Hugging Face's logo

azliza794
/
llm24

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
azliza794 commited on
Commit
1e9f6f4
·
verified ·
1 Parent(s): d175348

Training in progress, epoch 1

Browse files
Files changed (26) hide show
  1. model.safetensors +1 -1
  2. run-0/checkpoint-1069/config.json +25 -0
  3. run-0/checkpoint-1069/model.safetensors +3 -0
  4. run-0/checkpoint-1069/optimizer.pt +3 -0
  5. run-0/checkpoint-1069/rng_state.pth +3 -0
  6. run-0/checkpoint-1069/scheduler.pt +3 -0
  7. run-0/checkpoint-1069/special_tokens_map.json +7 -0
  8. run-0/checkpoint-1069/tokenizer.json +0 -0
  9. run-0/checkpoint-1069/tokenizer_config.json +55 -0
  10. run-0/checkpoint-1069/trainer_state.json +61 -0
  11. run-0/checkpoint-1069/training_args.bin +3 -0
  12. run-0/checkpoint-1069/vocab.txt +0 -0
  13. run-1/checkpoint-1069/config.json +25 -0
  14. run-1/checkpoint-1069/model.safetensors +3 -0
  15. run-1/checkpoint-1069/optimizer.pt +3 -0
  16. run-1/checkpoint-1069/rng_state.pth +3 -0
  17. run-1/checkpoint-1069/scheduler.pt +3 -0
  18. run-1/checkpoint-1069/special_tokens_map.json +7 -0
  19. run-1/checkpoint-1069/tokenizer.json +0 -0
  20. run-1/checkpoint-1069/tokenizer_config.json +55 -0
  21. run-1/checkpoint-1069/trainer_state.json +61 -0
  22. run-1/checkpoint-1069/training_args.bin +3 -0
  23. run-1/checkpoint-1069/vocab.txt +0 -0
  24. runs/Oct02_05-18-55_0fd1839bafe2/events.out.tfevents.1727846786.0fd1839bafe2.228.2 +3 -0
  25. runs/Oct02_05-18-55_0fd1839bafe2/events.out.tfevents.1727846874.0fd1839bafe2.228.3 +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:a1ace352e76ab6986ebe0dd8bce093a4625a156a977749bd38effc7d8dbd55ce
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37b4ebc6ca65f593e216669994f47a9363ce75bc9f71073bffb3783be94bb86c
3
  size 267832560
run-0/checkpoint-1069/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": "4.45.1",
24
+ "vocab_size": 30522
25
+ }
run-0/checkpoint-1069/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ec63bd3d0586873264c0699ee0abad1e554aa1708c36061a5de7b8826dd4b13
3
+ size 267832560
run-0/checkpoint-1069/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f93d0432cdad5416d55ccf6706c8591a97699305828909ef9c499906967ab1dd
3
+ size 535727290
run-0/checkpoint-1069/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8815fd7206bd76dc7aaaaa114fd28195948fa456ac671967a05e7fbddc0ec5d0
3
+ size 14308
run-0/checkpoint-1069/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59e9385eed2a90642560c65e7defc79c34d4b2abc1829598b0731c2a9d14b95b
3
+ size 1064
run-0/checkpoint-1069/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-0/checkpoint-1069/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-1069/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": false,
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-0/checkpoint-1069/trainer_state.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.3463041583465305,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-1069",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1069,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.4677268475210477,
13
+ "grad_norm": 4.9206624031066895,
14
+ "learning_rate": 2.5717418719148958e-06,
15
+ "loss": 0.5872,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.9354536950420954,
20
+ "grad_norm": 20.741090774536133,
21
+ "learning_rate": 3.1186324984556734e-07,
22
+ "loss": 0.5331,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 1.0,
27
+ "eval_loss": 0.5321354269981384,
28
+ "eval_matthews_correlation": 0.3463041583465305,
29
+ "eval_runtime": 0.8606,
30
+ "eval_samples_per_second": 1212.006,
31
+ "eval_steps_per_second": 76.695,
32
+ "step": 1069
33
+ }
34
+ ],
35
+ "logging_steps": 500,
36
+ "max_steps": 1069,
37
+ "num_input_tokens_seen": 0,
38
+ "num_train_epochs": 1,
39
+ "save_steps": 500,
40
+ "stateful_callbacks": {
41
+ "TrainerControl": {
42
+ "args": {
43
+ "should_epoch_stop": false,
44
+ "should_evaluate": false,
45
+ "should_log": false,
46
+ "should_save": true,
47
+ "should_training_stop": true
48
+ },
49
+ "attributes": {}
50
+ }
51
+ },
52
+ "total_flos": 37546228306560.0,
53
+ "train_batch_size": 8,
54
+ "trial_name": null,
55
+ "trial_params": {
56
+ "learning_rate": 4.8316204939842245e-06,
57
+ "num_train_epochs": 1,
58
+ "per_device_train_batch_size": 8,
59
+ "seed": 21
60
+ }
61
+ }
run-0/checkpoint-1069/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:978671faec00be23d01743f76ad88a471c29c2169b1f6af6ab3a2307f7cc2675
3
+ size 5304
run-0/checkpoint-1069/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-1069/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": "4.45.1",
24
+ "vocab_size": 30522
25
+ }
run-1/checkpoint-1069/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37b4ebc6ca65f593e216669994f47a9363ce75bc9f71073bffb3783be94bb86c
3
+ size 267832560
run-1/checkpoint-1069/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5006590409afb8ff13c955f6d3a46022c4cbae62014b1934c4c44a23208fa59
3
+ size 535727290
run-1/checkpoint-1069/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4055081704241a52eeaa39f32906ab4f80eb373224bfeec1f71fb9f80ad04217
3
+ size 14244
run-1/checkpoint-1069/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:333d7710a36f6b41ebf304884cf5ba6b1ce8a6ad6f5df052e64e2ebf425e6989
3
+ size 1064
run-1/checkpoint-1069/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-1069/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-1069/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": false,
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-1069/trainer_state.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.45788183343120153,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-1069",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1069,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.4677268475210477,
13
+ "grad_norm": 4.76369571685791,
14
+ "learning_rate": 2.2292054345772622e-05,
15
+ "loss": 0.5655,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.9354536950420954,
20
+ "grad_norm": 15.750553131103516,
21
+ "learning_rate": 1.93402463021057e-05,
22
+ "loss": 0.4835,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 1.0,
27
+ "eval_loss": 0.468739777803421,
28
+ "eval_matthews_correlation": 0.45788183343120153,
29
+ "eval_runtime": 0.7397,
30
+ "eval_samples_per_second": 1409.989,
31
+ "eval_steps_per_second": 89.223,
32
+ "step": 1069
33
+ }
34
+ ],
35
+ "logging_steps": 500,
36
+ "max_steps": 4276,
37
+ "num_input_tokens_seen": 0,
38
+ "num_train_epochs": 4,
39
+ "save_steps": 500,
40
+ "stateful_callbacks": {
41
+ "TrainerControl": {
42
+ "args": {
43
+ "should_epoch_stop": false,
44
+ "should_evaluate": false,
45
+ "should_log": false,
46
+ "should_save": true,
47
+ "should_training_stop": false
48
+ },
49
+ "attributes": {}
50
+ }
51
+ },
52
+ "total_flos": 37771836844896.0,
53
+ "train_batch_size": 8,
54
+ "trial_name": null,
55
+ "trial_params": {
56
+ "learning_rate": 2.524386238943955e-05,
57
+ "num_train_epochs": 4,
58
+ "per_device_train_batch_size": 8,
59
+ "seed": 11
60
+ }
61
+ }
run-1/checkpoint-1069/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3becf80cdc9221d5701481d18740c6b71586a42ea3a6944468cdacaf47dd2b83
3
+ size 5304
run-1/checkpoint-1069/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Oct02_05-18-55_0fd1839bafe2/events.out.tfevents.1727846786.0fd1839bafe2.228.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d00113673300131b7dcd4e0ec205fd6758decb3e0c676a5949331f9bdbf733a
3
+ size 6037
runs/Oct02_05-18-55_0fd1839bafe2/events.out.tfevents.1727846874.0fd1839bafe2.228.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7db834c2879f998d54c7ecc71d29682d433152add5d874e5ce3cb4a60c037f1a
3
+ size 5682
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25224953445e2462dc47684f3d4d5464caf4cd3a4f86811768e5e651c683afd5
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3becf80cdc9221d5701481d18740c6b71586a42ea3a6944468cdacaf47dd2b83
3
  size 5304