Hugging Face's logo

apuku0723
/
AIALMWork01

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
Metrics Community
apuku0723 commited on
Commit
69143fa
·
1 Parent(s): 4fb2117

Training in progress, epoch 1

Browse files
Files changed (25) hide show
  1. model.safetensors +1 -1
  2. run-2/checkpoint-2140/config.json +25 -0
  3. run-2/checkpoint-2140/model.safetensors +3 -0
  4. run-2/checkpoint-2140/optimizer.pt +3 -0
  5. run-2/checkpoint-2140/rng_state.pth +3 -0
  6. run-2/checkpoint-2140/scheduler.pt +3 -0
  7. run-2/checkpoint-2140/special_tokens_map.json +7 -0
  8. run-2/checkpoint-2140/tokenizer.json +0 -0
  9. run-2/checkpoint-2140/tokenizer_config.json +55 -0
  10. run-2/checkpoint-2140/trainer_state.json +86 -0
  11. run-2/checkpoint-2140/training_args.bin +3 -0
  12. run-2/checkpoint-2140/vocab.txt +0 -0
  13. run-3/checkpoint-535/config.json +25 -0
  14. run-3/checkpoint-535/model.safetensors +3 -0
  15. run-3/checkpoint-535/optimizer.pt +3 -0
  16. run-3/checkpoint-535/rng_state.pth +3 -0
  17. run-3/checkpoint-535/scheduler.pt +3 -0
  18. run-3/checkpoint-535/special_tokens_map.json +7 -0
  19. run-3/checkpoint-535/tokenizer.json +0 -0
  20. run-3/checkpoint-535/tokenizer_config.json +55 -0
  21. run-3/checkpoint-535/trainer_state.json +41 -0
  22. run-3/checkpoint-535/training_args.bin +3 -0
  23. run-3/checkpoint-535/vocab.txt +0 -0
  24. runs/Dec23_02-13-09_9bda7ec8aa80/events.out.tfevents.1703300066.9bda7ec8aa80.207.5 +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 sha256:98e549dcae2464c99aa1bb502cc607b4f7ae0454092cf01e5b4587ab937d7f3c
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e43af8d6793a1cb639f8b60b951fb7ce6569327be4bc8a87738d97a190d16ecf
3
  size 267832560
run-2/checkpoint-2140/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-2140/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee6f3a21831f8cad9e575903656cb7bfb55a6706b128cda0448721203c3ba5be
3
+ size 267832560
run-2/checkpoint-2140/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54f80837f64cdcec75941572e53cde1cf5fd3064b9acaf3075a2aa252e27e998
3
+ size 535727290
run-2/checkpoint-2140/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afc4b61b2eb5faa1cb87d2e6b687e2b4ef217fcb5b4c6af6c6d33d8ade9399c0
3
+ size 14244
run-2/checkpoint-2140/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99f2654624e34474bcfefdb6ab7a0baa2e72e88865cc2264d170f117cf30fc36
3
+ size 1064
run-2/checkpoint-2140/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-2140/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-2140/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-2140/trainer_state.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.27760340485389456,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-2140",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2140,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.93,
13
+ "learning_rate": 1.2971511744265264e-06,
14
+ "loss": 0.6123,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_loss": 0.5840290784835815,
20
+ "eval_matthews_correlation": 0.0,
21
+ "eval_runtime": 0.7468,
22
+ "eval_samples_per_second": 1396.633,
23
+ "eval_steps_per_second": 88.378,
24
+ "step": 535
25
+ },
26
+ {
27
+ "epoch": 1.87,
28
+ "learning_rate": 9.016782553940487e-07,
29
+ "loss": 0.5516,
30
+ "step": 1000
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_loss": 0.5512143969535828,
35
+ "eval_matthews_correlation": 0.0,
36
+ "eval_runtime": 0.8297,
37
+ "eval_samples_per_second": 1257.023,
38
+ "eval_steps_per_second": 79.543,
39
+ "step": 1070
40
+ },
41
+ {
42
+ "epoch": 2.8,
43
+ "learning_rate": 5.062053363615713e-07,
44
+ "loss": 0.5157,
45
+ "step": 1500
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_loss": 0.5409293174743652,
50
+ "eval_matthews_correlation": 0.20735838851492006,
51
+ "eval_runtime": 0.7486,
52
+ "eval_samples_per_second": 1393.339,
53
+ "eval_steps_per_second": 88.169,
54
+ "step": 1605
55
+ },
56
+ {
57
+ "epoch": 3.74,
58
+ "learning_rate": 1.107324173290937e-07,
59
+ "loss": 0.5031,
60
+ "step": 2000
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_loss": 0.5371504426002502,
65
+ "eval_matthews_correlation": 0.27760340485389456,
66
+ "eval_runtime": 1.3853,
67
+ "eval_samples_per_second": 752.912,
68
+ "eval_steps_per_second": 47.644,
69
+ "step": 2140
70
+ }
71
+ ],
72
+ "logging_steps": 500,
73
+ "max_steps": 2140,
74
+ "num_input_tokens_seen": 0,
75
+ "num_train_epochs": 4,
76
+ "save_steps": 500,
77
+ "total_flos": 171620311622040.0,
78
+ "train_batch_size": 16,
79
+ "trial_name": null,
80
+ "trial_params": {
81
+ "learning_rate": 1.692624093459004e-06,
82
+ "num_train_epochs": 4,
83
+ "per_device_train_batch_size": 16,
84
+ "seed": 6
85
+ }
86
+ }
run-2/checkpoint-2140/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddf6d1e41913d6b346143de2ae364997298bb25d96e0cee1326bb74d31817768
3
+ size 4792
run-2/checkpoint-2140/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-535/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-3/checkpoint-535/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e43af8d6793a1cb639f8b60b951fb7ce6569327be4bc8a87738d97a190d16ecf
3
+ size 267832560
run-3/checkpoint-535/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f59f19cee91ab063c77e59edfe7baef38a7e3f570710e8aa5d0a6666137524e7
3
+ size 535727290
run-3/checkpoint-535/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef104e2e0fc92f07429df53b0608736d2c27679bb32790be58be43a861f2b98c
3
+ size 14244
run-3/checkpoint-535/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d60e45b6afbf5a855a3f7420ca68168caca1fd164fbbdaa57369fd3ad0a7214
3
+ size 1064
run-3/checkpoint-535/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-3/checkpoint-535/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-535/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-3/checkpoint-535/trainer_state.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.36986609141954047,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-535",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 535,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.93,
13
+ "learning_rate": 3.480097556255927e-06,
14
+ "loss": 0.5622,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_loss": 0.5196835994720459,
20
+ "eval_matthews_correlation": 0.36986609141954047,
21
+ "eval_runtime": 0.7803,
22
+ "eval_samples_per_second": 1336.727,
23
+ "eval_steps_per_second": 84.587,
24
+ "step": 535
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 1605,
29
+ "num_input_tokens_seen": 0,
30
+ "num_train_epochs": 3,
31
+ "save_steps": 500,
32
+ "total_flos": 42935995589376.0,
33
+ "train_batch_size": 16,
34
+ "trial_name": null,
35
+ "trial_params": {
36
+ "learning_rate": 5.05480233284232e-06,
37
+ "num_train_epochs": 3,
38
+ "per_device_train_batch_size": 16,
39
+ "seed": 19
40
+ }
41
+ }
run-3/checkpoint-535/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c7854f8c5b24f447c6336a2e7013b1173fe81a9d26419c0db6c68611c45c8d1
3
+ size 4792
run-3/checkpoint-535/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Dec23_02-13-09_9bda7ec8aa80/events.out.tfevents.1703300066.9bda7ec8aa80.207.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc6fac3b8c57a17da8c0900818b0b15e53a0960f7fb05bd5570db577a9f9395f
3
+ size 6179
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ddf6d1e41913d6b346143de2ae364997298bb25d96e0cee1326bb74d31817768
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c7854f8c5b24f447c6336a2e7013b1173fe81a9d26419c0db6c68611c45c8d1
3
  size 4792