Hugging Face's logo

sibstrider
/
rubert-tiny2-finetuned-classification

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
sibstrider commited on
Commit
0e5cc57
•
1 Parent(s): fd3032d

Training in progress, epoch 1

Browse files
Files changed (40) hide show
  1. model.safetensors +1 -1
  2. run-27/checkpoint-1100/config.json +54 -0
  3. run-27/checkpoint-1100/model.safetensors +3 -0
  4. run-27/checkpoint-1100/optimizer.pt +3 -0
  5. run-27/checkpoint-1100/rng_state.pth +3 -0
  6. run-27/checkpoint-1100/scheduler.pt +3 -0
  7. run-27/checkpoint-1100/special_tokens_map.json +37 -0
  8. run-27/checkpoint-1100/tokenizer.json +0 -0
  9. run-27/checkpoint-1100/tokenizer_config.json +64 -0
  10. run-27/checkpoint-1100/trainer_state.json +56 -0
  11. run-27/checkpoint-1100/training_args.bin +3 -0
  12. run-27/checkpoint-1100/vocab.txt +0 -0
  13. run-27/checkpoint-550/config.json +54 -0
  14. run-27/checkpoint-550/model.safetensors +3 -0
  15. run-27/checkpoint-550/optimizer.pt +3 -0
  16. run-27/checkpoint-550/rng_state.pth +3 -0
  17. run-27/checkpoint-550/scheduler.pt +3 -0
  18. run-27/checkpoint-550/special_tokens_map.json +37 -0
  19. run-27/checkpoint-550/tokenizer.json +0 -0
  20. run-27/checkpoint-550/tokenizer_config.json +64 -0
  21. run-27/checkpoint-550/trainer_state.json +41 -0
  22. run-27/checkpoint-550/training_args.bin +3 -0
  23. run-27/checkpoint-550/vocab.txt +0 -0
  24. run-30/checkpoint-69/config.json +54 -0
  25. run-30/checkpoint-69/model.safetensors +3 -0
  26. run-30/checkpoint-69/optimizer.pt +3 -0
  27. run-30/checkpoint-69/rng_state.pth +3 -0
  28. run-30/checkpoint-69/scheduler.pt +3 -0
  29. run-30/checkpoint-69/special_tokens_map.json +37 -0
  30. run-30/checkpoint-69/tokenizer.json +0 -0
  31. run-30/checkpoint-69/tokenizer_config.json +64 -0
  32. run-30/checkpoint-69/trainer_state.json +35 -0
  33. run-30/checkpoint-69/training_args.bin +3 -0
  34. run-30/checkpoint-69/vocab.txt +0 -0
  35. runs/Jan15_00-51-52_DESKTOP-RFEED41/events.out.tfevents.1705280932.DESKTOP-RFEED41.20976.42 +3 -0
  36. runs/Jan15_00-51-52_DESKTOP-RFEED41/events.out.tfevents.1705281163.DESKTOP-RFEED41.20976.43 +3 -0
  37. runs/Jan15_00-51-52_DESKTOP-RFEED41/events.out.tfevents.1705281972.DESKTOP-RFEED41.20976.44 +3 -0
  38. runs/Jan15_00-51-52_DESKTOP-RFEED41/events.out.tfevents.1705282250.DESKTOP-RFEED41.20976.45 +3 -0
  39. runs/Jan15_00-51-52_DESKTOP-RFEED41/events.out.tfevents.1705282478.DESKTOP-RFEED41.20976.46 +3 -0
  40. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:180238f559019a543c247d905ccde86c7ea3b29a2747be282f1d9630d1faa285
3
  size 116795404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f3667e63f13459175b5f80563540a7e5545632d01e0d01bece91c452b223103
3
  size 116795404
run-27/checkpoint-1100/config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cointegrated/rubert-tiny2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "emb_size": 312,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 312,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5",
20
+ "6": "LABEL_6",
21
+ "7": "LABEL_7",
22
+ "8": "LABEL_8",
23
+ "9": "LABEL_9",
24
+ "10": "LABEL_10"
25
+ },
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 600,
28
+ "label2id": {
29
+ "LABEL_0": 0,
30
+ "LABEL_1": 1,
31
+ "LABEL_10": 10,
32
+ "LABEL_2": 2,
33
+ "LABEL_3": 3,
34
+ "LABEL_4": 4,
35
+ "LABEL_5": 5,
36
+ "LABEL_6": 6,
37
+ "LABEL_7": 7,
38
+ "LABEL_8": 8,
39
+ "LABEL_9": 9
40
+ },
41
+ "layer_norm_eps": 1e-12,
42
+ "max_position_embeddings": 2048,
43
+ "model_type": "bert",
44
+ "num_attention_heads": 12,
45
+ "num_hidden_layers": 3,
46
+ "pad_token_id": 0,
47
+ "position_embedding_type": "absolute",
48
+ "problem_type": "single_label_classification",
49
+ "torch_dtype": "float32",
50
+ "transformers_version": "4.36.2",
51
+ "type_vocab_size": 2,
52
+ "use_cache": true,
53
+ "vocab_size": 83828
54
+ }
run-27/checkpoint-1100/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cbfec0a6f2b0c45ef85f1335f8326f5fc7f80728308fe16f52793e41de90a0c
3
+ size 116795404
run-27/checkpoint-1100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27f707ca796e43cd3ef971c9c778013f32d530d2e20991dad08d0512a46a11a6
3
+ size 233621882
run-27/checkpoint-1100/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f483e0d33721c10e791fae5ea70aed55b5f9b4a22e71c4cbad97487e88ada917
3
+ size 14054
run-27/checkpoint-1100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:304449acad3f3c0c9502b21abebacd3a0a92cd463f7a91e25035eef0ef93dd7a
3
+ size 1064
run-27/checkpoint-1100/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
run-27/checkpoint-1100/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-27/checkpoint-1100/tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
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_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "mask_token": "[MASK]",
49
+ "max_length": 512,
50
+ "model_max_length": 2048,
51
+ "never_split": null,
52
+ "pad_to_multiple_of": null,
53
+ "pad_token": "[PAD]",
54
+ "pad_token_type_id": 0,
55
+ "padding_side": "right",
56
+ "sep_token": "[SEP]",
57
+ "stride": 0,
58
+ "strip_accents": null,
59
+ "tokenize_chinese_chars": true,
60
+ "tokenizer_class": "BertTokenizer",
61
+ "truncation_side": "right",
62
+ "truncation_strategy": "longest_first",
63
+ "unk_token": "[UNK]"
64
+ }
run-27/checkpoint-1100/trainer_state.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9020408163265307,
3
+ "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-27\\checkpoint-1100",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1100,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.91,
13
+ "learning_rate": 4.106777464711046e-05,
14
+ "loss": 1.2397,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8775510204081632,
20
+ "eval_loss": 0.5188024640083313,
21
+ "eval_runtime": 1.334,
22
+ "eval_samples_per_second": 183.658,
23
+ "eval_steps_per_second": 11.994,
24
+ "step": 550
25
+ },
26
+ {
27
+ "epoch": 1.82,
28
+ "learning_rate": 2.3212220452714603e-05,
29
+ "loss": 0.4622,
30
+ "step": 1000
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.9020408163265307,
35
+ "eval_loss": 0.38360315561294556,
36
+ "eval_runtime": 1.182,
37
+ "eval_samples_per_second": 207.276,
38
+ "eval_steps_per_second": 13.536,
39
+ "step": 1100
40
+ }
41
+ ],
42
+ "logging_steps": 500,
43
+ "max_steps": 1650,
44
+ "num_input_tokens_seen": 0,
45
+ "num_train_epochs": 3,
46
+ "save_steps": 500,
47
+ "total_flos": 2022384751800.0,
48
+ "train_batch_size": 4,
49
+ "trial_name": null,
50
+ "trial_params": {
51
+ "learning_rate": 5.89233288415063e-05,
52
+ "num_train_epochs": 3,
53
+ "per_device_train_batch_size": 4,
54
+ "seed": 32
55
+ }
56
+ }
run-27/checkpoint-1100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe086e5650cf9f8ed8a0cae6b3ee8d7c4e343fbfb527b6c35595233ca06377b3
3
+ size 4728
run-27/checkpoint-1100/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-27/checkpoint-550/config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cointegrated/rubert-tiny2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "emb_size": 312,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 312,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5",
20
+ "6": "LABEL_6",
21
+ "7": "LABEL_7",
22
+ "8": "LABEL_8",
23
+ "9": "LABEL_9",
24
+ "10": "LABEL_10"
25
+ },
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 600,
28
+ "label2id": {
29
+ "LABEL_0": 0,
30
+ "LABEL_1": 1,
31
+ "LABEL_10": 10,
32
+ "LABEL_2": 2,
33
+ "LABEL_3": 3,
34
+ "LABEL_4": 4,
35
+ "LABEL_5": 5,
36
+ "LABEL_6": 6,
37
+ "LABEL_7": 7,
38
+ "LABEL_8": 8,
39
+ "LABEL_9": 9
40
+ },
41
+ "layer_norm_eps": 1e-12,
42
+ "max_position_embeddings": 2048,
43
+ "model_type": "bert",
44
+ "num_attention_heads": 12,
45
+ "num_hidden_layers": 3,
46
+ "pad_token_id": 0,
47
+ "position_embedding_type": "absolute",
48
+ "problem_type": "single_label_classification",
49
+ "torch_dtype": "float32",
50
+ "transformers_version": "4.36.2",
51
+ "type_vocab_size": 2,
52
+ "use_cache": true,
53
+ "vocab_size": 83828
54
+ }
run-27/checkpoint-550/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2fbd1900582aae329c543a7161b561a98bfe7dc5450366d94061193cc2453d4
3
+ size 116795404
run-27/checkpoint-550/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c792f864b30643c58b3410c498dff3151da4f15ba085feb7300fc0200e8ab410
3
+ size 233621882
run-27/checkpoint-550/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32470f0a7dc646d99f088f1edacdd634dcffb4afc30fa756b32159680c849395
3
+ size 14054
run-27/checkpoint-550/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:024f894abab9bd52cbd76130f4b0ecbd20e2058d1011346c91157b3cdfe46f75
3
+ size 1064
run-27/checkpoint-550/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
run-27/checkpoint-550/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-27/checkpoint-550/tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
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_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "mask_token": "[MASK]",
49
+ "max_length": 512,
50
+ "model_max_length": 2048,
51
+ "never_split": null,
52
+ "pad_to_multiple_of": null,
53
+ "pad_token": "[PAD]",
54
+ "pad_token_type_id": 0,
55
+ "padding_side": "right",
56
+ "sep_token": "[SEP]",
57
+ "stride": 0,
58
+ "strip_accents": null,
59
+ "tokenize_chinese_chars": true,
60
+ "tokenizer_class": "BertTokenizer",
61
+ "truncation_side": "right",
62
+ "truncation_strategy": "longest_first",
63
+ "unk_token": "[UNK]"
64
+ }
run-27/checkpoint-550/trainer_state.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8775510204081632,
3
+ "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-27\\checkpoint-550",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 550,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.91,
13
+ "learning_rate": 4.106777464711046e-05,
14
+ "loss": 1.2397,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8775510204081632,
20
+ "eval_loss": 0.5188024640083313,
21
+ "eval_runtime": 1.334,
22
+ "eval_samples_per_second": 183.658,
23
+ "eval_steps_per_second": 11.994,
24
+ "step": 550
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 1650,
29
+ "num_input_tokens_seen": 0,
30
+ "num_train_epochs": 3,
31
+ "save_steps": 500,
32
+ "total_flos": 1067284814400.0,
33
+ "train_batch_size": 4,
34
+ "trial_name": null,
35
+ "trial_params": {
36
+ "learning_rate": 5.89233288415063e-05,
37
+ "num_train_epochs": 3,
38
+ "per_device_train_batch_size": 4,
39
+ "seed": 32
40
+ }
41
+ }
run-27/checkpoint-550/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe086e5650cf9f8ed8a0cae6b3ee8d7c4e343fbfb527b6c35595233ca06377b3
3
+ size 4728
run-27/checkpoint-550/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-30/checkpoint-69/config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cointegrated/rubert-tiny2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "emb_size": 312,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 312,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5",
20
+ "6": "LABEL_6",
21
+ "7": "LABEL_7",
22
+ "8": "LABEL_8",
23
+ "9": "LABEL_9",
24
+ "10": "LABEL_10"
25
+ },
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 600,
28
+ "label2id": {
29
+ "LABEL_0": 0,
30
+ "LABEL_1": 1,
31
+ "LABEL_10": 10,
32
+ "LABEL_2": 2,
33
+ "LABEL_3": 3,
34
+ "LABEL_4": 4,
35
+ "LABEL_5": 5,
36
+ "LABEL_6": 6,
37
+ "LABEL_7": 7,
38
+ "LABEL_8": 8,
39
+ "LABEL_9": 9
40
+ },
41
+ "layer_norm_eps": 1e-12,
42
+ "max_position_embeddings": 2048,
43
+ "model_type": "bert",
44
+ "num_attention_heads": 12,
45
+ "num_hidden_layers": 3,
46
+ "pad_token_id": 0,
47
+ "position_embedding_type": "absolute",
48
+ "problem_type": "single_label_classification",
49
+ "torch_dtype": "float32",
50
+ "transformers_version": "4.36.2",
51
+ "type_vocab_size": 2,
52
+ "use_cache": true,
53
+ "vocab_size": 83828
54
+ }
run-30/checkpoint-69/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f3667e63f13459175b5f80563540a7e5545632d01e0d01bece91c452b223103
3
+ size 116795404
run-30/checkpoint-69/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5408a29eec86e969e63dbc664b30316d5c959bd1cb9779f8519c9972fb88c79e
3
+ size 233621882
run-30/checkpoint-69/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a27c4510b2c6afc325669ed9ab5d4bf84096fc171a981763e1e185e30efb6573
3
+ size 14054
run-30/checkpoint-69/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc350a5bedabf24ff4b7842ea8bc21d73823bba19501519f418d4fe998f155c9
3
+ size 1064
run-30/checkpoint-69/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
run-30/checkpoint-69/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-30/checkpoint-69/tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
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_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "mask_token": "[MASK]",
49
+ "max_length": 512,
50
+ "model_max_length": 2048,
51
+ "never_split": null,
52
+ "pad_to_multiple_of": null,
53
+ "pad_token": "[PAD]",
54
+ "pad_token_type_id": 0,
55
+ "padding_side": "right",
56
+ "sep_token": "[SEP]",
57
+ "stride": 0,
58
+ "strip_accents": null,
59
+ "tokenize_chinese_chars": true,
60
+ "tokenizer_class": "BertTokenizer",
61
+ "truncation_side": "right",
62
+ "truncation_strategy": "longest_first",
63
+ "unk_token": "[UNK]"
64
+ }
run-30/checkpoint-69/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4897959183673469,
3
+ "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-30\\checkpoint-69",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 69,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.4897959183673469,
14
+ "eval_loss": 1.9634840488433838,
15
+ "eval_runtime": 1.387,
16
+ "eval_samples_per_second": 176.64,
17
+ "eval_steps_per_second": 11.536,
18
+ "step": 69
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 276,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 4,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 32,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 2.6594289569983575e-05,
31
+ "num_train_epochs": 4,
32
+ "per_device_train_batch_size": 32,
33
+ "seed": 30
34
+ }
35
+ }
run-30/checkpoint-69/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a54c3b65d26d0880f9603fe211c94c712c5a8c458ba1c9e03c8c8a0c04ede908
3
+ size 4728
run-30/checkpoint-69/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Jan15_00-51-52_DESKTOP-RFEED41/events.out.tfevents.1705280932.DESKTOP-RFEED41.20976.42 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0609a9968d12be987e626b81721132b4dfc189ca04e8c36dd946f4e26c260b5
3
+ size 5432
runs/Jan15_00-51-52_DESKTOP-RFEED41/events.out.tfevents.1705281163.DESKTOP-RFEED41.20976.43 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a0fcc8947cd61910fccd8653cdb86569ba217108c726ca8ca3b28be497bfda8
3
+ size 6390
runs/Jan15_00-51-52_DESKTOP-RFEED41/events.out.tfevents.1705281972.DESKTOP-RFEED41.20976.44 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75917388d39ba82bfd2fbc36ae1b4ae48511506b2d49b885b88828cef8d8f830
3
+ size 5432
runs/Jan15_00-51-52_DESKTOP-RFEED41/events.out.tfevents.1705282250.DESKTOP-RFEED41.20976.45 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed3eefe87a7e25925c85174e7d3464b6a78a2da69fb2fc6345bd54384943b997
3
+ size 5431
runs/Jan15_00-51-52_DESKTOP-RFEED41/events.out.tfevents.1705282478.DESKTOP-RFEED41.20976.46 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c1c008a470697bc86cf1e148769d8d3717bbc60799e3d6c54f5a4329d33a217
3
+ size 5593
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:047778ac627b15d9b405de94bbab5725f4b13e83e164b739c496e3256beed71b
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a54c3b65d26d0880f9603fe211c94c712c5a8c458ba1c9e03c8c8a0c04ede908
3
  size 4728