Hugging Face's logo

LastSmile
/
HW001

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Metrics Community
LastSmile commited on
Commit
3e1bc59
·
1 Parent(s): 1081334

Training in progress, epoch 3

Browse files
Files changed (24) hide show
  1. model.safetensors +1 -1
  2. run-5/checkpoint-1070/config.json +25 -0
  3. run-5/checkpoint-1070/model.safetensors +3 -0
  4. run-5/checkpoint-1070/optimizer.pt +3 -0
  5. run-5/checkpoint-1070/rng_state.pth +3 -0
  6. run-5/checkpoint-1070/scheduler.pt +3 -0
  7. run-5/checkpoint-1070/special_tokens_map.json +7 -0
  8. run-5/checkpoint-1070/tokenizer.json +0 -0
  9. run-5/checkpoint-1070/tokenizer_config.json +55 -0
  10. run-5/checkpoint-1070/trainer_state.json +56 -0
  11. run-5/checkpoint-1070/training_args.bin +3 -0
  12. run-5/checkpoint-1070/vocab.txt +0 -0
  13. run-5/checkpoint-1605/config.json +25 -0
  14. run-5/checkpoint-1605/model.safetensors +3 -0
  15. run-5/checkpoint-1605/optimizer.pt +3 -0
  16. run-5/checkpoint-1605/rng_state.pth +3 -0
  17. run-5/checkpoint-1605/scheduler.pt +3 -0
  18. run-5/checkpoint-1605/special_tokens_map.json +7 -0
  19. run-5/checkpoint-1605/tokenizer.json +0 -0
  20. run-5/checkpoint-1605/tokenizer_config.json +55 -0
  21. run-5/checkpoint-1605/trainer_state.json +71 -0
  22. run-5/checkpoint-1605/training_args.bin +3 -0
  23. run-5/checkpoint-1605/vocab.txt +0 -0
  24. runs/Dec23_02-11-14_9e1ba8448b92/events.out.tfevents.1703298319.9e1ba8448b92.4051.7 +2 -2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e8ca9ab4b89cee3632670ffec874245ca742aabbdf4369dcbc4971b7f52a6a2
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a962880d8987dc1d14001cd059d15e5f6a51b7133479555d7f277bb3654a8de1
3
  size 267832560
run-5/checkpoint-1070/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": "4.36.2",
24
+ "vocab_size": 30522
25
+ }
run-5/checkpoint-1070/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:088a17c2076db925734dabbac7854c5f714df104b5ccbf08f40a073a8b2cdc7f
3
+ size 267832560
run-5/checkpoint-1070/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ba36f9750222bc6411858556cbef916fcb74d69c835dd5513a856b1c0c7d042
3
+ size 535727290
run-5/checkpoint-1070/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8304bb130716ca9cfa55f310172f71be4ef4d0b2fb7058b9c0cfc9da0c7cc08a
3
+ size 14308
run-5/checkpoint-1070/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29345294b51dd059225d1c70d347e41037acba099ec30844cfbaa338e1fa1304
3
+ size 1064
run-5/checkpoint-1070/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-1070/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-1070/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-1070/trainer_state.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.42393201453251056,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-1070",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1070,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.93,
13
+ "learning_rate": 3.581857476234381e-06,
14
+ "loss": 0.5602,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_loss": 0.5253874659538269,
20
+ "eval_matthews_correlation": 0.37934402970245285,
21
+ "eval_runtime": 0.7661,
22
+ "eval_samples_per_second": 1361.425,
23
+ "eval_steps_per_second": 86.15,
24
+ "step": 535
25
+ },
26
+ {
27
+ "epoch": 1.87,
28
+ "learning_rate": 1.9611074869880546e-06,
29
+ "loss": 0.4633,
30
+ "step": 1000
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_loss": 0.525027334690094,
35
+ "eval_matthews_correlation": 0.42393201453251056,
36
+ "eval_runtime": 0.732,
37
+ "eval_samples_per_second": 1424.943,
38
+ "eval_steps_per_second": 90.169,
39
+ "step": 1070
40
+ }
41
+ ],
42
+ "logging_steps": 500,
43
+ "max_steps": 1605,
44
+ "num_input_tokens_seen": 0,
45
+ "num_train_epochs": 3,
46
+ "save_steps": 500,
47
+ "total_flos": 85817141396496.0,
48
+ "train_batch_size": 16,
49
+ "trial_name": null,
50
+ "trial_params": {
51
+ "learning_rate": 5.2026074654807075e-06,
52
+ "num_train_epochs": 3,
53
+ "per_device_train_batch_size": 16,
54
+ "seed": 20
55
+ }
56
+ }
run-5/checkpoint-1070/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63a95b5651db410bfe48f3747985cdad9c08bf9386c5b61dca08eb067c77013b
3
+ size 4792
run-5/checkpoint-1070/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-1605/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": "4.36.2",
24
+ "vocab_size": 30522
25
+ }
run-5/checkpoint-1605/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a962880d8987dc1d14001cd059d15e5f6a51b7133479555d7f277bb3654a8de1
3
+ size 267832560
run-5/checkpoint-1605/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baa5a58aeac08cdfcc99907fd63c76fd27781fb41c051e72b0cde5fcf56883bc
3
+ size 535727290
run-5/checkpoint-1605/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95a066f3f5f5f306eff5591c80de2d297ae5a37264a94a69ec152690e3808aa0
3
+ size 14308
run-5/checkpoint-1605/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52de62782bdb91b82ce1da2baa52e366757428c7dead574d25eb3dad57ea5ef7
3
+ size 1064
run-5/checkpoint-1605/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-1605/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-1605/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-1605/trainer_state.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4335972500415117,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-1605",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1605,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.93,
13
+ "learning_rate": 3.581857476234381e-06,
14
+ "loss": 0.5602,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_loss": 0.5253874659538269,
20
+ "eval_matthews_correlation": 0.37934402970245285,
21
+ "eval_runtime": 0.7661,
22
+ "eval_samples_per_second": 1361.425,
23
+ "eval_steps_per_second": 86.15,
24
+ "step": 535
25
+ },
26
+ {
27
+ "epoch": 1.87,
28
+ "learning_rate": 1.9611074869880546e-06,
29
+ "loss": 0.4633,
30
+ "step": 1000
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_loss": 0.525027334690094,
35
+ "eval_matthews_correlation": 0.42393201453251056,
36
+ "eval_runtime": 0.732,
37
+ "eval_samples_per_second": 1424.943,
38
+ "eval_steps_per_second": 90.169,
39
+ "step": 1070
40
+ },
41
+ {
42
+ "epoch": 2.8,
43
+ "learning_rate": 3.4035749774172847e-07,
44
+ "loss": 0.4199,
45
+ "step": 1500
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_loss": 0.5216795206069946,
50
+ "eval_matthews_correlation": 0.4335972500415117,
51
+ "eval_runtime": 0.7254,
52
+ "eval_samples_per_second": 1437.826,
53
+ "eval_steps_per_second": 90.984,
54
+ "step": 1605
55
+ }
56
+ ],
57
+ "logging_steps": 500,
58
+ "max_steps": 1605,
59
+ "num_input_tokens_seen": 0,
60
+ "num_train_epochs": 3,
61
+ "save_steps": 500,
62
+ "total_flos": 128837740187748.0,
63
+ "train_batch_size": 16,
64
+ "trial_name": null,
65
+ "trial_params": {
66
+ "learning_rate": 5.2026074654807075e-06,
67
+ "num_train_epochs": 3,
68
+ "per_device_train_batch_size": 16,
69
+ "seed": 20
70
+ }
71
+ }
run-5/checkpoint-1605/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63a95b5651db410bfe48f3747985cdad9c08bf9386c5b61dca08eb067c77013b
3
+ size 4792
run-5/checkpoint-1605/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Dec23_02-11-14_9e1ba8448b92/events.out.tfevents.1703298319.9e1ba8448b92.4051.7 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99540c1bbb948c707a9d1081840ec6aef4ec970d747b7961aedbf40153d57fcd
3
- size 5329
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b8afcc19942fcaf505976665d5047fc5344e9d20441af649883e9a24923e00c
3
+ size 6175