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
fb94690
•
1 Parent(s): e8e3353

Training in progress, epoch 1

Browse files
Files changed (26) hide show
  1. model.safetensors +1 -1
  2. run-34/checkpoint-550/config.json +54 -0
  3. run-34/checkpoint-550/model.safetensors +3 -0
  4. run-34/checkpoint-550/optimizer.pt +3 -0
  5. run-34/checkpoint-550/rng_state.pth +3 -0
  6. run-34/checkpoint-550/scheduler.pt +3 -0
  7. run-34/checkpoint-550/special_tokens_map.json +37 -0
  8. run-34/checkpoint-550/tokenizer.json +0 -0
  9. run-34/checkpoint-550/tokenizer_config.json +64 -0
  10. run-34/checkpoint-550/trainer_state.json +41 -0
  11. run-34/checkpoint-550/training_args.bin +3 -0
  12. run-34/checkpoint-550/vocab.txt +0 -0
  13. run-35/checkpoint-550/config.json +54 -0
  14. run-35/checkpoint-550/model.safetensors +3 -0
  15. run-35/checkpoint-550/optimizer.pt +3 -0
  16. run-35/checkpoint-550/rng_state.pth +3 -0
  17. run-35/checkpoint-550/scheduler.pt +3 -0
  18. run-35/checkpoint-550/special_tokens_map.json +37 -0
  19. run-35/checkpoint-550/tokenizer.json +0 -0
  20. run-35/checkpoint-550/tokenizer_config.json +64 -0
  21. run-35/checkpoint-550/trainer_state.json +41 -0
  22. run-35/checkpoint-550/training_args.bin +3 -0
  23. run-35/checkpoint-550/vocab.txt +0 -0
  24. runs/Jan15_00-51-52_DESKTOP-RFEED41/events.out.tfevents.1705285229.DESKTOP-RFEED41.20976.50 +3 -0
  25. runs/Jan15_00-51-52_DESKTOP-RFEED41/events.out.tfevents.1705285710.DESKTOP-RFEED41.20976.51 +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:a1356f3bcb9d985df284e08d5141a5e9bfd76b341bcf1854f3d182fc44785a7b
3
  size 116795404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71625a7bc7da7ac3ec61e53a7c882762f154525bd162f004286278bedaefecff
3
  size 116795404
run-34/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-34/checkpoint-550/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c64d046d029d8cb9ec91d6a27bdc422aca0f532047c89ba9e3ddcf0e7ac42ba
3
+ size 116795404
run-34/checkpoint-550/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f236c367dd267f1313778ee383b08b2b1f43ac4911bee4a6c3593cd6e60ab591
3
+ size 233621882
run-34/checkpoint-550/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cea1f72f5bc6670d59198a27a8af55f06a7f6eb6f75e5fa0ca92b634c5df5bf1
3
+ size 13990
run-34/checkpoint-550/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e60d41094bf14b5cbc77f3e1b97c087cc8ee14c314fe29492f74f8f5bb5bcc01
3
+ size 1064
run-34/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-34/checkpoint-550/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-34/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-34/checkpoint-550/trainer_state.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8530612244897959,
3
+ "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-34\\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": 3.063757566854564e-05,
14
+ "loss": 1.3796,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8530612244897959,
20
+ "eval_loss": 0.6359270215034485,
21
+ "eval_runtime": 2.196,
22
+ "eval_samples_per_second": 111.566,
23
+ "eval_steps_per_second": 7.286,
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": 1121762252100.0,
33
+ "train_batch_size": 4,
34
+ "trial_name": null,
35
+ "trial_params": {
36
+ "learning_rate": 4.395826074182635e-05,
37
+ "num_train_epochs": 3,
38
+ "per_device_train_batch_size": 4,
39
+ "seed": 27
40
+ }
41
+ }
run-34/checkpoint-550/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b0eb2ecf425327b1cfe9f0d37846fa8db7d455dc2c8975f3ce7f4c88b49d904
3
+ size 4728
run-34/checkpoint-550/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-35/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-35/checkpoint-550/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71625a7bc7da7ac3ec61e53a7c882762f154525bd162f004286278bedaefecff
3
+ size 116795404
run-35/checkpoint-550/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d671c1f9aa117e58e48486371b2eede1bbf60692a61df0f6b87eb3f1ae67c49
3
+ size 233621882
run-35/checkpoint-550/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fcd45dd473bce71171a22f81dbfe618fbc57274198904c2d5a0103ddb30d634
3
+ size 14054
run-35/checkpoint-550/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87164963fd773f91297d9f3ca0327e6319d74e00e1edf51b1bee786e08c55f0e
3
+ size 1064
run-35/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-35/checkpoint-550/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-35/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-35/checkpoint-550/trainer_state.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8979591836734694,
3
+ "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-35\\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": 5.2795502129364494e-05,
14
+ "loss": 1.1083,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8979591836734694,
20
+ "eval_loss": 0.4396211504936218,
21
+ "eval_runtime": 1.736,
22
+ "eval_samples_per_second": 141.129,
23
+ "eval_steps_per_second": 9.217,
24
+ "step": 550
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 2200,
29
+ "num_input_tokens_seen": 0,
30
+ "num_train_epochs": 4,
31
+ "save_steps": 500,
32
+ "total_flos": 1139339805450.0,
33
+ "train_batch_size": 4,
34
+ "trial_name": null,
35
+ "trial_params": {
36
+ "learning_rate": 6.832359099094229e-05,
37
+ "num_train_epochs": 4,
38
+ "per_device_train_batch_size": 4,
39
+ "seed": 37
40
+ }
41
+ }
run-35/checkpoint-550/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c80c52c992765bddc8826fcfc4f7dbc128e9eb3e71d4fb114f50cb2a381d85cb
3
+ size 4728
run-35/checkpoint-550/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.1705285229.DESKTOP-RFEED41.20976.50 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d5668543295d3c3cba5d0a991fa630fcc9205fe6bad7e63ece6a6be44c1d95f
3
+ size 5911
runs/Jan15_00-51-52_DESKTOP-RFEED41/events.out.tfevents.1705285710.DESKTOP-RFEED41.20976.51 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c995c10bafab82360a7a76a2abb443f4effff040640736749057acc475053b37
3
+ size 6068
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:53d9b57bb2e70ab25b5079603cb9ab294e1e3c759d78d4589dbf86e54f7e5146
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c80c52c992765bddc8826fcfc4f7dbc128e9eb3e71d4fb114f50cb2a381d85cb
3
  size 4728