Hugging Face's logo

JiAYu1997
/
LLM_Practice001

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
JiAYu1997 commited on
Commit
abd04b7
•
1 Parent(s): 820d805

Training in progress, epoch 3

Browse files
Files changed (24) hide show
  1. model.safetensors +1 -1
  2. run-6/checkpoint-2138/config.json +25 -0
  3. run-6/checkpoint-2138/model.safetensors +3 -0
  4. run-6/checkpoint-2138/optimizer.pt +3 -0
  5. run-6/checkpoint-2138/rng_state.pth +3 -0
  6. run-6/checkpoint-2138/scheduler.pt +3 -0
  7. run-6/checkpoint-2138/special_tokens_map.json +7 -0
  8. run-6/checkpoint-2138/tokenizer.json +0 -0
  9. run-6/checkpoint-2138/tokenizer_config.json +55 -0
  10. run-6/checkpoint-2138/trainer_state.json +68 -0
  11. run-6/checkpoint-2138/training_args.bin +3 -0
  12. run-6/checkpoint-2138/vocab.txt +0 -0
  13. run-6/checkpoint-3207/config.json +25 -0
  14. run-6/checkpoint-3207/model.safetensors +3 -0
  15. run-6/checkpoint-3207/optimizer.pt +3 -0
  16. run-6/checkpoint-3207/rng_state.pth +3 -0
  17. run-6/checkpoint-3207/scheduler.pt +3 -0
  18. run-6/checkpoint-3207/special_tokens_map.json +7 -0
  19. run-6/checkpoint-3207/tokenizer.json +0 -0
  20. run-6/checkpoint-3207/tokenizer_config.json +55 -0
  21. run-6/checkpoint-3207/trainer_state.json +89 -0
  22. run-6/checkpoint-3207/training_args.bin +3 -0
  23. run-6/checkpoint-3207/vocab.txt +0 -0
  24. runs/Feb07_07-45-57_5815a830ed1c/events.out.tfevents.1707293645.5815a830ed1c.392.8 +2 -2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c1565a16dea560b84c0fc885f5fd43e11ddd6953b3589fca8f9562003a01883
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c102d8c6754fb7bc6b11ae2233327ab82105c5841fabd0885c218b3e3a3512fb
3
  size 267832560
run-6/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": "4.37.2",
24
+ "vocab_size": 30522
25
+ }
run-6/checkpoint-2138/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7ad0a0cba09f1e0d5467da572bb5b9d8d917458de4a47cc534460f6ae5333f6
3
+ size 267832560
run-6/checkpoint-2138/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4e1b12c48ae7ff819f2446f366416eda42adc9723db44274bc6a95c2af92de5
3
+ size 535727290
run-6/checkpoint-2138/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86b27810fd4ddd73bd2a2360ec7b92652df95da2087579e890d3766cc73a4eeb
3
+ size 14244
run-6/checkpoint-2138/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5809cce2e5529946827af47319a0d581a914d0137ad65f1bbad561c66b8a657c
3
+ size 1064
run-6/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-6/checkpoint-2138/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/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-6/checkpoint-2138/trainer_state.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4700719675330965,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/checkpoint-2138",
4
+ "epoch": 2.0,
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": 0.47,
13
+ "learning_rate": 5.3938263247342015e-06,
14
+ "loss": 0.5711,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.94,
19
+ "learning_rate": 4.397552529992015e-06,
20
+ "loss": 0.5074,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 1.0,
25
+ "eval_loss": 0.5285322070121765,
26
+ "eval_matthews_correlation": 0.3822545955758537,
27
+ "eval_runtime": 0.7108,
28
+ "eval_samples_per_second": 1467.388,
29
+ "eval_steps_per_second": 92.855,
30
+ "step": 1069
31
+ },
32
+ {
33
+ "epoch": 1.4,
34
+ "learning_rate": 3.401278735249827e-06,
35
+ "loss": 0.4345,
36
+ "step": 1500
37
+ },
38
+ {
39
+ "epoch": 1.87,
40
+ "learning_rate": 2.40500494050764e-06,
41
+ "loss": 0.4083,
42
+ "step": 2000
43
+ },
44
+ {
45
+ "epoch": 2.0,
46
+ "eval_loss": 0.5192927122116089,
47
+ "eval_matthews_correlation": 0.4700719675330965,
48
+ "eval_runtime": 0.7849,
49
+ "eval_samples_per_second": 1328.766,
50
+ "eval_steps_per_second": 84.083,
51
+ "step": 2138
52
+ }
53
+ ],
54
+ "logging_steps": 500,
55
+ "max_steps": 3207,
56
+ "num_input_tokens_seen": 0,
57
+ "num_train_epochs": 3,
58
+ "save_steps": 500,
59
+ "total_flos": 75650527275036.0,
60
+ "train_batch_size": 8,
61
+ "trial_name": null,
62
+ "trial_params": {
63
+ "learning_rate": 6.390100119476389e-06,
64
+ "num_train_epochs": 3,
65
+ "per_device_train_batch_size": 8,
66
+ "seed": 30
67
+ }
68
+ }
run-6/checkpoint-2138/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86a994ef5bc4c3f065d76f170bb71613406cd0b2b7db662734167cd50f6cccdf
3
+ size 4792
run-6/checkpoint-2138/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-3207/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": "4.37.2",
24
+ "vocab_size": 30522
25
+ }
run-6/checkpoint-3207/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c102d8c6754fb7bc6b11ae2233327ab82105c5841fabd0885c218b3e3a3512fb
3
+ size 267832560
run-6/checkpoint-3207/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e78d945bff311617e33aea7c11d2ebd818eb672e875c30138304fbe1a873fa53
3
+ size 535727290
run-6/checkpoint-3207/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:555df31ea7f09ac7fa802dc97e1aca1be05812e7ececa64bfe9cb814703c5068
3
+ size 14244
run-6/checkpoint-3207/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:495d2e00545b0091e1f49532f3a3bbd0c5cdde5717e8ebd542aa0c4f29671578
3
+ size 1064
run-6/checkpoint-3207/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-6/checkpoint-3207/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-3207/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-6/checkpoint-3207/trainer_state.json ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4764873250102919,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/checkpoint-3207",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3207,
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": 5.3938263247342015e-06,
14
+ "loss": 0.5711,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.94,
19
+ "learning_rate": 4.397552529992015e-06,
20
+ "loss": 0.5074,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 1.0,
25
+ "eval_loss": 0.5285322070121765,
26
+ "eval_matthews_correlation": 0.3822545955758537,
27
+ "eval_runtime": 0.7108,
28
+ "eval_samples_per_second": 1467.388,
29
+ "eval_steps_per_second": 92.855,
30
+ "step": 1069
31
+ },
32
+ {
33
+ "epoch": 1.4,
34
+ "learning_rate": 3.401278735249827e-06,
35
+ "loss": 0.4345,
36
+ "step": 1500
37
+ },
38
+ {
39
+ "epoch": 1.87,
40
+ "learning_rate": 2.40500494050764e-06,
41
+ "loss": 0.4083,
42
+ "step": 2000
43
+ },
44
+ {
45
+ "epoch": 2.0,
46
+ "eval_loss": 0.5192927122116089,
47
+ "eval_matthews_correlation": 0.4700719675330965,
48
+ "eval_runtime": 0.7849,
49
+ "eval_samples_per_second": 1328.766,
50
+ "eval_steps_per_second": 84.083,
51
+ "step": 2138
52
+ },
53
+ {
54
+ "epoch": 2.34,
55
+ "learning_rate": 1.4087311457654528e-06,
56
+ "loss": 0.3741,
57
+ "step": 2500
58
+ },
59
+ {
60
+ "epoch": 2.81,
61
+ "learning_rate": 4.1245735102326556e-07,
62
+ "loss": 0.3494,
63
+ "step": 3000
64
+ },
65
+ {
66
+ "epoch": 3.0,
67
+ "eval_loss": 0.5613988041877747,
68
+ "eval_matthews_correlation": 0.4764873250102919,
69
+ "eval_runtime": 0.7007,
70
+ "eval_samples_per_second": 1488.508,
71
+ "eval_steps_per_second": 94.191,
72
+ "step": 3207
73
+ }
74
+ ],
75
+ "logging_steps": 500,
76
+ "max_steps": 3207,
77
+ "num_input_tokens_seen": 0,
78
+ "num_train_epochs": 3,
79
+ "save_steps": 500,
80
+ "total_flos": 113311112203092.0,
81
+ "train_batch_size": 8,
82
+ "trial_name": null,
83
+ "trial_params": {
84
+ "learning_rate": 6.390100119476389e-06,
85
+ "num_train_epochs": 3,
86
+ "per_device_train_batch_size": 8,
87
+ "seed": 30
88
+ }
89
+ }
run-6/checkpoint-3207/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86a994ef5bc4c3f065d76f170bb71613406cd0b2b7db662734167cd50f6cccdf
3
+ size 4792
run-6/checkpoint-3207/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Feb07_07-45-57_5815a830ed1c/events.out.tfevents.1707293645.5815a830ed1c.392.8 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b813a22343a58b34b0d4cf752424d9cef6e8a89689f2f99aadb1d72f3b337280
3
- size 5651
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42c4e35a83b7ba011aaed892bf7632b4c8cfe1513e116aa6a822cb7e8708b994
3
+ size 6654