Hugging Face's logo

dannychou
/
Homework01

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
Metrics Community
dannychou commited on
Commit
19ed69e
·
1 Parent(s): f0b2345

Training in progress, epoch 5

Browse files
Files changed (24) hide show
  1. model.safetensors +1 -1
  2. run-4/checkpoint-4276/config.json +25 -0
  3. run-4/checkpoint-4276/model.safetensors +3 -0
  4. run-4/checkpoint-4276/optimizer.pt +3 -0
  5. run-4/checkpoint-4276/rng_state.pth +3 -0
  6. run-4/checkpoint-4276/scheduler.pt +3 -0
  7. run-4/checkpoint-4276/special_tokens_map.json +7 -0
  8. run-4/checkpoint-4276/tokenizer.json +0 -0
  9. run-4/checkpoint-4276/tokenizer_config.json +55 -0
  10. run-4/checkpoint-4276/trainer_state.json +110 -0
  11. run-4/checkpoint-4276/training_args.bin +3 -0
  12. run-4/checkpoint-4276/vocab.txt +0 -0
  13. run-4/checkpoint-5345/config.json +25 -0
  14. run-4/checkpoint-5345/model.safetensors +3 -0
  15. run-4/checkpoint-5345/optimizer.pt +3 -0
  16. run-4/checkpoint-5345/rng_state.pth +3 -0
  17. run-4/checkpoint-5345/scheduler.pt +3 -0
  18. run-4/checkpoint-5345/special_tokens_map.json +7 -0
  19. run-4/checkpoint-5345/tokenizer.json +0 -0
  20. run-4/checkpoint-5345/tokenizer_config.json +55 -0
  21. run-4/checkpoint-5345/trainer_state.json +131 -0
  22. run-4/checkpoint-5345/training_args.bin +3 -0
  23. run-4/checkpoint-5345/vocab.txt +0 -0
  24. runs/Dec23_02-10-12_067bf7a71e5c/events.out.tfevents.1703298708.067bf7a71e5c.178.6 +2 -2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:130dba37b199d9e6051dc08c45083f897acbfbf9abdae1dcc44ec4481dadb9db
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4faec631b7e017243ef62bf66c5e213869e7ee5f9e7f8424ebf4133c0d2dbe7
3
  size 267832560
run-4/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-4/checkpoint-4276/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38b7189c8926cf7c7aa16633162dcbf82e6df4309f8eb5ea1ee0d48f013870ff
3
+ size 267832560
run-4/checkpoint-4276/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:289b6eb3414b5a6bc6bb64abdf4715133cbef0335066a571c9d1d48367f8fe72
3
+ size 535727290
run-4/checkpoint-4276/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9cedc0a477ad9d6f459404c005bc13487992a7211da77e24405ec095616ac84
3
+ size 14308
run-4/checkpoint-4276/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcaa716f2dfcb819c1a0d1fc8da74feb53a04c7730b5aa9be4286b5778451b33
3
+ size 1064
run-4/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-4/checkpoint-4276/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/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-4/checkpoint-4276/trainer_state.json ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.543909089281463,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-2138",
4
+ "epoch": 4.0,
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": 0.47,
13
+ "learning_rate": 2.0681209971615274e-05,
14
+ "loss": 0.5488,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.94,
19
+ "learning_rate": 1.8546926176814934e-05,
20
+ "loss": 0.498,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 1.0,
25
+ "eval_loss": 0.48384082317352295,
26
+ "eval_matthews_correlation": 0.4611631351812362,
27
+ "eval_runtime": 0.7492,
28
+ "eval_samples_per_second": 1392.127,
29
+ "eval_steps_per_second": 88.092,
30
+ "step": 1069
31
+ },
32
+ {
33
+ "epoch": 1.4,
34
+ "learning_rate": 1.6412642382014598e-05,
35
+ "loss": 0.3532,
36
+ "step": 1500
37
+ },
38
+ {
39
+ "epoch": 1.87,
40
+ "learning_rate": 1.4278358587214258e-05,
41
+ "loss": 0.354,
42
+ "step": 2000
43
+ },
44
+ {
45
+ "epoch": 2.0,
46
+ "eval_loss": 0.5868804454803467,
47
+ "eval_matthews_correlation": 0.543909089281463,
48
+ "eval_runtime": 0.7926,
49
+ "eval_samples_per_second": 1315.987,
50
+ "eval_steps_per_second": 83.274,
51
+ "step": 2138
52
+ },
53
+ {
54
+ "epoch": 2.34,
55
+ "learning_rate": 1.214407479241392e-05,
56
+ "loss": 0.2699,
57
+ "step": 2500
58
+ },
59
+ {
60
+ "epoch": 2.81,
61
+ "learning_rate": 1.0009790997613584e-05,
62
+ "loss": 0.2462,
63
+ "step": 3000
64
+ },
65
+ {
66
+ "epoch": 3.0,
67
+ "eval_loss": 0.7930343747138977,
68
+ "eval_matthews_correlation": 0.5340667882909217,
69
+ "eval_runtime": 0.7474,
70
+ "eval_samples_per_second": 1395.496,
71
+ "eval_steps_per_second": 88.306,
72
+ "step": 3207
73
+ },
74
+ {
75
+ "epoch": 3.27,
76
+ "learning_rate": 7.875507202813246e-06,
77
+ "loss": 0.1931,
78
+ "step": 3500
79
+ },
80
+ {
81
+ "epoch": 3.74,
82
+ "learning_rate": 5.741223408012909e-06,
83
+ "loss": 0.1671,
84
+ "step": 4000
85
+ },
86
+ {
87
+ "epoch": 4.0,
88
+ "eval_loss": 1.0090364217758179,
89
+ "eval_matthews_correlation": 0.5279532549901665,
90
+ "eval_runtime": 1.1191,
91
+ "eval_samples_per_second": 931.964,
92
+ "eval_steps_per_second": 58.974,
93
+ "step": 4276
94
+ }
95
+ ],
96
+ "logging_steps": 500,
97
+ "max_steps": 5345,
98
+ "num_input_tokens_seen": 0,
99
+ "num_train_epochs": 5,
100
+ "save_steps": 500,
101
+ "total_flos": 150372489132540.0,
102
+ "train_batch_size": 8,
103
+ "trial_name": null,
104
+ "trial_params": {
105
+ "learning_rate": 2.281549376641561e-05,
106
+ "num_train_epochs": 5,
107
+ "per_device_train_batch_size": 8,
108
+ "seed": 24
109
+ }
110
+ }
run-4/checkpoint-4276/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc878cb8d07fea1f5c4cd27f162cb2669e0bb6636b584389e9be49e2633f0a30
3
+ size 4792
run-4/checkpoint-4276/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-5345/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-4/checkpoint-5345/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4faec631b7e017243ef62bf66c5e213869e7ee5f9e7f8424ebf4133c0d2dbe7
3
+ size 267832560
run-4/checkpoint-5345/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a9af1979b2b9b7e2e074175036cfd83db2436a348970e1281148cbf9c73f298
3
+ size 535727290
run-4/checkpoint-5345/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:454e397e9dc08dfe8f9488374b2a5ec23bc31ab335aedc32b09e9af7f9a0791a
3
+ size 14308
run-4/checkpoint-5345/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2f3dd10849d600e12d32b3137caba12b5ea8cb31ab7f5f26df31cdad0907990
3
+ size 1064
run-4/checkpoint-5345/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-4/checkpoint-5345/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-5345/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-4/checkpoint-5345/trainer_state.json ADDED
@@ -0,0 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.543909089281463,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-2138",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 5345,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.47,
13
+ "learning_rate": 2.0681209971615274e-05,
14
+ "loss": 0.5488,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.94,
19
+ "learning_rate": 1.8546926176814934e-05,
20
+ "loss": 0.498,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 1.0,
25
+ "eval_loss": 0.48384082317352295,
26
+ "eval_matthews_correlation": 0.4611631351812362,
27
+ "eval_runtime": 0.7492,
28
+ "eval_samples_per_second": 1392.127,
29
+ "eval_steps_per_second": 88.092,
30
+ "step": 1069
31
+ },
32
+ {
33
+ "epoch": 1.4,
34
+ "learning_rate": 1.6412642382014598e-05,
35
+ "loss": 0.3532,
36
+ "step": 1500
37
+ },
38
+ {
39
+ "epoch": 1.87,
40
+ "learning_rate": 1.4278358587214258e-05,
41
+ "loss": 0.354,
42
+ "step": 2000
43
+ },
44
+ {
45
+ "epoch": 2.0,
46
+ "eval_loss": 0.5868804454803467,
47
+ "eval_matthews_correlation": 0.543909089281463,
48
+ "eval_runtime": 0.7926,
49
+ "eval_samples_per_second": 1315.987,
50
+ "eval_steps_per_second": 83.274,
51
+ "step": 2138
52
+ },
53
+ {
54
+ "epoch": 2.34,
55
+ "learning_rate": 1.214407479241392e-05,
56
+ "loss": 0.2699,
57
+ "step": 2500
58
+ },
59
+ {
60
+ "epoch": 2.81,
61
+ "learning_rate": 1.0009790997613584e-05,
62
+ "loss": 0.2462,
63
+ "step": 3000
64
+ },
65
+ {
66
+ "epoch": 3.0,
67
+ "eval_loss": 0.7930343747138977,
68
+ "eval_matthews_correlation": 0.5340667882909217,
69
+ "eval_runtime": 0.7474,
70
+ "eval_samples_per_second": 1395.496,
71
+ "eval_steps_per_second": 88.306,
72
+ "step": 3207
73
+ },
74
+ {
75
+ "epoch": 3.27,
76
+ "learning_rate": 7.875507202813246e-06,
77
+ "loss": 0.1931,
78
+ "step": 3500
79
+ },
80
+ {
81
+ "epoch": 3.74,
82
+ "learning_rate": 5.741223408012909e-06,
83
+ "loss": 0.1671,
84
+ "step": 4000
85
+ },
86
+ {
87
+ "epoch": 4.0,
88
+ "eval_loss": 1.0090364217758179,
89
+ "eval_matthews_correlation": 0.5279532549901665,
90
+ "eval_runtime": 1.1191,
91
+ "eval_samples_per_second": 931.964,
92
+ "eval_steps_per_second": 58.974,
93
+ "step": 4276
94
+ },
95
+ {
96
+ "epoch": 4.21,
97
+ "learning_rate": 3.6069396132125703e-06,
98
+ "loss": 0.1374,
99
+ "step": 4500
100
+ },
101
+ {
102
+ "epoch": 4.68,
103
+ "learning_rate": 1.472655818412233e-06,
104
+ "loss": 0.097,
105
+ "step": 5000
106
+ },
107
+ {
108
+ "epoch": 5.0,
109
+ "eval_loss": 1.1014072895050049,
110
+ "eval_matthews_correlation": 0.5211120728046958,
111
+ "eval_runtime": 0.7198,
112
+ "eval_samples_per_second": 1448.925,
113
+ "eval_steps_per_second": 91.687,
114
+ "step": 5345
115
+ }
116
+ ],
117
+ "logging_steps": 500,
118
+ "max_steps": 5345,
119
+ "num_input_tokens_seen": 0,
120
+ "num_train_epochs": 5,
121
+ "save_steps": 500,
122
+ "total_flos": 188320776692052.0,
123
+ "train_batch_size": 8,
124
+ "trial_name": null,
125
+ "trial_params": {
126
+ "learning_rate": 2.281549376641561e-05,
127
+ "num_train_epochs": 5,
128
+ "per_device_train_batch_size": 8,
129
+ "seed": 24
130
+ }
131
+ }
run-4/checkpoint-5345/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc878cb8d07fea1f5c4cd27f162cb2669e0bb6636b584389e9be49e2633f0a30
3
+ size 4792
run-4/checkpoint-5345/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Dec23_02-10-12_067bf7a71e5c/events.out.tfevents.1703298708.067bf7a71e5c.178.6 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c86fcfd83947acebf571dd93ee7eeb9e28a3aaece7652c2fb6d9674b4a632e8
3
- size 7101
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eacc154f06c25c466fdadde55a0163879cc6b7c9a667b56e846207c8510aa52d
3
+ size 7947