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
678d666
·
verified ·
1 Parent(s): b2c6b1f

Training in progress, epoch 1

Browse files
Files changed (28) hide show
  1. model.safetensors +1 -1
  2. run-12/checkpoint-1066/config.json +43 -0
  3. run-12/checkpoint-1066/model.safetensors +3 -0
  4. run-12/checkpoint-1066/optimizer.pt +3 -0
  5. run-12/checkpoint-1066/rng_state.pth +3 -0
  6. run-12/checkpoint-1066/scheduler.pt +3 -0
  7. run-12/checkpoint-1066/special_tokens_map.json +37 -0
  8. run-12/checkpoint-1066/tokenizer_config.json +57 -0
  9. run-12/checkpoint-1066/trainer_state.json +55 -0
  10. run-12/checkpoint-1066/training_args.bin +3 -0
  11. run-12/checkpoint-1066/vocab.txt +0 -0
  12. run-12/checkpoint-1599/config.json +43 -0
  13. run-12/checkpoint-1599/model.safetensors +3 -0
  14. run-12/checkpoint-1599/optimizer.pt +3 -0
  15. run-12/checkpoint-1599/rng_state.pth +3 -0
  16. run-12/checkpoint-1599/scheduler.pt +3 -0
  17. run-12/checkpoint-1599/special_tokens_map.json +37 -0
  18. run-12/checkpoint-1599/tokenizer_config.json +57 -0
  19. run-12/checkpoint-1599/trainer_state.json +71 -0
  20. run-12/checkpoint-1599/training_args.bin +3 -0
  21. run-12/checkpoint-1599/vocab.txt +0 -0
  22. run-13/checkpoint-533/model.safetensors +1 -1
  23. run-13/checkpoint-533/optimizer.pt +1 -1
  24. run-13/checkpoint-533/scheduler.pt +1 -1
  25. run-13/checkpoint-533/trainer_state.json +12 -15
  26. run-13/checkpoint-533/training_args.bin +1 -1
  27. runs/Apr18_16-31-07_544fc269209b/events.out.tfevents.1713459519.544fc269209b.792.13 +3 -0
  28. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe07259d9730d4e977f0ace3095ed9a12db8ca213a077aeeb4a5734c51a25244
3
  size 409103316
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70eeaf9350225dda5a0f2d7d25da6b9991bac7fadb137f197edf5640a325b3af
3
  size 409103316
run-12/checkpoint-1066/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-12/checkpoint-1066/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c77f3d4b9fd1426ccb708631c63840f2f782b85a4177115d5f7ad195a765127f
3
+ size 409103316
run-12/checkpoint-1066/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:930cfe7f801c357cd26151bafe7a7c79bce1942f6d8f49e81ca2361c3f240571
3
+ size 818327802
run-12/checkpoint-1066/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e93670da55318d823f1e4c03808b51663a5b6c2853342674abb539144107925
3
+ size 14244
run-12/checkpoint-1066/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01566d09b959fa7876a7b4c5f191b36630af280370c683efc42faf753dca04ea
3
+ size 1064
run-12/checkpoint-1066/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-12/checkpoint-1066/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-12/checkpoint-1066/trainer_state.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6433334350585938,
3
+ "best_model_checkpoint": "BERT-WMM/run-12/checkpoint-1066",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1066,
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": 10.519768714904785,
14
+ "learning_rate": 2.0153542741677195e-05,
15
+ "loss": 0.7357,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7380281690140845,
21
+ "eval_loss": 0.6585038304328918,
22
+ "eval_runtime": 2.092,
23
+ "eval_samples_per_second": 1018.141,
24
+ "eval_steps_per_second": 64.052,
25
+ "step": 533
26
+ },
27
+ {
28
+ "epoch": 1.88,
29
+ "grad_norm": 10.527291297912598,
30
+ "learning_rate": 1.0984506007520144e-05,
31
+ "loss": 0.4807,
32
+ "step": 1000
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.7624413145539906,
37
+ "eval_loss": 0.6433334350585938,
38
+ "eval_runtime": 2.1058,
39
+ "eval_samples_per_second": 1011.511,
40
+ "eval_steps_per_second": 63.635,
41
+ "step": 1066
42
+ }
43
+ ],
44
+ "logging_steps": 500,
45
+ "max_steps": 1599,
46
+ "num_input_tokens_seen": 0,
47
+ "num_train_epochs": 3,
48
+ "save_steps": 500,
49
+ "total_flos": 338261076519408.0,
50
+ "train_batch_size": 16,
51
+ "trial_name": null,
52
+ "trial_params": {
53
+ "learning_rate": 2.9322579475834245e-05
54
+ }
55
+ }
run-12/checkpoint-1066/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4cc0e168941911ceed1d2a5b00947af0590a3aef308b6c49e334538f60ccac1
3
+ size 4856
run-12/checkpoint-1066/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-12/checkpoint-1599/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-12/checkpoint-1599/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0afa6460faa921a394cb65651e8f781c01ef4ec980a2e5f506e92acb5f6f5fba
3
+ size 409103316
run-12/checkpoint-1599/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca678a0148195272928542e152c5453c9eeeaacd2cba9db27791580af03d7791
3
+ size 818327802
run-12/checkpoint-1599/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a0297d8a44379421fcc37b5cd89b37859cf20f999ea1e0c6d33126202fb0483
3
+ size 14244
run-12/checkpoint-1599/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca0187aba9001887cea0c1fea9f711f19a38e350f855f202624d90b355f15904
3
+ size 1064
run-12/checkpoint-1599/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-12/checkpoint-1599/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-12/checkpoint-1599/trainer_state.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6433334350585938,
3
+ "best_model_checkpoint": "BERT-WMM/run-12/checkpoint-1066",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1599,
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": 10.519768714904785,
14
+ "learning_rate": 2.0153542741677195e-05,
15
+ "loss": 0.7357,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7380281690140845,
21
+ "eval_loss": 0.6585038304328918,
22
+ "eval_runtime": 2.092,
23
+ "eval_samples_per_second": 1018.141,
24
+ "eval_steps_per_second": 64.052,
25
+ "step": 533
26
+ },
27
+ {
28
+ "epoch": 1.88,
29
+ "grad_norm": 10.527291297912598,
30
+ "learning_rate": 1.0984506007520144e-05,
31
+ "loss": 0.4807,
32
+ "step": 1000
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.7624413145539906,
37
+ "eval_loss": 0.6433334350585938,
38
+ "eval_runtime": 2.1058,
39
+ "eval_samples_per_second": 1011.511,
40
+ "eval_steps_per_second": 63.635,
41
+ "step": 1066
42
+ },
43
+ {
44
+ "epoch": 2.81,
45
+ "grad_norm": 16.033649444580078,
46
+ "learning_rate": 1.8154692733630958e-06,
47
+ "loss": 0.2957,
48
+ "step": 1500
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.7713615023474178,
53
+ "eval_loss": 0.7535221576690674,
54
+ "eval_runtime": 2.0955,
55
+ "eval_samples_per_second": 1016.443,
56
+ "eval_steps_per_second": 63.945,
57
+ "step": 1599
58
+ }
59
+ ],
60
+ "logging_steps": 500,
61
+ "max_steps": 1599,
62
+ "num_input_tokens_seen": 0,
63
+ "num_train_epochs": 3,
64
+ "save_steps": 500,
65
+ "total_flos": 507646505902536.0,
66
+ "train_batch_size": 16,
67
+ "trial_name": null,
68
+ "trial_params": {
69
+ "learning_rate": 2.9322579475834245e-05
70
+ }
71
+ }
run-12/checkpoint-1599/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4cc0e168941911ceed1d2a5b00947af0590a3aef308b6c49e334538f60ccac1
3
+ size 4856
run-12/checkpoint-1599/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-13/checkpoint-533/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19cf132e1ec02e0c30d81009a761fc4520c92c64412183f266bf3de7c588a666
3
  size 409103316
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70eeaf9350225dda5a0f2d7d25da6b9991bac7fadb137f197edf5640a325b3af
3
  size 409103316
run-13/checkpoint-533/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d2e1b0dfc1f51895712dcfe08b77fa0369aa05eaa30e73279457dc58f81cc6d
3
  size 818327802
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbc34a4ada868fe18028722fdd3af34b640747388c1efb0592c4f7d7af2e9366
3
  size 818327802
run-13/checkpoint-533/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:229b4fbc616a55a6a6eb2b1116adb38304a2b6c1cedd5849bbec02d9163089aa
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28833eb2e810e4dca2d9066862f3ae1fdc7b441f7af868505dbd8ae8ca72e062
3
  size 1064
run-13/checkpoint-533/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.6162846088409424,
3
  "best_model_checkpoint": "BERT-WMM/run-13/checkpoint-533",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
@@ -10,33 +10,30 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.94,
13
- "grad_norm": 12.600181579589844,
14
- "learning_rate": 1.4607577277616791e-05,
15
- "loss": 0.7148,
16
  "step": 500
17
  },
18
  {
19
  "epoch": 1.0,
20
- "eval_accuracy": 0.7577464788732394,
21
- "eval_loss": 0.6162846088409424,
22
- "eval_runtime": 1.9944,
23
- "eval_samples_per_second": 1067.994,
24
- "eval_steps_per_second": 67.188,
25
  "step": 533
26
  }
27
  ],
28
  "logging_steps": 500,
29
- "max_steps": 2665,
30
  "num_input_tokens_seen": 0,
31
- "num_train_epochs": 5,
32
  "save_steps": 500,
33
  "total_flos": 169371040368096.0,
34
  "train_batch_size": 16,
35
  "trial_name": null,
36
  "trial_params": {
37
- "learning_rate": 1.7981151706627596e-05,
38
- "num_train_epochs": 5,
39
- "per_device_train_batch_size": 16,
40
- "weight_decay": 0.009594844383188954
41
  }
42
  }
 
1
  {
2
+ "best_metric": 0.6320850253105164,
3
  "best_model_checkpoint": "BERT-WMM/run-13/checkpoint-533",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
 
10
  "log_history": [
11
  {
12
  "epoch": 0.94,
13
+ "grad_norm": 10.287070274353027,
14
+ "learning_rate": 2.5052467945332135e-05,
15
+ "loss": 0.738,
16
  "step": 500
17
  },
18
  {
19
  "epoch": 1.0,
20
+ "eval_accuracy": 0.7553990610328638,
21
+ "eval_loss": 0.6320850253105164,
22
+ "eval_runtime": 2.1232,
23
+ "eval_samples_per_second": 1003.214,
24
+ "eval_steps_per_second": 63.113,
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
+ "learning_rate": 3.645031505421846e-05
 
 
 
38
  }
39
  }
run-13/checkpoint-533/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:487692c351886fb721523721f90e7b355b077959171c7e7c7bf47d30d3da6baa
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25eca8561e5e43ced594151a61c7d90ab719b2866c7c317a196854a07d1bafd0
3
  size 4856
runs/Apr18_16-31-07_544fc269209b/events.out.tfevents.1713459519.544fc269209b.792.13 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2058b196438af8bea2636b30adcd926f3e696e5b78ad3df92d9603b40abf4821
3
+ size 5961
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4cc0e168941911ceed1d2a5b00947af0590a3aef308b6c49e334538f60ccac1
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25eca8561e5e43ced594151a61c7d90ab719b2866c7c317a196854a07d1bafd0
3
  size 4856