Hugging Face's logo

Poodja
/
distilbert-base-uncased-finetuned-cola

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Model card Files Metrics Community
Poodja commited on
Commit
dab1fae
·
verified ·
1 Parent(s): 467ae60

Training in progress, epoch 1

Browse files
Files changed (26) hide show
  1. model.safetensors +1 -1
  2. run-7/checkpoint-27/config.json +25 -0
  3. run-7/checkpoint-27/model.safetensors +3 -0
  4. run-7/checkpoint-27/optimizer.pt +3 -0
  5. run-7/checkpoint-27/rng_state.pth +3 -0
  6. run-7/checkpoint-27/scheduler.pt +3 -0
  7. run-7/checkpoint-27/special_tokens_map.json +7 -0
  8. run-7/checkpoint-27/tokenizer.json +0 -0
  9. run-7/checkpoint-27/tokenizer_config.json +55 -0
  10. run-7/checkpoint-27/trainer_state.json +35 -0
  11. run-7/checkpoint-27/training_args.bin +3 -0
  12. run-7/checkpoint-27/vocab.txt +0 -0
  13. run-7/checkpoint-54/config.json +25 -0
  14. run-7/checkpoint-54/model.safetensors +3 -0
  15. run-7/checkpoint-54/optimizer.pt +3 -0
  16. run-7/checkpoint-54/rng_state.pth +3 -0
  17. run-7/checkpoint-54/scheduler.pt +3 -0
  18. run-7/checkpoint-54/special_tokens_map.json +7 -0
  19. run-7/checkpoint-54/tokenizer.json +0 -0
  20. run-7/checkpoint-54/tokenizer_config.json +55 -0
  21. run-7/checkpoint-54/trainer_state.json +44 -0
  22. run-7/checkpoint-54/training_args.bin +3 -0
  23. run-7/checkpoint-54/vocab.txt +0 -0
  24. runs/Feb27_13-20-57_4ffe06e164fd/events.out.tfevents.1709042479.4ffe06e164fd.373.9 +3 -0
  25. runs/Feb27_13-20-57_4ffe06e164fd/events.out.tfevents.1709042612.4ffe06e164fd.373.10 +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 sha256:2d9d23539cd0695db1fa3cf1edbe16f251e6fdee17c0c8565e864464fb03af40
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66f6dc4976add4fa7a1018c071ef317964482b2988e73b3cf0f9432489872805
3
  size 267832560
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 sha256:13c186e40f60b208c86f1f32cb70b76cf0615d6fae227ca20be97b4da093df26
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 sha256:1d1dfa1709a3e7997f9f604e5e8192840d9b6d0db4c9164eda0a19084a001331
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:ae837617b0afa0ec944d90976998d63cb827b1ae141579dc94411d023f1bcd81
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 sha256:8961ec16e0e41d87eab9252b685dd90b87bcd940b14b9c52fbd0f0aa94e78a37
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": 0.6133371591567993,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7749,
16
+ "eval_samples_per_second": 1345.953,
17
+ "eval_steps_per_second": 85.171,
18
+ "step": 27
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 54,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 2,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 32,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 1.2305995139643607e-05,
31
+ "num_train_epochs": 2,
32
+ "per_device_train_batch_size": 32,
33
+ "seed": 18
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 sha256:50b1e2ba9d31980fe4517bc1c228c76ff8d2c802891778d650c99b93abd8d834
3
+ size 4984
run-7/checkpoint-27/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-54/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-54/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9eac9c65667a2326be68879b85f16c1ecdb2b4c56c52eee7d71c516e21cd0f3a
3
+ size 267832560
run-7/checkpoint-54/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:957b788c562cdf65c5e03f22c218874c55f321ee8a7d1a478b78d688a6401c09
3
+ size 535727290
run-7/checkpoint-54/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27d5f6107fea9ff9520b9afc83db118d51d2d35f3dfccb6b2e999772386f02ee
3
+ size 14244
run-7/checkpoint-54/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcf0531eb16d12ed29f5cf65bd1bffe5fade9c48fc629b5390caf62369ad4749
3
+ size 1064
run-7/checkpoint-54/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-54/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-54/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-54/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-27",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 54,
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": 0.6133371591567993,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7749,
16
+ "eval_samples_per_second": 1345.953,
17
+ "eval_steps_per_second": 85.171,
18
+ "step": 27
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.607426106929779,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 0.7817,
25
+ "eval_samples_per_second": 1334.272,
26
+ "eval_steps_per_second": 84.431,
27
+ "step": 54
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 54,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 2,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 32,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 1.2305995139643607e-05,
40
+ "num_train_epochs": 2,
41
+ "per_device_train_batch_size": 32,
42
+ "seed": 18
43
+ }
44
+ }
run-7/checkpoint-54/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50b1e2ba9d31980fe4517bc1c228c76ff8d2c802891778d650c99b93abd8d834
3
+ size 4984
run-7/checkpoint-54/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Feb27_13-20-57_4ffe06e164fd/events.out.tfevents.1709042479.4ffe06e164fd.373.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebaa358ce2534a05845a1a8725c520bb0c17cb5753be3e5f2a94d41c7bbb14a1
3
+ size 5549
runs/Feb27_13-20-57_4ffe06e164fd/events.out.tfevents.1709042612.4ffe06e164fd.373.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a50b14e407768a9341661446dac7662f665fb6c28ee7440995ac6778f89386e1
3
+ size 6205
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f3c8a6180c576f3fcd336e4699de32476040a2d72ac3a97504067164856bce52
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dc1c6b307c6ca7717f881c029f7fc58a4f9ed6aab13cb972a5ddda6c4579cb9
3
  size 4984