Hugging Face's logo

Duocas
/
CHT_LLM_Lesson

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Model card Files
xet
Metrics Community
Duocas commited on
Commit
cc4661a
·
verified ·
1 Parent(s): 695208a

Training in progress, epoch 3

Browse files
Files changed (24) hide show
  1. model.safetensors +1 -1
  2. run-2/checkpoint-1070/config.json +25 -0
  3. run-2/checkpoint-1070/model.safetensors +3 -0
  4. run-2/checkpoint-1070/optimizer.pt +3 -0
  5. run-2/checkpoint-1070/rng_state.pth +3 -0
  6. run-2/checkpoint-1070/scheduler.pt +3 -0
  7. run-2/checkpoint-1070/special_tokens_map.json +7 -0
  8. run-2/checkpoint-1070/tokenizer.json +0 -0
  9. run-2/checkpoint-1070/tokenizer_config.json +55 -0
  10. run-2/checkpoint-1070/trainer_state.json +58 -0
  11. run-2/checkpoint-1070/training_args.bin +3 -0
  12. run-2/checkpoint-1070/vocab.txt +0 -0
  13. run-2/checkpoint-1605/config.json +25 -0
  14. run-2/checkpoint-1605/model.safetensors +3 -0
  15. run-2/checkpoint-1605/optimizer.pt +3 -0
  16. run-2/checkpoint-1605/rng_state.pth +3 -0
  17. run-2/checkpoint-1605/scheduler.pt +3 -0
  18. run-2/checkpoint-1605/special_tokens_map.json +7 -0
  19. run-2/checkpoint-1605/tokenizer.json +0 -0
  20. run-2/checkpoint-1605/tokenizer_config.json +55 -0
  21. run-2/checkpoint-1605/trainer_state.json +74 -0
  22. run-2/checkpoint-1605/training_args.bin +3 -0
  23. run-2/checkpoint-1605/vocab.txt +0 -0
  24. runs/Mar04_02-28-38_78dd22f13cdf/events.out.tfevents.1709520379.78dd22f13cdf.294.4 +2 -2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:931b2d7dadb3810530014a96f322a40b6a1fb3810a1943185850eb38e65245c5
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6eac6dca7047026cafd222333a0d25c97922abd1b519ac6d7e827c310fa1999a
3
  size 267832560
run-2/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": "4.38.2",
24
+ "vocab_size": 30522
25
+ }
run-2/checkpoint-1070/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9d4f15ebd1bd6e5624e51ca18df52d4518814a36a87027eeef7d5069b397eb0
3
+ size 267832560
run-2/checkpoint-1070/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:713dff70545eae513f340c2886cd5c528cc14852e19cf7f78b8aafa17c44f434
3
+ size 535727290
run-2/checkpoint-1070/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:674cf0c9cac7fb317826de69a952a348ab3d28a80280f7bbb3c5d81d42334218
3
+ size 14244
run-2/checkpoint-1070/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddc4f1dd8c8356a66470fb72f1c565f64a1c80513d2f896cc8edc81abc1c8e4e
3
+ size 1064
run-2/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-2/checkpoint-1070/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/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-2/checkpoint-1070/trainer_state.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.49867676415016876,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/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": 4.918482780456543,
14
+ "learning_rate": 5.0273219162249924e-05,
15
+ "loss": 0.5455,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_loss": 0.4970824718475342,
21
+ "eval_matthews_correlation": 0.3827318387959091,
22
+ "eval_runtime": 0.7956,
23
+ "eval_samples_per_second": 1310.993,
24
+ "eval_steps_per_second": 82.958,
25
+ "step": 535
26
+ },
27
+ {
28
+ "epoch": 1.87,
29
+ "grad_norm": 8.05403995513916,
30
+ "learning_rate": 2.7525156192906067e-05,
31
+ "loss": 0.3233,
32
+ "step": 1000
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_loss": 0.5374172329902649,
37
+ "eval_matthews_correlation": 0.49867676415016876,
38
+ "eval_runtime": 1.1803,
39
+ "eval_samples_per_second": 883.698,
40
+ "eval_steps_per_second": 55.92,
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": 85557898557720.0,
50
+ "train_batch_size": 16,
51
+ "trial_name": null,
52
+ "trial_params": {
53
+ "learning_rate": 7.302128213159378e-05,
54
+ "num_train_epochs": 3,
55
+ "per_device_train_batch_size": 16,
56
+ "seed": 39
57
+ }
58
+ }
run-2/checkpoint-1070/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33497bd59a9f6c8b2867c40da019c6ac32b06651eec90e317b27724a29d30e7a
3
+ size 4984
run-2/checkpoint-1070/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/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": "4.38.2",
24
+ "vocab_size": 30522
25
+ }
run-2/checkpoint-1605/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6eac6dca7047026cafd222333a0d25c97922abd1b519ac6d7e827c310fa1999a
3
+ size 267832560
run-2/checkpoint-1605/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4890e1680ddaed7d5e5f8e466ebb119b97a1885d59fa466c71dc1ccb432b0df4
3
+ size 535727290
run-2/checkpoint-1605/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc1d38134f31fc4803e66d10c8f87990eb1447ac1c58ed3b816962ae4e145878
3
+ size 14244
run-2/checkpoint-1605/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:488d30d141b3ff7f2b96c6fbcec0ea9315aec37816e86dfddc6140d939380012
3
+ size 1064
run-2/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-2/checkpoint-1605/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/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-2/checkpoint-1605/trainer_state.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.49867676415016876,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/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": 4.918482780456543,
14
+ "learning_rate": 5.0273219162249924e-05,
15
+ "loss": 0.5455,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_loss": 0.4970824718475342,
21
+ "eval_matthews_correlation": 0.3827318387959091,
22
+ "eval_runtime": 0.7956,
23
+ "eval_samples_per_second": 1310.993,
24
+ "eval_steps_per_second": 82.958,
25
+ "step": 535
26
+ },
27
+ {
28
+ "epoch": 1.87,
29
+ "grad_norm": 8.05403995513916,
30
+ "learning_rate": 2.7525156192906067e-05,
31
+ "loss": 0.3233,
32
+ "step": 1000
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_loss": 0.5374172329902649,
37
+ "eval_matthews_correlation": 0.49867676415016876,
38
+ "eval_runtime": 1.1803,
39
+ "eval_samples_per_second": 883.698,
40
+ "eval_steps_per_second": 55.92,
41
+ "step": 1070
42
+ },
43
+ {
44
+ "epoch": 2.8,
45
+ "grad_norm": 12.47011947631836,
46
+ "learning_rate": 4.77709322356221e-06,
47
+ "loss": 0.1756,
48
+ "step": 1500
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_loss": 0.8386874794960022,
53
+ "eval_matthews_correlation": 0.46417453765870365,
54
+ "eval_runtime": 0.8078,
55
+ "eval_samples_per_second": 1291.106,
56
+ "eval_steps_per_second": 81.7,
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": 128518731784344.0,
66
+ "train_batch_size": 16,
67
+ "trial_name": null,
68
+ "trial_params": {
69
+ "learning_rate": 7.302128213159378e-05,
70
+ "num_train_epochs": 3,
71
+ "per_device_train_batch_size": 16,
72
+ "seed": 39
73
+ }
74
+ }
run-2/checkpoint-1605/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33497bd59a9f6c8b2867c40da019c6ac32b06651eec90e317b27724a29d30e7a
3
+ size 4984
run-2/checkpoint-1605/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Mar04_02-28-38_78dd22f13cdf/events.out.tfevents.1709520379.78dd22f13cdf.294.4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5efcd481c6a3510fe92d6ff1edf3468fdce7b31aeb8a157ce27b1f5ac9309b9e
3
- size 5318
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4134756656e4290ecfeefb6644377d9a09dbb80d74a486b39cca4fe32b7a9ef
3
+ size 6553