checkpoint-28/optimizer.pt +3 -0
  5. run-5/checkpoint-28/rng_state.pth +3 -0
  6. run-5/checkpoint-28/scheduler.pt +3 -0
  7. run-5/checkpoint-28/special_tokens_map.json +7 -0
  8. run-5/checkpoint-28/tokenizer.json +0 -0
  9. run-5/checkpoint-28/tokenizer_config.json +55 -0
  10. run-5/checkpoint-28/trainer_state.json +44 -0
  11. run-5/checkpoint-28/training_args.bin +3 -0
  12. run-5/checkpoint-28/vocab.txt +0 -0
  13. run-5/checkpoint-42/config.json +25 -0
  14. run-5/checkpoint-42/model.safetensors +3 -0
  15. run-5/checkpoint-42/optimizer.pt +3 -0
  16. run-5/checkpoint-42/rng_state.pth +3 -0
  17. run-5/checkpoint-42/scheduler.pt +3 -0
  18. run-5/checkpoint-42/special_tokens_map.json +7 -0
  19. run-5/checkpoint-42/tokenizer.json +0 -0
  20. run-5/checkpoint-42/tokenizer_config.json +55 -0
  21. run-5/checkpoint-42/trainer_state.json +53 -0
  22. run-5/checkpoint-42/training_args.bin +3 -0
  23. run-5/checkpoint-42/vocab.txt +0 -0
  24. runs/Mar08_15-33-58_7fccc33f1b3d/events.out.tfevents.1709913268.7fccc33f1b3d.260.8 +3 -0
  25. runs/Mar08_15-33-58_7fccc33f1b3d/events.out.tfevents.1709913271.7fccc33f1b3d.260.9 +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:d9c7b49c6d8ba25a0d0f032df3444c693497291e893d0eb3f0c3988aeb07a88a
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d437ba0557553d73bf13e7cfd9c98f8546c9629c982de7cccb897ccbfdad8906
3
  size 267832560
run-5/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-5/checkpoint-28/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd8f5f258d6f9298a47941bc68df8d71591e01b6cc4400933bdd761b3f969857
3
+ size 267832560
run-5/checkpoint-28/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15fc47b2ab33d6dfdad6a2ba76a23938d7b10f67410992bd1b942026385598b0
3
+ size 535727290
run-5/checkpoint-28/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19c7873ffeb1cd74b23dcb152a997c1c5c273b7c1936ad71baf19cbb2c8039aa
3
+ size 14244
run-5/checkpoint-28/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c52f2bcf505ca6a6e8b227ec4b9424edab309a9414efd99cfc153622a3fa936d
3
+ size 1064
run-5/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-5/checkpoint-28/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/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-5/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-5/checkpoint-14",
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": 0.6160410046577454,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.692,
16
+ "eval_samples_per_second": 1507.255,
17
+ "eval_steps_per_second": 95.378,
18
+ "step": 14
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6135153770446777,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 0.7572,
25
+ "eval_samples_per_second": 1377.427,
26
+ "eval_steps_per_second": 87.162,
27
+ "step": 28
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 42,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 3,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 64,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 1.9926677441108413e-05,
40
+ "num_train_epochs": 3,
41
+ "per_device_train_batch_size": 64,
42
+ "seed": 36
43
+ }
44
+ }
run-5/checkpoint-28/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d5032917dcd256ad853291b278c3fd614ba75aec4f1d090975f8741663aca29
3
+ size 4984
run-5/checkpoint-28/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-42/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-5/checkpoint-42/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e98ca04f350b54bc5b648c13875461289a9ecf13742bb0f57b1cf7183990619e
3
+ size 267832560
run-5/checkpoint-42/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88706107456575575e183dc3cd2c01f3c53dbcc57666c22836cd2350c27087eb
3
+ size 535727290
run-5/checkpoint-42/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27dbe52c64c703b6c5d4ea4a865023d97795f52f0e06d182ee9ce908cb6d5404
3
+ size 14244
run-5/checkpoint-42/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4897b3e2382fc0038aae0acb3c6ae3117fb075ef7d8c28064890a66968a2ddd
3
+ size 1064
run-5/checkpoint-42/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-42/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-42/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-42/trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-14",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 42,
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": 0.6160410046577454,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.692,
16
+ "eval_samples_per_second": 1507.255,
17
+ "eval_steps_per_second": 95.378,
18
+ "step": 14
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6135153770446777,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 0.7572,
25
+ "eval_samples_per_second": 1377.427,
26
+ "eval_steps_per_second": 87.162,
27
+ "step": 28
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.6120091676712036,
32
+ "eval_matthews_correlation": 0.0,
33
+ "eval_runtime": 0.763,
34
+ "eval_samples_per_second": 1367.027,
35
+ "eval_steps_per_second": 86.504,
36
+ "step": 42
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 42,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 3,
43
+ "save_steps": 500,
44
+ "total_flos": 0,
45
+ "train_batch_size": 64,
46
+ "trial_name": null,
47
+ "trial_params": {
48
+ "learning_rate": 1.9926677441108413e-05,
49
+ "num_train_epochs": 3,
50
+ "per_device_train_batch_size": 64,
51
+ "seed": 36
52
+ }
53
+ }
run-5/checkpoint-42/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d5032917dcd256ad853291b278c3fd614ba75aec4f1d090975f8741663aca29
3
+ size 4984
run-5/checkpoint-42/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Mar08_15-33-58_7fccc33f1b3d/events.out.tfevents.1709913268.7fccc33f1b3d.260.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b446a8a8f6cb0225fe12895bb50d32c8fb25f7c8263e94e6b66b3a29ad5a698
3
+ size 4870
runs/Mar08_15-33-58_7fccc33f1b3d/events.out.tfevents.1709913271.7fccc33f1b3d.260.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6085a946827702b573a5754808811da6d96e81e66517e50095f7144242c841d5
3
+ size 6775
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d5032917dcd256ad853291b278c3fd614ba75aec4f1d090975f8741663aca29
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad5622bdb7172c1c8e962d591254e3206b4db43bc8557abbc9aa195dd03c32c6
3
  size 4984