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
b78eb80
·
verified ·
1 Parent(s): 09799f5

Training in progress, epoch 1

Browse files
Files changed (25) hide show
  1. model.safetensors +1 -1
  2. run-7/checkpoint-102/config.json +43 -0
  3. run-7/checkpoint-102/model.safetensors +3 -0
  4. run-7/checkpoint-102/optimizer.pt +3 -0
  5. run-7/checkpoint-102/rng_state.pth +3 -0
  6. run-7/checkpoint-102/scheduler.pt +3 -0
  7. run-7/checkpoint-102/special_tokens_map.json +37 -0
  8. run-7/checkpoint-102/tokenizer_config.json +57 -0
  9. run-7/checkpoint-102/trainer_state.json +50 -0
  10. run-7/checkpoint-102/training_args.bin +3 -0
  11. run-7/checkpoint-102/vocab.txt +0 -0
  12. run-7/checkpoint-68/model.safetensors +1 -1
  13. run-7/checkpoint-68/optimizer.pt +1 -1
  14. run-7/checkpoint-68/rng_state.pth +1 -1
  15. run-7/checkpoint-68/scheduler.pt +1 -1
  16. run-7/checkpoint-68/trainer_state.json +14 -17
  17. run-7/checkpoint-68/training_args.bin +1 -1
  18. run-8/checkpoint-67/model.safetensors +1 -1
  19. run-8/checkpoint-67/optimizer.pt +1 -1
  20. run-8/checkpoint-67/rng_state.pth +1 -1
  21. run-8/checkpoint-67/scheduler.pt +1 -1
  22. run-8/checkpoint-67/trainer_state.json +9 -12
  23. run-8/checkpoint-67/training_args.bin +1 -1
  24. runs/Apr19_07-31-51_21d31c708e60/events.out.tfevents.1713513186.21d31c708e60.946.8 +3 -0
  25. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:caa48ffd14eb35c6b29c6ab7442c2f5348b6e6b121e688f63d22592e6b23ff7b
3
  size 409103316
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c111bdda5e63ed643f9e9bbf5263f981bade833ba8a91d158a63e63ce15dbfd7
3
  size 409103316
run-7/checkpoint-102/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-7/checkpoint-102/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bc884480b0f95ab9090f90ae82038be16fa6a5adb360b5d6be4dac2688a43a6
3
+ size 409103316
run-7/checkpoint-102/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0b8258d06656f0740871eefd0955bd5dabbdfca8452e7d8f777427096e26e58
3
+ size 818327802
run-7/checkpoint-102/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea47b1b05839911b64924cd317be2ec83826dbf9cc2c34f94e4e124e2b2a7b77
3
+ size 14244
run-7/checkpoint-102/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e92c366abba4d2151976bc1dcc7e61565d088928310c962cab02ccd9837c8ae
3
+ size 1064
run-7/checkpoint-102/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-7/checkpoint-102/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-7/checkpoint-102/trainer_state.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6329721808433533,
3
+ "best_model_checkpoint": "BERT-WMM/run-7/checkpoint-102",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 102,
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": 0.7056338028169014,
14
+ "eval_loss": 0.7160280346870422,
15
+ "eval_runtime": 2.484,
16
+ "eval_samples_per_second": 857.474,
17
+ "eval_steps_per_second": 53.944,
18
+ "step": 34
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.7389671361502348,
23
+ "eval_loss": 0.6426944732666016,
24
+ "eval_runtime": 2.5129,
25
+ "eval_samples_per_second": 847.618,
26
+ "eval_steps_per_second": 53.324,
27
+ "step": 68
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_accuracy": 0.7394366197183099,
32
+ "eval_loss": 0.6329721808433533,
33
+ "eval_runtime": 2.5022,
34
+ "eval_samples_per_second": 851.264,
35
+ "eval_steps_per_second": 53.554,
36
+ "step": 102
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 102,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 3,
43
+ "save_steps": 500,
44
+ "total_flos": 0,
45
+ "train_batch_size": 256,
46
+ "trial_name": null,
47
+ "trial_params": {
48
+ "per_device_train_batch_size": 256
49
+ }
50
+ }
run-7/checkpoint-102/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:737ee679ef3f19e9db5cc10c2c9fa844d60b242aacb6b6733c2c5ef939da8045
3
+ size 4856
run-7/checkpoint-102/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-68/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6dc3acca66d03ff44a6d6f2d279a81a4a20e376e740c2db12a7f52fc55f9db50
3
  size 409103316
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:398860ac6d76db7029e8e2548f14d6815d02d98756b08a2f5d5f9b289f8989fe
3
  size 409103316
run-7/checkpoint-68/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aea89b454ef047218ca9aa7974a8c177046710628bd83d7f3aa9d823be41f16a
3
  size 818327802
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:507ab11be7fb9454ea2b474cb1ba269c0392ac5458ceda887bb554646236c8d5
3
  size 818327802
run-7/checkpoint-68/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9eceba03aec53c56e4e84551a3c4df5d382d62d120b30345074d8d435cf85c5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fdfa98531aaf097225a42a10008d0fdcb1536c2425abf080be01d7f85a1247d
3
  size 14244
run-7/checkpoint-68/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8cb16be71f15963587c272aa389928227c4aa20424473e2f4b79019fb5bd7aa4
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d7dc2f08b89a0cc0f4cafe51e97ba263bb3e4f0f403161fc364b53f56b0c3d9
3
  size 1064
run-7/checkpoint-68/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.6432904601097107,
3
  "best_model_checkpoint": "BERT-WMM/run-7/checkpoint-68",
4
  "epoch": 2.0,
5
  "eval_steps": 500,
@@ -10,35 +10,32 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_accuracy": 0.7136150234741784,
14
- "eval_loss": 0.6808687448501587,
15
- "eval_runtime": 2.0038,
16
- "eval_samples_per_second": 1063.006,
17
- "eval_steps_per_second": 66.875,
18
  "step": 34
19
  },
20
  {
21
  "epoch": 2.0,
22
- "eval_accuracy": 0.7370892018779343,
23
- "eval_loss": 0.6432904601097107,
24
- "eval_runtime": 2.1671,
25
- "eval_samples_per_second": 982.896,
26
- "eval_steps_per_second": 61.835,
27
  "step": 68
28
  }
29
  ],
30
  "logging_steps": 500,
31
- "max_steps": 68,
32
  "num_input_tokens_seen": 0,
33
- "num_train_epochs": 2,
34
  "save_steps": 500,
35
  "total_flos": 0,
36
  "train_batch_size": 256,
37
  "trial_name": null,
38
  "trial_params": {
39
- "learning_rate": 2.8228078127928265e-05,
40
- "num_train_epochs": 2,
41
- "per_device_train_batch_size": 256,
42
- "weight_decay": 9.933633111626257e-05
43
  }
44
  }
 
1
  {
2
+ "best_metric": 0.6426944732666016,
3
  "best_model_checkpoint": "BERT-WMM/run-7/checkpoint-68",
4
  "epoch": 2.0,
5
  "eval_steps": 500,
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_accuracy": 0.7056338028169014,
14
+ "eval_loss": 0.7160280346870422,
15
+ "eval_runtime": 2.484,
16
+ "eval_samples_per_second": 857.474,
17
+ "eval_steps_per_second": 53.944,
18
  "step": 34
19
  },
20
  {
21
  "epoch": 2.0,
22
+ "eval_accuracy": 0.7389671361502348,
23
+ "eval_loss": 0.6426944732666016,
24
+ "eval_runtime": 2.5129,
25
+ "eval_samples_per_second": 847.618,
26
+ "eval_steps_per_second": 53.324,
27
  "step": 68
28
  }
29
  ],
30
  "logging_steps": 500,
31
+ "max_steps": 102,
32
  "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 3,
34
  "save_steps": 500,
35
  "total_flos": 0,
36
  "train_batch_size": 256,
37
  "trial_name": null,
38
  "trial_params": {
39
+ "per_device_train_batch_size": 256
 
 
 
40
  }
41
  }
run-7/checkpoint-68/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d0664cb84434137aa481b2ab8fa3a6ae86965cb1d2f9c1e6700ae921a512164
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:737ee679ef3f19e9db5cc10c2c9fa844d60b242aacb6b6733c2c5ef939da8045
3
  size 4856
run-8/checkpoint-67/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d78992e35935d5f911a751b5d9af9f3337a0fdf972c4ad150fa4832b8cd50fd8
3
  size 409103316
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c111bdda5e63ed643f9e9bbf5263f981bade833ba8a91d158a63e63ce15dbfd7
3
  size 409103316
run-8/checkpoint-67/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c87b924bb00545becd74ee89a984554c0ce16cb734114c56c8f2298be62c5afe
3
  size 818327802
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e46eeb46e538e3fa9368cdb9d9c603cdcaf73f039a0e0775af1ed10fbf51b463
3
  size 818327802
run-8/checkpoint-67/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae15c22d65bfce78a7d29ac404b15eb9e54c59089cc9c853a5ec4b8b89370a99
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5981e0d53037ec7abf90bd1c7fd7545ded749f2e186df624e2582b9ab57152c
3
  size 14244
run-8/checkpoint-67/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed55a781adb2711f21864b1a342b58cd7af0ff8ab55c991c5fc5695524c01f6c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b24a81c409199d13852daaad7ee11bc071f7e0be1a34b167f29b26cbea73c492
3
  size 1064
run-8/checkpoint-67/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.7196662425994873,
3
  "best_model_checkpoint": "BERT-WMM/run-8/checkpoint-67",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
@@ -10,26 +10,23 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_accuracy": 0.7004694835680751,
14
- "eval_loss": 0.7196662425994873,
15
- "eval_runtime": 2.0508,
16
- "eval_samples_per_second": 1038.62,
17
- "eval_steps_per_second": 65.34,
18
  "step": 67
19
  }
20
  ],
21
  "logging_steps": 500,
22
- "max_steps": 67,
23
  "num_input_tokens_seen": 0,
24
- "num_train_epochs": 1,
25
  "save_steps": 500,
26
  "total_flos": 0,
27
  "train_batch_size": 128,
28
  "trial_name": null,
29
  "trial_params": {
30
- "learning_rate": 7.063546836742468e-05,
31
- "num_train_epochs": 1,
32
- "per_device_train_batch_size": 128,
33
- "weight_decay": 0.06190261700862519
34
  }
35
  }
 
1
  {
2
+ "best_metric": 0.6488438844680786,
3
  "best_model_checkpoint": "BERT-WMM/run-8/checkpoint-67",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_accuracy": 0.7380281690140845,
14
+ "eval_loss": 0.6488438844680786,
15
+ "eval_runtime": 2.483,
16
+ "eval_samples_per_second": 857.843,
17
+ "eval_steps_per_second": 53.968,
18
  "step": 67
19
  }
20
  ],
21
  "logging_steps": 500,
22
+ "max_steps": 201,
23
  "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 3,
25
  "save_steps": 500,
26
  "total_flos": 0,
27
  "train_batch_size": 128,
28
  "trial_name": null,
29
  "trial_params": {
30
+ "per_device_train_batch_size": 128
 
 
 
31
  }
32
  }
run-8/checkpoint-67/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4bb84483d3f37a31eb4791395662665a1f55283f28759b8d3e52c8a7e2c3a0c
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f283a46d9e3dec517768c984d4d84d933f3cae0cde493cec55ad2e6b7c2b58f
3
  size 4856
runs/Apr19_07-31-51_21d31c708e60/events.out.tfevents.1713513186.21d31c708e60.946.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:929978132be17649707adac84cb85f249446c723d32fe73f0d5846957605bfee
3
+ size 6212
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:737ee679ef3f19e9db5cc10c2c9fa844d60b242aacb6b6733c2c5ef939da8045
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f283a46d9e3dec517768c984d4d84d933f3cae0cde493cec55ad2e6b7c2b58f
3
  size 4856