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
9a8dd7d
·
verified ·
1 Parent(s): cfc788c

Training in progress, epoch 1

Browse files
Files changed (33) hide show
  1. model.safetensors +1 -1
  2. run-1/checkpoint-534/config.json +43 -0
  3. run-1/checkpoint-534/model.safetensors +3 -0
  4. run-1/checkpoint-534/optimizer.pt +3 -0
  5. run-1/checkpoint-534/rng_state.pth +3 -0
  6. run-1/checkpoint-534/scheduler.pt +3 -0
  7. run-1/checkpoint-534/special_tokens_map.json +37 -0
  8. run-1/checkpoint-534/tokenizer_config.json +57 -0
  9. run-1/checkpoint-534/trainer_state.json +48 -0
  10. run-1/checkpoint-534/training_args.bin +3 -0
  11. run-1/checkpoint-534/vocab.txt +0 -0
  12. run-1/checkpoint-801/config.json +43 -0
  13. run-1/checkpoint-801/model.safetensors +3 -0
  14. run-1/checkpoint-801/optimizer.pt +3 -0
  15. run-1/checkpoint-801/rng_state.pth +3 -0
  16. run-1/checkpoint-801/scheduler.pt +3 -0
  17. run-1/checkpoint-801/special_tokens_map.json +37 -0
  18. run-1/checkpoint-801/tokenizer_config.json +57 -0
  19. run-1/checkpoint-801/trainer_state.json +57 -0
  20. run-1/checkpoint-801/training_args.bin +3 -0
  21. run-1/checkpoint-801/vocab.txt +0 -0
  22. run-2/checkpoint-267/model.safetensors +1 -1
  23. run-2/checkpoint-267/optimizer.pt +1 -1
  24. run-2/checkpoint-267/scheduler.pt +1 -1
  25. run-2/checkpoint-267/trainer_state.json +9 -9
  26. run-2/checkpoint-267/training_args.bin +1 -1
  27. run-2/checkpoint-534/model.safetensors +1 -1
  28. run-2/checkpoint-534/optimizer.pt +1 -1
  29. run-2/checkpoint-534/scheduler.pt +1 -1
  30. run-2/checkpoint-534/trainer_state.json +17 -17
  31. run-2/checkpoint-534/training_args.bin +1 -1
  32. runs/Apr19_08-35-52_21d31c708e60/events.out.tfevents.1713516474.21d31c708e60.946.22 +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 sha256:67471fdb2de3f5e33b781185b34de1cdacb31c3a781a88037017f879255731a6
3
  size 409103316
run-1/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-1/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-1/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-1/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-1/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-1/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-1/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-1/checkpoint-534/trainer_state.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5817901492118835,
3
+ "best_model_checkpoint": "BERT-WMM/run-1/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": 2.4047,
16
+ "eval_samples_per_second": 885.778,
17
+ "eval_steps_per_second": 55.725,
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": 2.4428,
32
+ "eval_samples_per_second": 871.96,
33
+ "eval_steps_per_second": 54.856,
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
+ "num_train_epochs": 3
47
+ }
48
+ }
run-1/checkpoint-534/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11f7c65747bd635b8f0e76f611e224f7ef08b5428ba70dd1530c26977be68e0b
3
+ size 4856
run-1/checkpoint-534/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/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-1/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-1/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-1/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-1/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-1/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-1/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-1/checkpoint-801/trainer_state.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5817901492118835,
3
+ "best_model_checkpoint": "BERT-WMM/run-1/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": 2.4047,
16
+ "eval_samples_per_second": 885.778,
17
+ "eval_steps_per_second": 55.725,
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": 2.4428,
32
+ "eval_samples_per_second": 871.96,
33
+ "eval_steps_per_second": 54.856,
34
+ "step": 534
35
+ },
36
+ {
37
+ "epoch": 3.0,
38
+ "eval_accuracy": 0.7582159624413145,
39
+ "eval_loss": 0.6465383768081665,
40
+ "eval_runtime": 2.4711,
41
+ "eval_samples_per_second": 861.971,
42
+ "eval_steps_per_second": 54.227,
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
+ "num_train_epochs": 3
56
+ }
57
+ }
run-1/checkpoint-801/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11f7c65747bd635b8f0e76f611e224f7ef08b5428ba70dd1530c26977be68e0b
3
+ size 4856
run-1/checkpoint-801/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-267/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 sha256:67471fdb2de3f5e33b781185b34de1cdacb31c3a781a88037017f879255731a6
3
  size 409103316
run-2/checkpoint-267/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc8b54fc5e8c9423b8eb78032472c72dce9ff03db39846d1622f31a3d6911c46
3
  size 818327802
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff34e4293540b0ab680ba65acc1e022bc0f9b82e15eae52efd1386161248b150
3
  size 818327802
run-2/checkpoint-267/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d605219d0cdfe1356d19dfc261c4f045664dbc44ddf04517d0b2ebd1dab264c7
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef3be8be9037b2d6a9348611f95c19fb1d17ca7cb1da92486df22b7e0a3c655a
3
  size 1064
run-2/checkpoint-267/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.6019130349159241,
3
  "best_model_checkpoint": "BERT-WMM/run-2/checkpoint-267",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
@@ -10,23 +10,23 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_accuracy": 0.7563380281690141,
14
- "eval_loss": 0.6019130349159241,
15
- "eval_runtime": 2.4784,
16
- "eval_samples_per_second": 859.428,
17
- "eval_steps_per_second": 54.067,
18
  "step": 267
19
  }
20
  ],
21
  "logging_steps": 500,
22
- "max_steps": 801,
23
  "num_input_tokens_seen": 0,
24
- "num_train_epochs": 3,
25
  "save_steps": 500,
26
  "total_flos": 0,
27
  "train_batch_size": 32,
28
  "trial_name": null,
29
  "trial_params": {
30
- "per_device_train_batch_size": 32
31
  }
32
  }
 
1
  {
2
+ "best_metric": 0.6066119074821472,
3
  "best_model_checkpoint": "BERT-WMM/run-2/checkpoint-267",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_accuracy": 0.7530516431924883,
14
+ "eval_loss": 0.6066119074821472,
15
+ "eval_runtime": 2.3977,
16
+ "eval_samples_per_second": 888.358,
17
+ "eval_steps_per_second": 55.887,
18
  "step": 267
19
  }
20
  ],
21
  "logging_steps": 500,
22
+ "max_steps": 534,
23
  "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 2,
25
  "save_steps": 500,
26
  "total_flos": 0,
27
  "train_batch_size": 32,
28
  "trial_name": null,
29
  "trial_params": {
30
+ "num_train_epochs": 2
31
  }
32
  }
run-2/checkpoint-267/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:b8f6fcf5a47eba5b7826ee1d35993639457d0dd79c2a23e274fbc08816d4b616
3
  size 4856
run-2/checkpoint-534/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2c26a4990298c617435add4fef099a107381df4b5d4dd2ceb1932c28c743541
3
  size 409103316
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47cc2a88ee5ce8d55f3222e55dbf8add7de9908d8091afb8cc226bfb3d399dd2
3
  size 409103316
run-2/checkpoint-534/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7c82d05f4ce26f22c9acaa7998473a49f5f6cbfcd52e5fa856d9f347b60ad8c
3
  size 818327802
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2f5edb9079d5e469022909184db9c02b90e6aa9da43f5b6f0fa52822ac26dda
3
  size 818327802
run-2/checkpoint-534/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dda5eab8086c3361f01b6da1d0d501e5d7ffcc15041db5c9a3384c00b843300f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a56050495e1938ae70b239ae8ece3c43ac800b58f0a6e02bd7ed6cd1669797d
3
  size 1064
run-2/checkpoint-534/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.5817901492118835,
3
  "best_model_checkpoint": "BERT-WMM/run-2/checkpoint-534",
4
  "epoch": 2.0,
5
  "eval_steps": 500,
@@ -10,39 +10,39 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_accuracy": 0.7563380281690141,
14
- "eval_loss": 0.6019130349159241,
15
- "eval_runtime": 2.4784,
16
- "eval_samples_per_second": 859.428,
17
- "eval_steps_per_second": 54.067,
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": 2.5361,
32
- "eval_samples_per_second": 839.87,
33
- "eval_steps_per_second": 52.837,
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
  }
 
1
  {
2
+ "best_metric": 0.6037493944168091,
3
  "best_model_checkpoint": "BERT-WMM/run-2/checkpoint-534",
4
  "epoch": 2.0,
5
  "eval_steps": 500,
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_accuracy": 0.7530516431924883,
14
+ "eval_loss": 0.6066119074821472,
15
+ "eval_runtime": 2.3977,
16
+ "eval_samples_per_second": 888.358,
17
+ "eval_steps_per_second": 55.887,
18
  "step": 267
19
  },
20
  {
21
  "epoch": 1.87,
22
+ "grad_norm": 9.448624610900879,
23
+ "learning_rate": 9.825065893169892e-07,
24
+ "loss": 0.6083,
25
  "step": 500
26
  },
27
  {
28
  "epoch": 2.0,
29
+ "eval_accuracy": 0.7615023474178404,
30
+ "eval_loss": 0.6037493944168091,
31
+ "eval_runtime": 2.4307,
32
+ "eval_samples_per_second": 876.303,
33
+ "eval_steps_per_second": 55.129,
34
  "step": 534
35
  }
36
  ],
37
  "logging_steps": 500,
38
+ "max_steps": 534,
39
  "num_input_tokens_seen": 0,
40
+ "num_train_epochs": 2,
41
  "save_steps": 500,
42
  "total_flos": 349221394826640.0,
43
  "train_batch_size": 32,
44
  "trial_name": null,
45
  "trial_params": {
46
+ "num_train_epochs": 2
47
  }
48
  }
run-2/checkpoint-534/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:b8f6fcf5a47eba5b7826ee1d35993639457d0dd79c2a23e274fbc08816d4b616
3
  size 4856
runs/Apr19_08-35-52_21d31c708e60/events.out.tfevents.1713516474.21d31c708e60.946.22 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73d499a4d5c063a37a00526f52a08c367b52a59b26eea7d6073a7b559a756d4d
3
+ size 6105
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11f7c65747bd635b8f0e76f611e224f7ef08b5428ba70dd1530c26977be68e0b
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8f6fcf5a47eba5b7826ee1d35993639457d0dd79c2a23e274fbc08816d4b616
3
  size 4856