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
4891e95
·
verified ·
1 Parent(s): a2c812e

Training in progress, epoch 4

Browse files
Files changed (24) hide show
  1. model.safetensors +1 -1
  2. run-0/checkpoint-105/config.json +54 -0
  3. run-0/checkpoint-105/model.safetensors +3 -0
  4. run-0/checkpoint-105/optimizer.pt +3 -0
  5. run-0/checkpoint-105/rng_state.pth +3 -0
  6. run-0/checkpoint-105/scheduler.pt +3 -0
  7. run-0/checkpoint-105/special_tokens_map.json +37 -0
  8. run-0/checkpoint-105/tokenizer.json +0 -0
  9. run-0/checkpoint-105/tokenizer_config.json +64 -0
  10. run-0/checkpoint-105/trainer_state.json +53 -0
  11. run-0/checkpoint-105/training_args.bin +3 -0
  12. run-0/checkpoint-105/vocab.txt +0 -0
  13. run-0/checkpoint-140/config.json +54 -0
  14. run-0/checkpoint-140/model.safetensors +3 -0
  15. run-0/checkpoint-140/optimizer.pt +3 -0
  16. run-0/checkpoint-140/rng_state.pth +3 -0
  17. run-0/checkpoint-140/scheduler.pt +3 -0
  18. run-0/checkpoint-140/special_tokens_map.json +37 -0
  19. run-0/checkpoint-140/tokenizer.json +0 -0
  20. run-0/checkpoint-140/tokenizer_config.json +64 -0
  21. run-0/checkpoint-140/trainer_state.json +62 -0
  22. run-0/checkpoint-140/training_args.bin +3 -0
  23. run-0/checkpoint-140/vocab.txt +0 -0
  24. runs/Jan15_00-51-52_DESKTOP-RFEED41/events.out.tfevents.1705259198.DESKTOP-RFEED41.20976.6 +2 -2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b76707e678e420dead52178d88d619b95e7e71ee61a1e8b2736ba99496ef6639
3
  size 116795404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bca4f83e77e430177f1bee6ffd9c57ecd2364107a77cc848abe414e2a222457d
3
  size 116795404
run-0/checkpoint-105/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-0/checkpoint-105/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d5590a56fac44516691bbd3b532661218831261f8b95e6b6662d072dab1250e
3
+ size 116795404
run-0/checkpoint-105/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a976ee490c20c9ab5f3dc84fde56323949b533e9fa305096a71923fa93b91b5
3
+ size 233621882
run-0/checkpoint-105/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56bc8314e284e6eb19c4148a570a68baba6798bb6588ab7fd30859669bd32bde
3
+ size 13990
run-0/checkpoint-105/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:410af8c2fd8aef68215bc32244a6d776e14e21169a6660a8cc95491826af8cbc
3
+ size 1064
run-0/checkpoint-105/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-0/checkpoint-105/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-105/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-0/checkpoint-105/trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8204081632653061,
3
+ "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-0\\checkpoint-105",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 105,
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": 0.5142857142857142,
14
+ "eval_loss": 1.8266521692276,
15
+ "eval_runtime": 1.249,
16
+ "eval_samples_per_second": 196.157,
17
+ "eval_steps_per_second": 12.81,
18
+ "step": 35
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.7387755102040816,
23
+ "eval_loss": 1.3899593353271484,
24
+ "eval_runtime": 1.192,
25
+ "eval_samples_per_second": 205.538,
26
+ "eval_steps_per_second": 13.423,
27
+ "step": 70
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_accuracy": 0.8204081632653061,
32
+ "eval_loss": 1.1317118406295776,
33
+ "eval_runtime": 1.127,
34
+ "eval_samples_per_second": 217.391,
35
+ "eval_steps_per_second": 14.197,
36
+ "step": 105
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 175,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 5,
43
+ "save_steps": 500,
44
+ "total_flos": 0,
45
+ "train_batch_size": 64,
46
+ "trial_name": null,
47
+ "trial_params": {
48
+ "learning_rate": 5.723967938193154e-05,
49
+ "num_train_epochs": 5,
50
+ "per_device_train_batch_size": 64,
51
+ "seed": 40
52
+ }
53
+ }
run-0/checkpoint-105/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdf30298e8e2e3d70c6b83e014c63bac7fbca10e5fe524ad7f608198d8195428
3
+ size 4728
run-0/checkpoint-105/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-140/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-0/checkpoint-140/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bca4f83e77e430177f1bee6ffd9c57ecd2364107a77cc848abe414e2a222457d
3
+ size 116795404
run-0/checkpoint-140/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a71e3c02486d9817ecc212148b0bd2e4e79e2138e6743b785df77d2fa9e3fe71
3
+ size 233621882
run-0/checkpoint-140/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23beccfe725296bb15f8825d28ebba19c00e2cc509b17c211bf153c204bb5495
3
+ size 13990
run-0/checkpoint-140/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbee453c4749dc6c3790590531bccb5cb661c104b0a91889a5b9c7ee8810835b
3
+ size 1064
run-0/checkpoint-140/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-0/checkpoint-140/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-140/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-0/checkpoint-140/trainer_state.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8367346938775511,
3
+ "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-0\\checkpoint-140",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 140,
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": 0.5142857142857142,
14
+ "eval_loss": 1.8266521692276,
15
+ "eval_runtime": 1.249,
16
+ "eval_samples_per_second": 196.157,
17
+ "eval_steps_per_second": 12.81,
18
+ "step": 35
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.7387755102040816,
23
+ "eval_loss": 1.3899593353271484,
24
+ "eval_runtime": 1.192,
25
+ "eval_samples_per_second": 205.538,
26
+ "eval_steps_per_second": 13.423,
27
+ "step": 70
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_accuracy": 0.8204081632653061,
32
+ "eval_loss": 1.1317118406295776,
33
+ "eval_runtime": 1.127,
34
+ "eval_samples_per_second": 217.391,
35
+ "eval_steps_per_second": 14.197,
36
+ "step": 105
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_accuracy": 0.8367346938775511,
41
+ "eval_loss": 0.9972113370895386,
42
+ "eval_runtime": 1.106,
43
+ "eval_samples_per_second": 221.52,
44
+ "eval_steps_per_second": 14.467,
45
+ "step": 140
46
+ }
47
+ ],
48
+ "logging_steps": 500,
49
+ "max_steps": 175,
50
+ "num_input_tokens_seen": 0,
51
+ "num_train_epochs": 5,
52
+ "save_steps": 500,
53
+ "total_flos": 0,
54
+ "train_batch_size": 64,
55
+ "trial_name": null,
56
+ "trial_params": {
57
+ "learning_rate": 5.723967938193154e-05,
58
+ "num_train_epochs": 5,
59
+ "per_device_train_batch_size": 64,
60
+ "seed": 40
61
+ }
62
+ }
run-0/checkpoint-140/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdf30298e8e2e3d70c6b83e014c63bac7fbca10e5fe524ad7f608198d8195428
3
+ size 4728
run-0/checkpoint-140/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.1705259198.DESKTOP-RFEED41.20976.6 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15fcd3fe023f2c0ba611955061a08994b72925ac9fbba59e945bd81366081e99
3
- size 5586
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf8d5155d731c07ce961abab28a22ba9645bd217b721568cb5a9fa9b1a8d3b77
3
+ size 6226