Hugging Face's logo

AilingDAI
/
HM_1

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Metrics Community
AilingDAI commited on
Commit
0a90a8e
·
verified ·
1 Parent(s): 5810abf

Training in progress, epoch 1

Browse files
Files changed (26) hide show
  1. model.safetensors +1 -1
  2. run-8/checkpoint-1070/config.json +25 -0
  3. run-8/checkpoint-1070/model.safetensors +3 -0
  4. run-8/checkpoint-1070/optimizer.pt +3 -0
  5. run-8/checkpoint-1070/rng_state.pth +3 -0
  6. run-8/checkpoint-1070/scheduler.pt +3 -0
  7. run-8/checkpoint-1070/special_tokens_map.json +7 -0
  8. run-8/checkpoint-1070/tokenizer.json +0 -0
  9. run-8/checkpoint-1070/tokenizer_config.json +55 -0
  10. run-8/checkpoint-1070/trainer_state.json +58 -0
  11. run-8/checkpoint-1070/training_args.bin +3 -0
  12. run-8/checkpoint-1070/vocab.txt +0 -0
  13. run-8/checkpoint-1605/config.json +25 -0
  14. run-8/checkpoint-1605/model.safetensors +3 -0
  15. run-8/checkpoint-1605/optimizer.pt +3 -0
  16. run-8/checkpoint-1605/rng_state.pth +3 -0
  17. run-8/checkpoint-1605/scheduler.pt +3 -0
  18. run-8/checkpoint-1605/special_tokens_map.json +7 -0
  19. run-8/checkpoint-1605/tokenizer.json +0 -0
  20. run-8/checkpoint-1605/tokenizer_config.json +55 -0
  21. run-8/checkpoint-1605/trainer_state.json +74 -0
  22. run-8/checkpoint-1605/training_args.bin +3 -0
  23. run-8/checkpoint-1605/vocab.txt +0 -0
  24. runs/Mar23_02-10-25_52e0cb6c1736/events.out.tfevents.1711161265.52e0cb6c1736.459.11 +3 -0
  25. runs/Mar23_02-10-25_52e0cb6c1736/events.out.tfevents.1711161582.52e0cb6c1736.459.12 +3 -0
  26. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6af8ceaeaabc6af3df2cc1096d9f8e6aad1a69b3cf65efc9a9abc6aa1272efe
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9113d76ba545fb086fb6a5e9e3fc213529275493d8432e21f9e80dab7fab4bca
3
  size 267832560
run-8/checkpoint-1070/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": "4.39.1",
24
+ "vocab_size": 30522
25
+ }
run-8/checkpoint-1070/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a8546d79653727ef2e3472e47adc6789ef9114c68b99c38d94c2676fa8ce393
3
+ size 267832560
run-8/checkpoint-1070/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0b505e4de21a6c78d5d64b777912c32a5216dda8fd170c0680613b6fd98b908
3
+ size 535727290
run-8/checkpoint-1070/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:735953fa6cd11e734791dd5c81df81ae523716b7a8b84ab1913e5a1d4b7503d1
3
+ size 14308
run-8/checkpoint-1070/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aca70411c8e46e4b8cc88b10642bea0be4cca2663bc9c6744aa86912579aaab7
3
+ size 1064
run-8/checkpoint-1070/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-8/checkpoint-1070/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-1070/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-8/checkpoint-1070/trainer_state.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4901764242082043,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/checkpoint-1070",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1070,
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
+ "grad_norm": 12.733132362365723,
14
+ "learning_rate": 4.1412896561923345e-05,
15
+ "loss": 0.5383,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_loss": 0.4885631799697876,
21
+ "eval_matthews_correlation": 0.40824346633328423,
22
+ "eval_runtime": 0.7542,
23
+ "eval_samples_per_second": 1382.997,
24
+ "eval_steps_per_second": 87.515,
25
+ "step": 535
26
+ },
27
+ {
28
+ "epoch": 1.87,
29
+ "grad_norm": 6.756022930145264,
30
+ "learning_rate": 2.2674029339333595e-05,
31
+ "loss": 0.3226,
32
+ "step": 1000
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_loss": 0.4925340414047241,
37
+ "eval_matthews_correlation": 0.4901764242082043,
38
+ "eval_runtime": 0.8126,
39
+ "eval_samples_per_second": 1283.561,
40
+ "eval_steps_per_second": 81.222,
41
+ "step": 1070
42
+ }
43
+ ],
44
+ "logging_steps": 500,
45
+ "max_steps": 1605,
46
+ "num_input_tokens_seen": 0,
47
+ "num_train_epochs": 3,
48
+ "save_steps": 500,
49
+ "total_flos": 194805728542272.0,
50
+ "train_batch_size": 16,
51
+ "trial_name": null,
52
+ "trial_params": {
53
+ "learning_rate": 6.0151763784513094e-05,
54
+ "num_train_epochs": 3,
55
+ "per_device_train_batch_size": 16,
56
+ "seed": 33
57
+ }
58
+ }
run-8/checkpoint-1070/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f35b87dae681b4cabecc8611f7e21810b3ce0f859314ccdeac4709bfce1a14fe
3
+ size 4984
run-8/checkpoint-1070/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-1605/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": "4.39.1",
24
+ "vocab_size": 30522
25
+ }
run-8/checkpoint-1605/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ecf119c6accc06d88f0c29661ccf01c17c6b96792551f3a36c4e5fd732c8a07
3
+ size 267832560
run-8/checkpoint-1605/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:505490285099abf13aeb34cc94bd49da1dd95125225b2d207bf744b4038181a8
3
+ size 535727290
run-8/checkpoint-1605/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6844877a379b357f8ff18127035270a302389fab3af650d5edea9f984bbcb60c
3
+ size 14308
run-8/checkpoint-1605/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca73b027452dc18e9b6dcc95a1d1c9e7cdd8ed2aee2c1c6375531c2ac4b49ff6
3
+ size 1064
run-8/checkpoint-1605/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-8/checkpoint-1605/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-1605/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-8/checkpoint-1605/trainer_state.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4901764242082043,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/checkpoint-1070",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1605,
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
+ "grad_norm": 12.733132362365723,
14
+ "learning_rate": 4.1412896561923345e-05,
15
+ "loss": 0.5383,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_loss": 0.4885631799697876,
21
+ "eval_matthews_correlation": 0.40824346633328423,
22
+ "eval_runtime": 0.7542,
23
+ "eval_samples_per_second": 1382.997,
24
+ "eval_steps_per_second": 87.515,
25
+ "step": 535
26
+ },
27
+ {
28
+ "epoch": 1.87,
29
+ "grad_norm": 6.756022930145264,
30
+ "learning_rate": 2.2674029339333595e-05,
31
+ "loss": 0.3226,
32
+ "step": 1000
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_loss": 0.4925340414047241,
37
+ "eval_matthews_correlation": 0.4901764242082043,
38
+ "eval_runtime": 0.8126,
39
+ "eval_samples_per_second": 1283.561,
40
+ "eval_steps_per_second": 81.222,
41
+ "step": 1070
42
+ },
43
+ {
44
+ "epoch": 2.8,
45
+ "grad_norm": 18.629661560058594,
46
+ "learning_rate": 3.935162116743847e-06,
47
+ "loss": 0.1686,
48
+ "step": 1500
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_loss": 0.7480262517929077,
53
+ "eval_matthews_correlation": 0.4669544300405407,
54
+ "eval_runtime": 0.8215,
55
+ "eval_samples_per_second": 1269.67,
56
+ "eval_steps_per_second": 80.343,
57
+ "step": 1605
58
+ }
59
+ ],
60
+ "logging_steps": 500,
61
+ "max_steps": 1605,
62
+ "num_input_tokens_seen": 0,
63
+ "num_train_epochs": 3,
64
+ "save_steps": 500,
65
+ "total_flos": 237987771975636.0,
66
+ "train_batch_size": 16,
67
+ "trial_name": null,
68
+ "trial_params": {
69
+ "learning_rate": 6.0151763784513094e-05,
70
+ "num_train_epochs": 3,
71
+ "per_device_train_batch_size": 16,
72
+ "seed": 33
73
+ }
74
+ }
run-8/checkpoint-1605/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f35b87dae681b4cabecc8611f7e21810b3ce0f859314ccdeac4709bfce1a14fe
3
+ size 4984
run-8/checkpoint-1605/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Mar23_02-10-25_52e0cb6c1736/events.out.tfevents.1711161265.52e0cb6c1736.459.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:824051ce38db2a7f594dd8af1f7d3cf0b1499077d4ecef48c88c0507428cbd80
3
+ size 4922
runs/Mar23_02-10-25_52e0cb6c1736/events.out.tfevents.1711161582.52e0cb6c1736.459.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efe2ac40f513f67eb9598ff46d698e070346f7e677a4a3333e58419f70d2ecba
3
+ size 6492
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f35b87dae681b4cabecc8611f7e21810b3ce0f859314ccdeac4709bfce1a14fe
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:151c174a2ffa585401c97ac1e4a204237f812a0791c32e61c4a49909b4de743c
3
  size 4984