Hugging Face's logo

Ethan615
/
try

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Metrics Community
Ethan615 commited on
Commit
59a9c26
·
1 Parent(s): 97a453b

Training in progress, epoch 2

Browse files
Files changed (25) hide show
  1. model.safetensors +1 -1
  2. run-0/checkpoint-2138/config.json +25 -0
  3. run-0/checkpoint-2138/model.safetensors +3 -0
  4. run-0/checkpoint-2138/optimizer.pt +3 -0
  5. run-0/checkpoint-2138/rng_state.pth +3 -0
  6. run-0/checkpoint-2138/scheduler.pt +3 -0
  7. run-0/checkpoint-2138/special_tokens_map.json +7 -0
  8. run-0/checkpoint-2138/tokenizer.json +0 -0
  9. run-0/checkpoint-2138/tokenizer_config.json +55 -0
  10. run-0/checkpoint-2138/trainer_state.json +59 -0
  11. run-0/checkpoint-2138/training_args.bin +3 -0
  12. run-0/checkpoint-2138/vocab.txt +0 -0
  13. run-0/checkpoint-4276/config.json +25 -0
  14. run-0/checkpoint-4276/model.safetensors +3 -0
  15. run-0/checkpoint-4276/optimizer.pt +3 -0
  16. run-0/checkpoint-4276/rng_state.pth +3 -0
  17. run-0/checkpoint-4276/scheduler.pt +3 -0
  18. run-0/checkpoint-4276/special_tokens_map.json +7 -0
  19. run-0/checkpoint-4276/tokenizer.json +0 -0
  20. run-0/checkpoint-4276/tokenizer_config.json +55 -0
  21. run-0/checkpoint-4276/trainer_state.json +92 -0
  22. run-0/checkpoint-4276/training_args.bin +3 -0
  23. run-0/checkpoint-4276/vocab.txt +0 -0
  24. runs/Dec23_01-09-39_cab176ec49ea/events.out.tfevents.1703294132.cab176ec49ea.681.2 +3 -0
  25. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b508e1af35173ae3f802f74a9e81434c4401fafb38281b6896fa211683516b75
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2ad2c39211fbc204817af62eefaa7eceac8c9136c0ddcea09a9f3cfebd16bea
3
  size 267832560
run-0/checkpoint-2138/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-0/checkpoint-2138/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01c2f4589f772b2a183a5db9074077e3604c774ddde9f6e6fa247ba2bec1891a
3
+ size 267832560
run-0/checkpoint-2138/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1bdffc1cada2f465cc5f614aba9a5fa6aedaaa320a62651ddadbae3de523a36
3
+ size 535727290
run-0/checkpoint-2138/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a1d34d8c66debf8d31f2b8edc92db8048a10207e2dc6a5cfef15845cb45e1e3
3
+ size 14244
run-0/checkpoint-2138/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1933aad2e4d1e0f9d8028ca1bd063befa7ee5a4f39958c3683aeb5e93ba8667
3
+ size 1064
run-0/checkpoint-2138/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-0/checkpoint-2138/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-2138/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-0/checkpoint-2138/trainer_state.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.40454640840116707,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-2138",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2138,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.23,
13
+ "learning_rate": 9.967147053469058e-06,
14
+ "loss": 0.5657,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.47,
19
+ "learning_rate": 8.647344742363515e-06,
20
+ "loss": 0.5621,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.7,
25
+ "learning_rate": 7.327542431257973e-06,
26
+ "loss": 0.5429,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.94,
31
+ "learning_rate": 6.0077401201524294e-06,
32
+ "loss": 0.5214,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 1.0,
37
+ "eval_loss": 0.5339541435241699,
38
+ "eval_matthews_correlation": 0.40454640840116707,
39
+ "eval_runtime": 0.7883,
40
+ "eval_samples_per_second": 1323.162,
41
+ "eval_steps_per_second": 83.728,
42
+ "step": 2138
43
+ }
44
+ ],
45
+ "logging_steps": 500,
46
+ "max_steps": 4276,
47
+ "num_input_tokens_seen": 0,
48
+ "num_train_epochs": 2,
49
+ "save_steps": 500,
50
+ "total_flos": 32490734225040.0,
51
+ "train_batch_size": 4,
52
+ "trial_name": null,
53
+ "trial_params": {
54
+ "learning_rate": 1.1286949364574601e-05,
55
+ "num_train_epochs": 2,
56
+ "per_device_train_batch_size": 4,
57
+ "seed": 27
58
+ }
59
+ }
run-0/checkpoint-2138/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0819cb158943ae09f3b80bb459146d75a549846361b972033a0ddb1fc169aaf
3
+ size 4792
run-0/checkpoint-2138/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-4276/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-0/checkpoint-4276/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2ad2c39211fbc204817af62eefaa7eceac8c9136c0ddcea09a9f3cfebd16bea
3
+ size 267832560
run-0/checkpoint-4276/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e85f4653d58a42bff107ce13cbbd87baeadf0e74cf9d886534ebb77ebdbd0507
3
+ size 535727290
run-0/checkpoint-4276/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b92b7ebf70483fa612250f363a3006dc1b89c25a92d56b1971cccf28491aeaa6
3
+ size 14244
run-0/checkpoint-4276/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14b5cbc399794fef1516c5b4d2315d0d9a865d6a8c8a45e1494bac700a3da82f
3
+ size 1064
run-0/checkpoint-4276/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-0/checkpoint-4276/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-4276/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-0/checkpoint-4276/trainer_state.json ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4975221305697031,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-4276",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 4276,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.23,
13
+ "learning_rate": 9.967147053469058e-06,
14
+ "loss": 0.5657,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.47,
19
+ "learning_rate": 8.647344742363515e-06,
20
+ "loss": 0.5621,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.7,
25
+ "learning_rate": 7.327542431257973e-06,
26
+ "loss": 0.5429,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.94,
31
+ "learning_rate": 6.0077401201524294e-06,
32
+ "loss": 0.5214,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 1.0,
37
+ "eval_loss": 0.5339541435241699,
38
+ "eval_matthews_correlation": 0.40454640840116707,
39
+ "eval_runtime": 0.7883,
40
+ "eval_samples_per_second": 1323.162,
41
+ "eval_steps_per_second": 83.728,
42
+ "step": 2138
43
+ },
44
+ {
45
+ "epoch": 1.17,
46
+ "learning_rate": 4.687937809046888e-06,
47
+ "loss": 0.4709,
48
+ "step": 2500
49
+ },
50
+ {
51
+ "epoch": 1.4,
52
+ "learning_rate": 3.368135497941345e-06,
53
+ "loss": 0.4733,
54
+ "step": 3000
55
+ },
56
+ {
57
+ "epoch": 1.64,
58
+ "learning_rate": 2.048333186835802e-06,
59
+ "loss": 0.4707,
60
+ "step": 3500
61
+ },
62
+ {
63
+ "epoch": 1.87,
64
+ "learning_rate": 7.285308757302596e-07,
65
+ "loss": 0.5123,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 2.0,
70
+ "eval_loss": 0.7701239585876465,
71
+ "eval_matthews_correlation": 0.4975221305697031,
72
+ "eval_runtime": 0.7314,
73
+ "eval_samples_per_second": 1426.085,
74
+ "eval_steps_per_second": 90.241,
75
+ "step": 4276
76
+ }
77
+ ],
78
+ "logging_steps": 500,
79
+ "max_steps": 4276,
80
+ "num_input_tokens_seen": 0,
81
+ "num_train_epochs": 2,
82
+ "save_steps": 500,
83
+ "total_flos": 65123767413480.0,
84
+ "train_batch_size": 4,
85
+ "trial_name": null,
86
+ "trial_params": {
87
+ "learning_rate": 1.1286949364574601e-05,
88
+ "num_train_epochs": 2,
89
+ "per_device_train_batch_size": 4,
90
+ "seed": 27
91
+ }
92
+ }
run-0/checkpoint-4276/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0819cb158943ae09f3b80bb459146d75a549846361b972033a0ddb1fc169aaf
3
+ size 4792
run-0/checkpoint-4276/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Dec23_01-09-39_cab176ec49ea/events.out.tfevents.1703294132.cab176ec49ea.681.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2677412e710de3aceb06f5bae443af712f76283c598c7e47d7b9d587e6bd841d
3
+ size 6621
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1cd66a3a4fb25c6aa29b2ec337d29c6cfa6ef081de82a68f11191e0160e589a1
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0819cb158943ae09f3b80bb459146d75a549846361b972033a0ddb1fc169aaf
3
  size 4792