Hugging Face's logo

HikasaHana
/
BERT-WMM

Text Classification
Transformers
TensorBoard
Safetensors
Chinese
bert
Inference Endpoints
Model card Files Metrics Community
HikasaHana commited on
Commit
d59c5d2
·
verified ·
1 Parent(s): 7ec675a

Training in progress, epoch 1

Browse files
Files changed (33) hide show
  1. model.safetensors +1 -1
  2. run-13/checkpoint-534/config.json +43 -0
  3. run-13/checkpoint-534/model.safetensors +3 -0
  4. run-13/checkpoint-534/optimizer.pt +3 -0
  5. run-13/checkpoint-534/rng_state.pth +3 -0
  6. run-13/checkpoint-534/scheduler.pt +3 -0
  7. run-13/checkpoint-534/special_tokens_map.json +37 -0
  8. run-13/checkpoint-534/tokenizer_config.json +57 -0
  9. run-13/checkpoint-534/trainer_state.json +48 -0
  10. run-13/checkpoint-534/training_args.bin +3 -0
  11. run-13/checkpoint-534/vocab.txt +0 -0
  12. run-13/checkpoint-801/config.json +43 -0
  13. run-13/checkpoint-801/model.safetensors +3 -0
  14. run-13/checkpoint-801/optimizer.pt +3 -0
  15. run-13/checkpoint-801/rng_state.pth +3 -0
  16. run-13/checkpoint-801/scheduler.pt +3 -0
  17. run-13/checkpoint-801/special_tokens_map.json +37 -0
  18. run-13/checkpoint-801/tokenizer_config.json +57 -0
  19. run-13/checkpoint-801/trainer_state.json +57 -0
  20. run-13/checkpoint-801/training_args.bin +3 -0
  21. run-13/checkpoint-801/vocab.txt +0 -0
  22. run-14/checkpoint-533/config.json +43 -0
  23. run-14/checkpoint-533/model.safetensors +3 -0
  24. run-14/checkpoint-533/optimizer.pt +3 -0
  25. run-14/checkpoint-533/rng_state.pth +3 -0
  26. run-14/checkpoint-533/scheduler.pt +3 -0
  27. run-14/checkpoint-533/special_tokens_map.json +37 -0
  28. run-14/checkpoint-533/tokenizer_config.json +57 -0
  29. run-14/checkpoint-533/trainer_state.json +39 -0
  30. run-14/checkpoint-533/training_args.bin +3 -0
  31. run-14/checkpoint-533/vocab.txt +0 -0
  32. runs/Apr19_07-31-51_21d31c708e60/events.out.tfevents.1713514120.21d31c708e60.946.14 +3 -0
  33. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:971a3ddf817b712dc07195c844772ef5d1ec4a8fd2faa3cfc511b714130228d0
3
  size 409103316
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a945d947e49e86e546787bb669f7b65c020565b63a4511277f9d6d829957c53
3
  size 409103316
run-13/checkpoint-534/config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "hfl/chinese-bert-wwm-ext",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "NEGATIVE",
14
+ "1": "POSITIVE",
15
+ "2": "NEUTRAL"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "NEGATIVE": 0,
21
+ "NEUTRAL": 2,
22
+ "POSITIVE": 1
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "output_past": true,
30
+ "pad_token_id": 0,
31
+ "pooler_fc_size": 768,
32
+ "pooler_num_attention_heads": 12,
33
+ "pooler_num_fc_layers": 3,
34
+ "pooler_size_per_head": 128,
35
+ "pooler_type": "first_token_transform",
36
+ "position_embedding_type": "absolute",
37
+ "problem_type": "single_label_classification",
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.38.2",
40
+ "type_vocab_size": 2,
41
+ "use_cache": true,
42
+ "vocab_size": 21128
43
+ }
run-13/checkpoint-534/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2c26a4990298c617435add4fef099a107381df4b5d4dd2ceb1932c28c743541
3
+ size 409103316
run-13/checkpoint-534/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7c82d05f4ce26f22c9acaa7998473a49f5f6cbfcd52e5fa856d9f347b60ad8c
3
+ size 818327802
run-13/checkpoint-534/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50b42ca1a83d9e0487eef7bc4978f59ad97364890e28f585669fc8e766195ed9
3
+ size 14244
run-13/checkpoint-534/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dda5eab8086c3361f01b6da1d0d501e5d7ffcc15041db5c9a3384c00b843300f
3
+ size 1064
run-13/checkpoint-534/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-13/checkpoint-534/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-13/checkpoint-534/trainer_state.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5817901492118835,
3
+ "best_model_checkpoint": "BERT-WMM/run-13/checkpoint-534",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 534,
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": 0.7563380281690141,
14
+ "eval_loss": 0.6019130349159241,
15
+ "eval_runtime": 2.4359,
16
+ "eval_samples_per_second": 874.427,
17
+ "eval_steps_per_second": 55.011,
18
+ "step": 267
19
+ },
20
+ {
21
+ "epoch": 1.87,
22
+ "grad_norm": 9.674468994140625,
23
+ "learning_rate": 5.7987153604787005e-06,
24
+ "loss": 0.6061,
25
+ "step": 500
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "eval_accuracy": 0.7619718309859155,
30
+ "eval_loss": 0.5817901492118835,
31
+ "eval_runtime": 2.4819,
32
+ "eval_samples_per_second": 858.201,
33
+ "eval_steps_per_second": 53.99,
34
+ "step": 534
35
+ }
36
+ ],
37
+ "logging_steps": 500,
38
+ "max_steps": 801,
39
+ "num_input_tokens_seen": 0,
40
+ "num_train_epochs": 3,
41
+ "save_steps": 500,
42
+ "total_flos": 349221394826640.0,
43
+ "train_batch_size": 32,
44
+ "trial_name": null,
45
+ "trial_params": {
46
+ "per_device_train_batch_size": 32
47
+ }
48
+ }
run-13/checkpoint-534/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cc12ec9008fe3ca8c11132361abe51e0525170497895a06dfb1609f916fd77f
3
+ size 4856
run-13/checkpoint-534/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-13/checkpoint-801/config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "hfl/chinese-bert-wwm-ext",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "NEGATIVE",
14
+ "1": "POSITIVE",
15
+ "2": "NEUTRAL"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "NEGATIVE": 0,
21
+ "NEUTRAL": 2,
22
+ "POSITIVE": 1
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "output_past": true,
30
+ "pad_token_id": 0,
31
+ "pooler_fc_size": 768,
32
+ "pooler_num_attention_heads": 12,
33
+ "pooler_num_fc_layers": 3,
34
+ "pooler_size_per_head": 128,
35
+ "pooler_type": "first_token_transform",
36
+ "position_embedding_type": "absolute",
37
+ "problem_type": "single_label_classification",
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.38.2",
40
+ "type_vocab_size": 2,
41
+ "use_cache": true,
42
+ "vocab_size": 21128
43
+ }
run-13/checkpoint-801/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26d7f234a18b08d68556eb791d0055c0b179dd8190747f6d104dae29ea9eda1d
3
+ size 409103316
run-13/checkpoint-801/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cb41a29b069558e60295633a1200ae5a46374d86a3d3f48077ca97f9aa46387
3
+ size 818327802
run-13/checkpoint-801/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f2e88e818a2ba76e34870352cb30ede96939fd3b25fc6442146490e0caecf29
3
+ size 14244
run-13/checkpoint-801/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cbdc9fc2ef477673574bd96dbcbae5c7987ba9b5b853636ae08a8f9164bbb32
3
+ size 1064
run-13/checkpoint-801/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-13/checkpoint-801/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-13/checkpoint-801/trainer_state.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5817901492118835,
3
+ "best_model_checkpoint": "BERT-WMM/run-13/checkpoint-534",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 801,
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": 0.7563380281690141,
14
+ "eval_loss": 0.6019130349159241,
15
+ "eval_runtime": 2.4359,
16
+ "eval_samples_per_second": 874.427,
17
+ "eval_steps_per_second": 55.011,
18
+ "step": 267
19
+ },
20
+ {
21
+ "epoch": 1.87,
22
+ "grad_norm": 9.674468994140625,
23
+ "learning_rate": 5.7987153604787005e-06,
24
+ "loss": 0.6061,
25
+ "step": 500
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "eval_accuracy": 0.7619718309859155,
30
+ "eval_loss": 0.5817901492118835,
31
+ "eval_runtime": 2.4819,
32
+ "eval_samples_per_second": 858.201,
33
+ "eval_steps_per_second": 53.99,
34
+ "step": 534
35
+ },
36
+ {
37
+ "epoch": 3.0,
38
+ "eval_accuracy": 0.7582159624413145,
39
+ "eval_loss": 0.6465383768081665,
40
+ "eval_runtime": 2.4611,
41
+ "eval_samples_per_second": 865.479,
42
+ "eval_steps_per_second": 54.448,
43
+ "step": 801
44
+ }
45
+ ],
46
+ "logging_steps": 500,
47
+ "max_steps": 801,
48
+ "num_input_tokens_seen": 0,
49
+ "num_train_epochs": 3,
50
+ "save_steps": 500,
51
+ "total_flos": 349221394826640.0,
52
+ "train_batch_size": 32,
53
+ "trial_name": null,
54
+ "trial_params": {
55
+ "per_device_train_batch_size": 32
56
+ }
57
+ }
run-13/checkpoint-801/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cc12ec9008fe3ca8c11132361abe51e0525170497895a06dfb1609f916fd77f
3
+ size 4856
run-13/checkpoint-801/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-14/checkpoint-533/config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "hfl/chinese-bert-wwm-ext",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "NEGATIVE",
14
+ "1": "POSITIVE",
15
+ "2": "NEUTRAL"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "NEGATIVE": 0,
21
+ "NEUTRAL": 2,
22
+ "POSITIVE": 1
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "output_past": true,
30
+ "pad_token_id": 0,
31
+ "pooler_fc_size": 768,
32
+ "pooler_num_attention_heads": 12,
33
+ "pooler_num_fc_layers": 3,
34
+ "pooler_size_per_head": 128,
35
+ "pooler_type": "first_token_transform",
36
+ "position_embedding_type": "absolute",
37
+ "problem_type": "single_label_classification",
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.38.2",
40
+ "type_vocab_size": 2,
41
+ "use_cache": true,
42
+ "vocab_size": 21128
43
+ }
run-14/checkpoint-533/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a945d947e49e86e546787bb669f7b65c020565b63a4511277f9d6d829957c53
3
+ size 409103316
run-14/checkpoint-533/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e69f0b7d99f34f2e81422584ee7b6f8d6d5951fc530dceb4c4dabf03e73df7f
3
+ size 818327802
run-14/checkpoint-533/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4808b2c3875b1e10fbc84d9c9db1c6be6492311d42fc011bb566cb647c74695b
3
+ size 14244
run-14/checkpoint-533/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26d6e84cec3f6682da5e6ce3adbec8136f9cd24a430311733c1ab27f15ac4fc1
3
+ size 1064
run-14/checkpoint-533/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-14/checkpoint-533/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-14/checkpoint-533/trainer_state.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.603524923324585,
3
+ "best_model_checkpoint": "BERT-WMM/run-14/checkpoint-533",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 533,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.94,
13
+ "grad_norm": 11.3766508102417,
14
+ "learning_rate": 1.0605888092670128e-05,
15
+ "loss": 0.7117,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7568075117370892,
21
+ "eval_loss": 0.603524923324585,
22
+ "eval_runtime": 2.4291,
23
+ "eval_samples_per_second": 876.864,
24
+ "eval_steps_per_second": 55.164,
25
+ "step": 533
26
+ }
27
+ ],
28
+ "logging_steps": 500,
29
+ "max_steps": 1599,
30
+ "num_input_tokens_seen": 0,
31
+ "num_train_epochs": 3,
32
+ "save_steps": 500,
33
+ "total_flos": 169371040368096.0,
34
+ "train_batch_size": 16,
35
+ "trial_name": null,
36
+ "trial_params": {
37
+ "per_device_train_batch_size": 16
38
+ }
39
+ }
run-14/checkpoint-533/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebedef9b751bedd4e796367e1472df25f06ffc187165c1b123fac9f3e7ae22ec
3
+ size 4856
run-14/checkpoint-533/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Apr19_07-31-51_21d31c708e60/events.out.tfevents.1713514120.21d31c708e60.946.14 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21ea71ff2b10e3c5e5c3ba77cd525d928c55453441275efe4e2ce91930a692a3
3
+ size 6850
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9cc12ec9008fe3ca8c11132361abe51e0525170497895a06dfb1609f916fd77f
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebedef9b751bedd4e796367e1472df25f06ffc187165c1b123fac9f3e7ae22ec
3
  size 4856