Hugging Face's logo

halu1003
/
LLMClassWork1

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
Metrics Community
halu1003 commited on
Commit
dc8b5ec
·
1 Parent(s): 9b19e98

Training in progress, epoch 3

Browse files
Files changed (24) hide show
  1. model.safetensors +1 -1
  2. run-2/checkpoint-4276/config.json +25 -0
  3. run-2/checkpoint-4276/model.safetensors +3 -0
  4. run-2/checkpoint-4276/optimizer.pt +3 -0
  5. run-2/checkpoint-4276/rng_state.pth +3 -0
  6. run-2/checkpoint-4276/scheduler.pt +3 -0
  7. run-2/checkpoint-4276/special_tokens_map.json +7 -0
  8. run-2/checkpoint-4276/tokenizer.json +0 -0
  9. run-2/checkpoint-4276/tokenizer_config.json +55 -0
  10. run-2/checkpoint-4276/trainer_state.json +92 -0
  11. run-2/checkpoint-4276/training_args.bin +3 -0
  12. run-2/checkpoint-4276/vocab.txt +0 -0
  13. run-2/checkpoint-6414/config.json +25 -0
  14. run-2/checkpoint-6414/model.safetensors +3 -0
  15. run-2/checkpoint-6414/optimizer.pt +3 -0
  16. run-2/checkpoint-6414/rng_state.pth +3 -0
  17. run-2/checkpoint-6414/scheduler.pt +3 -0
  18. run-2/checkpoint-6414/special_tokens_map.json +7 -0
  19. run-2/checkpoint-6414/tokenizer.json +0 -0
  20. run-2/checkpoint-6414/tokenizer_config.json +55 -0
  21. run-2/checkpoint-6414/trainer_state.json +125 -0
  22. run-2/checkpoint-6414/training_args.bin +3 -0
  23. run-2/checkpoint-6414/vocab.txt +0 -0
  24. runs/Dec23_02-22-21_04248f4b0c3a/events.out.tfevents.1703298770.04248f4b0c3a.492.4 +2 -2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb37994c8d195c3403ae005a1dbdf662d7da0433fc507c766712b75a4a073113
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b22416acb57a20c87e73624357cf69b4784a4756ae3263dd6d5e6f0f9dc3628
3
  size 267832560
run-2/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-2/checkpoint-4276/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb37994c8d195c3403ae005a1dbdf662d7da0433fc507c766712b75a4a073113
3
+ size 267832560
run-2/checkpoint-4276/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2afc659253a6a4f90a0a28c77284ec5b6201727d45c36c14278d1a51386ee647
3
+ size 535727290
run-2/checkpoint-4276/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c76a9e2c882102b6bc05501887118bd602c4d5a830017585573b0bed099579e3
3
+ size 14308
run-2/checkpoint-4276/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7868247cde172106e4cbe200d71170d3dbffd9ba289518e41ff590a7429ad5e7
3
+ size 1064
run-2/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-2/checkpoint-4276/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/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-2/checkpoint-4276/trainer_state.json ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.3112801106717032,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/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": 5.6188127124741755e-05,
14
+ "loss": 0.6368,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.47,
19
+ "learning_rate": 5.269904819250494e-05,
20
+ "loss": 0.6054,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.7,
25
+ "learning_rate": 4.920996926026812e-05,
26
+ "loss": 0.6131,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.94,
31
+ "learning_rate": 4.57208903280313e-05,
32
+ "loss": 0.5971,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 1.0,
37
+ "eval_loss": 0.6043549180030823,
38
+ "eval_matthews_correlation": 0.16979966395795365,
39
+ "eval_runtime": 0.8177,
40
+ "eval_samples_per_second": 1275.601,
41
+ "eval_steps_per_second": 80.719,
42
+ "step": 2138
43
+ },
44
+ {
45
+ "epoch": 1.17,
46
+ "learning_rate": 4.2231811395794476e-05,
47
+ "loss": 0.5802,
48
+ "step": 2500
49
+ },
50
+ {
51
+ "epoch": 1.4,
52
+ "learning_rate": 3.874273246355766e-05,
53
+ "loss": 0.5465,
54
+ "step": 3000
55
+ },
56
+ {
57
+ "epoch": 1.64,
58
+ "learning_rate": 3.525365353132083e-05,
59
+ "loss": 0.575,
60
+ "step": 3500
61
+ },
62
+ {
63
+ "epoch": 1.87,
64
+ "learning_rate": 3.1764574599084014e-05,
65
+ "loss": 0.56,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 2.0,
70
+ "eval_loss": 0.8283206820487976,
71
+ "eval_matthews_correlation": 0.3112801106717032,
72
+ "eval_runtime": 0.7366,
73
+ "eval_samples_per_second": 1416.049,
74
+ "eval_steps_per_second": 89.606,
75
+ "step": 4276
76
+ }
77
+ ],
78
+ "logging_steps": 500,
79
+ "max_steps": 8552,
80
+ "num_input_tokens_seen": 0,
81
+ "num_train_epochs": 4,
82
+ "save_steps": 500,
83
+ "total_flos": 65437860034512.0,
84
+ "train_batch_size": 4,
85
+ "trial_name": null,
86
+ "trial_params": {
87
+ "learning_rate": 5.967720605697858e-05,
88
+ "num_train_epochs": 4,
89
+ "per_device_train_batch_size": 4,
90
+ "seed": 37
91
+ }
92
+ }
run-2/checkpoint-4276/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4cd2fef8507de0b6ec4fc6f0e972dd20ee83952ed9d6116f7f100b26d2a1eca
3
+ size 4792
run-2/checkpoint-4276/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-6414/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-2/checkpoint-6414/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b22416acb57a20c87e73624357cf69b4784a4756ae3263dd6d5e6f0f9dc3628
3
+ size 267832560
run-2/checkpoint-6414/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c82ecff406f9f5678fba412f4f492174c06db86136e05e23cac34649703cd842
3
+ size 535727290
run-2/checkpoint-6414/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32c99d72e10338ebcf4b2e0cdde22346a50fcce8e303722846f71d521fafb321
3
+ size 14308
run-2/checkpoint-6414/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b391d7d91d3441c3ddb8644ff65cf54fe356ca1ac57f9b87e1753c41d4ddcbc
3
+ size 1064
run-2/checkpoint-6414/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-2/checkpoint-6414/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-6414/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-2/checkpoint-6414/trainer_state.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.3321332844589781,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-6414",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 6414,
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": 5.6188127124741755e-05,
14
+ "loss": 0.6368,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.47,
19
+ "learning_rate": 5.269904819250494e-05,
20
+ "loss": 0.6054,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.7,
25
+ "learning_rate": 4.920996926026812e-05,
26
+ "loss": 0.6131,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.94,
31
+ "learning_rate": 4.57208903280313e-05,
32
+ "loss": 0.5971,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 1.0,
37
+ "eval_loss": 0.6043549180030823,
38
+ "eval_matthews_correlation": 0.16979966395795365,
39
+ "eval_runtime": 0.8177,
40
+ "eval_samples_per_second": 1275.601,
41
+ "eval_steps_per_second": 80.719,
42
+ "step": 2138
43
+ },
44
+ {
45
+ "epoch": 1.17,
46
+ "learning_rate": 4.2231811395794476e-05,
47
+ "loss": 0.5802,
48
+ "step": 2500
49
+ },
50
+ {
51
+ "epoch": 1.4,
52
+ "learning_rate": 3.874273246355766e-05,
53
+ "loss": 0.5465,
54
+ "step": 3000
55
+ },
56
+ {
57
+ "epoch": 1.64,
58
+ "learning_rate": 3.525365353132083e-05,
59
+ "loss": 0.575,
60
+ "step": 3500
61
+ },
62
+ {
63
+ "epoch": 1.87,
64
+ "learning_rate": 3.1764574599084014e-05,
65
+ "loss": 0.56,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 2.0,
70
+ "eval_loss": 0.8283206820487976,
71
+ "eval_matthews_correlation": 0.3112801106717032,
72
+ "eval_runtime": 0.7366,
73
+ "eval_samples_per_second": 1416.049,
74
+ "eval_steps_per_second": 89.606,
75
+ "step": 4276
76
+ },
77
+ {
78
+ "epoch": 2.1,
79
+ "learning_rate": 2.8275495666847193e-05,
80
+ "loss": 0.4468,
81
+ "step": 4500
82
+ },
83
+ {
84
+ "epoch": 2.34,
85
+ "learning_rate": 2.4786416734610375e-05,
86
+ "loss": 0.4467,
87
+ "step": 5000
88
+ },
89
+ {
90
+ "epoch": 2.57,
91
+ "learning_rate": 2.1297337802373553e-05,
92
+ "loss": 0.4318,
93
+ "step": 5500
94
+ },
95
+ {
96
+ "epoch": 2.81,
97
+ "learning_rate": 1.7808258870136732e-05,
98
+ "loss": 0.4282,
99
+ "step": 6000
100
+ },
101
+ {
102
+ "epoch": 3.0,
103
+ "eval_loss": 1.206721544265747,
104
+ "eval_matthews_correlation": 0.3321332844589781,
105
+ "eval_runtime": 0.7912,
106
+ "eval_samples_per_second": 1318.307,
107
+ "eval_steps_per_second": 83.421,
108
+ "step": 6414
109
+ }
110
+ ],
111
+ "logging_steps": 500,
112
+ "max_steps": 8552,
113
+ "num_input_tokens_seen": 0,
114
+ "num_train_epochs": 4,
115
+ "save_steps": 500,
116
+ "total_flos": 98055887150448.0,
117
+ "train_batch_size": 4,
118
+ "trial_name": null,
119
+ "trial_params": {
120
+ "learning_rate": 5.967720605697858e-05,
121
+ "num_train_epochs": 4,
122
+ "per_device_train_batch_size": 4,
123
+ "seed": 37
124
+ }
125
+ }
run-2/checkpoint-6414/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4cd2fef8507de0b6ec4fc6f0e972dd20ee83952ed9d6116f7f100b26d2a1eca
3
+ size 4792
run-2/checkpoint-6414/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Dec23_02-22-21_04248f4b0c3a/events.out.tfevents.1703298770.04248f4b0c3a.492.4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14b9ac68f93d6f2a706e457e18bb618aa30393fc441f2d4b5c13b2e9b9058cc9
3
- size 6590
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c223c52fd94e287fce08c411c90961041b8eb2806c1644da7f58786c5202535
3
+ size 7553