Hugging Face's logo

andyWuTw
/
homework001

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Metrics Community
andyWuTw commited on
Commit
f06a90c
·
1 Parent(s): bee0513

Training in progress, epoch 5

Browse files
Files changed (13) hide show
  1. model.safetensors +1 -1
  2. run-1/checkpoint-5345/config.json +25 -0
  3. run-1/checkpoint-5345/model.safetensors +3 -0
  4. run-1/checkpoint-5345/optimizer.pt +3 -0
  5. run-1/checkpoint-5345/rng_state.pth +3 -0
  6. run-1/checkpoint-5345/scheduler.pt +3 -0
  7. run-1/checkpoint-5345/special_tokens_map.json +7 -0
  8. run-1/checkpoint-5345/tokenizer.json +0 -0
  9. run-1/checkpoint-5345/tokenizer_config.json +55 -0
  10. run-1/checkpoint-5345/trainer_state.json +131 -0
  11. run-1/checkpoint-5345/training_args.bin +3 -0
  12. run-1/checkpoint-5345/vocab.txt +0 -0
  13. runs/Dec23_02-16-37_5c7585257882/events.out.tfevents.1703298289.5c7585257882.414.3 +2 -2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a79c2da23f1a8aa2d33c0e916ecdcbdf7f935f0328add30b49499a6b07cbd728
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b54ab93c12a6243b73e5e2e568eba3327df11b4bb24bded942bb06b2c4bf68f3
3
  size 267832560
run-1/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-1/checkpoint-5345/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b54ab93c12a6243b73e5e2e568eba3327df11b4bb24bded942bb06b2c4bf68f3
3
+ size 267832560
run-1/checkpoint-5345/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a09aac2d0159da3d04f0d8bd1b1eb195c68e3c6222c4b89fd0099f7b3357cbe
3
+ size 535727290
run-1/checkpoint-5345/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5faf33e7b05fe77180b11933c8f941fbe7aa6892c4bf2f6d1c479b8f78ad060
3
+ size 14308
run-1/checkpoint-5345/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:185741c4990a4e55affe98830b51653c7af59d2798b2fc952fd5efe1fd87f84f
3
+ size 1064
run-1/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-1/checkpoint-5345/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/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-1/checkpoint-5345/trainer_state.json ADDED
@@ -0,0 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5308567193176762,
3
+ "best_model_checkpoint": "andyWuTw/homework001-finetuned-cola/run-1/checkpoint-5345",
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": 3.2452452129344327e-05,
14
+ "loss": 0.5576,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.94,
19
+ "learning_rate": 2.910338586212613e-05,
20
+ "loss": 0.5108,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 1.0,
25
+ "eval_loss": 0.49123480916023254,
26
+ "eval_matthews_correlation": 0.4402129756759477,
27
+ "eval_runtime": 0.7657,
28
+ "eval_samples_per_second": 1362.107,
29
+ "eval_steps_per_second": 86.193,
30
+ "step": 1069
31
+ },
32
+ {
33
+ "epoch": 1.4,
34
+ "learning_rate": 2.5754319594907933e-05,
35
+ "loss": 0.3607,
36
+ "step": 1500
37
+ },
38
+ {
39
+ "epoch": 1.87,
40
+ "learning_rate": 2.2405253327689737e-05,
41
+ "loss": 0.3536,
42
+ "step": 2000
43
+ },
44
+ {
45
+ "epoch": 2.0,
46
+ "eval_loss": 0.5718550682067871,
47
+ "eval_matthews_correlation": 0.5015124872115657,
48
+ "eval_runtime": 0.728,
49
+ "eval_samples_per_second": 1432.68,
50
+ "eval_steps_per_second": 90.659,
51
+ "step": 2138
52
+ },
53
+ {
54
+ "epoch": 2.34,
55
+ "learning_rate": 1.905618706047154e-05,
56
+ "loss": 0.254,
57
+ "step": 2500
58
+ },
59
+ {
60
+ "epoch": 2.81,
61
+ "learning_rate": 1.5707120793253344e-05,
62
+ "loss": 0.2655,
63
+ "step": 3000
64
+ },
65
+ {
66
+ "epoch": 3.0,
67
+ "eval_loss": 0.762388288974762,
68
+ "eval_matthews_correlation": 0.528465157424671,
69
+ "eval_runtime": 0.7265,
70
+ "eval_samples_per_second": 1435.582,
71
+ "eval_steps_per_second": 90.842,
72
+ "step": 3207
73
+ },
74
+ {
75
+ "epoch": 3.27,
76
+ "learning_rate": 1.2358054526035147e-05,
77
+ "loss": 0.1973,
78
+ "step": 3500
79
+ },
80
+ {
81
+ "epoch": 3.74,
82
+ "learning_rate": 9.008988258816951e-06,
83
+ "loss": 0.1485,
84
+ "step": 4000
85
+ },
86
+ {
87
+ "epoch": 4.0,
88
+ "eval_loss": 1.010642647743225,
89
+ "eval_matthews_correlation": 0.5132479296361289,
90
+ "eval_runtime": 0.7256,
91
+ "eval_samples_per_second": 1437.459,
92
+ "eval_steps_per_second": 90.961,
93
+ "step": 4276
94
+ },
95
+ {
96
+ "epoch": 4.21,
97
+ "learning_rate": 5.659921991598752e-06,
98
+ "loss": 0.1311,
99
+ "step": 4500
100
+ },
101
+ {
102
+ "epoch": 4.68,
103
+ "learning_rate": 2.310855724380556e-06,
104
+ "loss": 0.1107,
105
+ "step": 5000
106
+ },
107
+ {
108
+ "epoch": 5.0,
109
+ "eval_loss": 1.067962646484375,
110
+ "eval_matthews_correlation": 0.5308567193176762,
111
+ "eval_runtime": 0.7292,
112
+ "eval_samples_per_second": 1430.383,
113
+ "eval_steps_per_second": 90.513,
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": 188199951935856.0,
123
+ "train_batch_size": 8,
124
+ "trial_name": null,
125
+ "trial_params": {
126
+ "learning_rate": 3.5801518396562525e-05,
127
+ "num_train_epochs": 5,
128
+ "per_device_train_batch_size": 8,
129
+ "seed": 37
130
+ }
131
+ }
run-1/checkpoint-5345/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0cb55dad53927b5406db1fec190e847582487bb47dbf1f9d20c4d55a9c8beeb
3
+ size 4792
run-1/checkpoint-5345/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Dec23_02-16-37_5c7585257882/events.out.tfevents.1703298289.5c7585257882.414.3 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19c3b1d41522ebf13d5250cb458789d452a5dce010200e51bf3056807902012a
3
- size 7093
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8215c157d1d281b2bba36525b5a388f77d524de044d7a16d653150efff1bd8
3
+ size 7939