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
85c274c
•
1 Parent(s): b36ff2c

Training in progress, epoch 4

Browse files
Files changed (47) hide show
  1. model.safetensors +1 -1
  2. run-39/checkpoint-1100/config.json +54 -0
  3. run-39/checkpoint-1100/model.safetensors +3 -0
  4. run-39/checkpoint-1100/optimizer.pt +3 -0
  5. run-39/checkpoint-1100/rng_state.pth +3 -0
  6. run-39/checkpoint-1100/scheduler.pt +3 -0
  7. run-39/checkpoint-1100/special_tokens_map.json +37 -0
  8. run-39/checkpoint-1100/tokenizer.json +0 -0
  9. run-39/checkpoint-1100/tokenizer_config.json +64 -0
  10. run-39/checkpoint-1100/trainer_state.json +74 -0
  11. run-39/checkpoint-1100/training_args.bin +3 -0
  12. run-39/checkpoint-1100/vocab.txt +0 -0
  13. run-39/checkpoint-275/config.json +54 -0
  14. run-39/checkpoint-275/model.safetensors +3 -0
  15. run-39/checkpoint-275/optimizer.pt +3 -0
  16. run-39/checkpoint-275/rng_state.pth +3 -0
  17. run-39/checkpoint-275/scheduler.pt +3 -0
  18. run-39/checkpoint-275/special_tokens_map.json +37 -0
  19. run-39/checkpoint-275/tokenizer.json +0 -0
  20. run-39/checkpoint-275/tokenizer_config.json +64 -0
  21. run-39/checkpoint-275/trainer_state.json +35 -0
  22. run-39/checkpoint-275/training_args.bin +3 -0
  23. run-39/checkpoint-275/vocab.txt +0 -0
  24. run-39/checkpoint-550/config.json +54 -0
  25. run-39/checkpoint-550/model.safetensors +3 -0
  26. run-39/checkpoint-550/optimizer.pt +3 -0
  27. run-39/checkpoint-550/rng_state.pth +3 -0
  28. run-39/checkpoint-550/scheduler.pt +3 -0
  29. run-39/checkpoint-550/special_tokens_map.json +37 -0
  30. run-39/checkpoint-550/tokenizer.json +0 -0
  31. run-39/checkpoint-550/tokenizer_config.json +64 -0
  32. run-39/checkpoint-550/trainer_state.json +50 -0
  33. run-39/checkpoint-550/training_args.bin +3 -0
  34. run-39/checkpoint-550/vocab.txt +0 -0
  35. run-39/checkpoint-825/config.json +54 -0
  36. run-39/checkpoint-825/model.safetensors +3 -0
  37. run-39/checkpoint-825/optimizer.pt +3 -0
  38. run-39/checkpoint-825/rng_state.pth +3 -0
  39. run-39/checkpoint-825/scheduler.pt +3 -0
  40. run-39/checkpoint-825/special_tokens_map.json +37 -0
  41. run-39/checkpoint-825/tokenizer.json +0 -0
  42. run-39/checkpoint-825/tokenizer_config.json +64 -0
  43. run-39/checkpoint-825/trainer_state.json +59 -0
  44. run-39/checkpoint-825/training_args.bin +3 -0
  45. run-39/checkpoint-825/vocab.txt +0 -0
  46. runs/Jan15_00-51-52_DESKTOP-RFEED41/events.out.tfevents.1705288129.DESKTOP-RFEED41.20976.55 +3 -0
  47. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:badb624e726471b2a3449cf7a3a6a3268e2d9a8a5832c2dcf3ed83aeb7a8130a
3
  size 116795404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24f6c1119856169bf10fcd494d84fdfb680ee364e87c03434486731c77e23977
3
  size 116795404
run-39/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-39/checkpoint-1100/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24f6c1119856169bf10fcd494d84fdfb680ee364e87c03434486731c77e23977
3
+ size 116795404
run-39/checkpoint-1100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a1a433a7c63287183883a90395ff9d2ce8e6d488d2134710469ae8415527c04
3
+ size 233621882
run-39/checkpoint-1100/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f731a2bd77c618ca5cb2a4de8dd894db54bf55e9876d18fbd56e62b34ce4517
3
+ size 14054
run-39/checkpoint-1100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1852f7f454d35b8534a057c3956ec25f0c897fcff83bd78c5eaf812f9c802536
3
+ size 1064
run-39/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-39/checkpoint-1100/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-39/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-39/checkpoint-1100/trainer_state.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9306122448979591,
3
+ "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-39\\checkpoint-1100",
4
+ "epoch": 4.0,
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": 1.0,
13
+ "eval_accuracy": 0.8653061224489796,
14
+ "eval_loss": 0.5870106220245361,
15
+ "eval_runtime": 1.459,
16
+ "eval_samples_per_second": 167.923,
17
+ "eval_steps_per_second": 10.966,
18
+ "step": 275
19
+ },
20
+ {
21
+ "epoch": 1.82,
22
+ "learning_rate": 3.829606216423644e-05,
23
+ "loss": 0.9249,
24
+ "step": 500
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_accuracy": 0.8979591836734694,
29
+ "eval_loss": 0.38964176177978516,
30
+ "eval_runtime": 1.361,
31
+ "eval_samples_per_second": 180.015,
32
+ "eval_steps_per_second": 11.756,
33
+ "step": 550
34
+ },
35
+ {
36
+ "epoch": 3.0,
37
+ "eval_accuracy": 0.9142857142857143,
38
+ "eval_loss": 0.3397238254547119,
39
+ "eval_runtime": 1.452,
40
+ "eval_samples_per_second": 168.733,
41
+ "eval_steps_per_second": 11.019,
42
+ "step": 825
43
+ },
44
+ {
45
+ "epoch": 3.64,
46
+ "learning_rate": 6.382677027372741e-06,
47
+ "loss": 0.2985,
48
+ "step": 1000
49
+ },
50
+ {
51
+ "epoch": 4.0,
52
+ "eval_accuracy": 0.9306122448979591,
53
+ "eval_loss": 0.3207901120185852,
54
+ "eval_runtime": 1.266,
55
+ "eval_samples_per_second": 193.523,
56
+ "eval_steps_per_second": 12.638,
57
+ "step": 1100
58
+ }
59
+ ],
60
+ "logging_steps": 500,
61
+ "max_steps": 1100,
62
+ "num_input_tokens_seen": 0,
63
+ "num_train_epochs": 4,
64
+ "save_steps": 500,
65
+ "total_flos": 5124210082950.0,
66
+ "train_batch_size": 8,
67
+ "trial_name": null,
68
+ "trial_params": {
69
+ "learning_rate": 7.020944730110015e-05,
70
+ "num_train_epochs": 4,
71
+ "per_device_train_batch_size": 8,
72
+ "seed": 33
73
+ }
74
+ }
run-39/checkpoint-1100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f1cfc24eb746a84e5a75175b5bf42ed72b5698f2d259e5f34ce8571e30acc46
3
+ size 4728
run-39/checkpoint-1100/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-39/checkpoint-275/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-39/checkpoint-275/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08454d687648fa30235ec09894ed2599fa49b85f8cba7a0b2479faa6ed2d9a82
3
+ size 116795404
run-39/checkpoint-275/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7da2d0fe31c2eccdc0ca713bc5b0a690a68375666df644180f785eb60fa8c130
3
+ size 233621882
run-39/checkpoint-275/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:527a601a1dcf787d741b4261645d1e9d1bbdab472ef3c2bf7c40d3ce3b71fa33
3
+ size 14054
run-39/checkpoint-275/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94d33a39cb6fbb7dda3fc34340c466f75f52b784f7a2dbcc3573fec2334ab1a7
3
+ size 1064
run-39/checkpoint-275/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-39/checkpoint-275/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-39/checkpoint-275/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-39/checkpoint-275/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8653061224489796,
3
+ "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-39\\checkpoint-275",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 275,
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": 0.8653061224489796,
14
+ "eval_loss": 0.5870106220245361,
15
+ "eval_runtime": 1.459,
16
+ "eval_samples_per_second": 167.923,
17
+ "eval_steps_per_second": 10.966,
18
+ "step": 275
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 1100,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 4,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 8,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 7.020944730110015e-05,
31
+ "num_train_epochs": 4,
32
+ "per_device_train_batch_size": 8,
33
+ "seed": 33
34
+ }
35
+ }
run-39/checkpoint-275/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f1cfc24eb746a84e5a75175b5bf42ed72b5698f2d259e5f34ce8571e30acc46
3
+ size 4728
run-39/checkpoint-275/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-39/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-39/checkpoint-550/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0b484e7dea3016d26a2a8484d07440201c4f0cebe95c0c1a7f98d3be00f4dc9
3
+ size 116795404
run-39/checkpoint-550/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c78d7703bea87277ad840215a52c3a988a708504a16c336cfd0a0fc6a1a79b5
3
+ size 233621882
run-39/checkpoint-550/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95a29839bc6a7ddbc496ef4b9cff4eea0e6c610ca10b2ac708f33edd082c3817
3
+ size 14054
run-39/checkpoint-550/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08fdb3bdce681941d17253e7aa1fe2b9a1dcc97545620c07e89b96e4523d1168
3
+ size 1064
run-39/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-39/checkpoint-550/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-39/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-39/checkpoint-550/trainer_state.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8979591836734694,
3
+ "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-39\\checkpoint-550",
4
+ "epoch": 2.0,
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": 1.0,
13
+ "eval_accuracy": 0.8653061224489796,
14
+ "eval_loss": 0.5870106220245361,
15
+ "eval_runtime": 1.459,
16
+ "eval_samples_per_second": 167.923,
17
+ "eval_steps_per_second": 10.966,
18
+ "step": 275
19
+ },
20
+ {
21
+ "epoch": 1.82,
22
+ "learning_rate": 3.829606216423644e-05,
23
+ "loss": 0.9249,
24
+ "step": 500
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_accuracy": 0.8979591836734694,
29
+ "eval_loss": 0.38964176177978516,
30
+ "eval_runtime": 1.361,
31
+ "eval_samples_per_second": 180.015,
32
+ "eval_steps_per_second": 11.756,
33
+ "step": 550
34
+ }
35
+ ],
36
+ "logging_steps": 500,
37
+ "max_steps": 1100,
38
+ "num_input_tokens_seen": 0,
39
+ "num_train_epochs": 4,
40
+ "save_steps": 500,
41
+ "total_flos": 2664448507350.0,
42
+ "train_batch_size": 8,
43
+ "trial_name": null,
44
+ "trial_params": {
45
+ "learning_rate": 7.020944730110015e-05,
46
+ "num_train_epochs": 4,
47
+ "per_device_train_batch_size": 8,
48
+ "seed": 33
49
+ }
50
+ }
run-39/checkpoint-550/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f1cfc24eb746a84e5a75175b5bf42ed72b5698f2d259e5f34ce8571e30acc46
3
+ size 4728
run-39/checkpoint-550/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-39/checkpoint-825/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-39/checkpoint-825/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9a8dbd3647096ea1d8c99f3f419aa64237bcd1836628ac41484cfeba6c8c2af
3
+ size 116795404
run-39/checkpoint-825/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:484b998274b7dc117c359bd64da02afd645886592cd368e371652a2d0a2038de
3
+ size 233621882
run-39/checkpoint-825/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:053aa4ad3bdb2722caee45efd4be4479a65dae70e4a8b5bb9411c248fa20cf1c
3
+ size 14054
run-39/checkpoint-825/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:765797d77daa58ae71d8c92a8f701cedd3573462b813aad0bf6fe964bdc65eae
3
+ size 1064
run-39/checkpoint-825/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-39/checkpoint-825/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-39/checkpoint-825/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-39/checkpoint-825/trainer_state.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9142857142857143,
3
+ "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-39\\checkpoint-825",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 825,
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": 0.8653061224489796,
14
+ "eval_loss": 0.5870106220245361,
15
+ "eval_runtime": 1.459,
16
+ "eval_samples_per_second": 167.923,
17
+ "eval_steps_per_second": 10.966,
18
+ "step": 275
19
+ },
20
+ {
21
+ "epoch": 1.82,
22
+ "learning_rate": 3.829606216423644e-05,
23
+ "loss": 0.9249,
24
+ "step": 500
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_accuracy": 0.8979591836734694,
29
+ "eval_loss": 0.38964176177978516,
30
+ "eval_runtime": 1.361,
31
+ "eval_samples_per_second": 180.015,
32
+ "eval_steps_per_second": 11.756,
33
+ "step": 550
34
+ },
35
+ {
36
+ "epoch": 3.0,
37
+ "eval_accuracy": 0.9142857142857143,
38
+ "eval_loss": 0.3397238254547119,
39
+ "eval_runtime": 1.452,
40
+ "eval_samples_per_second": 168.733,
41
+ "eval_steps_per_second": 11.019,
42
+ "step": 825
43
+ }
44
+ ],
45
+ "logging_steps": 500,
46
+ "max_steps": 1100,
47
+ "num_input_tokens_seen": 0,
48
+ "num_train_epochs": 4,
49
+ "save_steps": 500,
50
+ "total_flos": 2664448507350.0,
51
+ "train_batch_size": 8,
52
+ "trial_name": null,
53
+ "trial_params": {
54
+ "learning_rate": 7.020944730110015e-05,
55
+ "num_train_epochs": 4,
56
+ "per_device_train_batch_size": 8,
57
+ "seed": 33
58
+ }
59
+ }
run-39/checkpoint-825/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f1cfc24eb746a84e5a75175b5bf42ed72b5698f2d259e5f34ce8571e30acc46
3
+ size 4728
run-39/checkpoint-825/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.1705288129.DESKTOP-RFEED41.20976.55 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56cd31d5100ab07b19d8aed2820a760860b073198c635881d3bade1159e4f441
3
+ size 6911
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9314423a6750fc63ba427ee3bd5ef2153be8f4d51bb47b3fca413dc5f5c9ba6d
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f1cfc24eb746a84e5a75175b5bf42ed72b5698f2d259e5f34ce8571e30acc46
3
  size 4728