Hugging Face's logo

joseph10
/
tinybert-TG-HS-HX-parentpretrained

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
joseph10 commited on
Commit
2c70d60
•
1 Parent(s): d0b23dd

Training in progress, epoch 1

Browse files
Files changed (34) hide show
  1. logs/events.out.tfevents.1702265532.joseph_legion.22340.14 +2 -2
  2. logs/events.out.tfevents.1702267900.joseph_legion.22340.15 +3 -0
  3. model.safetensors +1 -1
  4. run-1/checkpoint-788/config.json +34 -0
  5. run-1/checkpoint-788/model.safetensors +3 -0
  6. run-1/checkpoint-788/optimizer.pt +3 -0
  7. run-1/checkpoint-788/rng_state.pth +3 -0
  8. run-1/checkpoint-788/scheduler.pt +3 -0
  9. run-1/checkpoint-788/special_tokens_map.json +7 -0
  10. run-1/checkpoint-788/tokenizer_config.json +57 -0
  11. run-1/checkpoint-788/trainer_state.json +85 -0
  12. run-1/checkpoint-788/training_args.bin +3 -0
  13. run-1/checkpoint-788/vocab.txt +0 -0
  14. run-1/checkpoint-985/config.json +34 -0
  15. run-1/checkpoint-985/model.safetensors +3 -0
  16. run-1/checkpoint-985/optimizer.pt +3 -0
  17. run-1/checkpoint-985/rng_state.pth +3 -0
  18. run-1/checkpoint-985/scheduler.pt +3 -0
  19. run-1/checkpoint-985/special_tokens_map.json +7 -0
  20. run-1/checkpoint-985/tokenizer_config.json +57 -0
  21. run-1/checkpoint-985/trainer_state.json +100 -0
  22. run-1/checkpoint-985/training_args.bin +3 -0
  23. run-1/checkpoint-985/vocab.txt +0 -0
  24. run-2/checkpoint-197/config.json +34 -0
  25. run-2/checkpoint-197/model.safetensors +3 -0
  26. run-2/checkpoint-197/optimizer.pt +3 -0
  27. run-2/checkpoint-197/rng_state.pth +3 -0
  28. run-2/checkpoint-197/scheduler.pt +3 -0
  29. run-2/checkpoint-197/special_tokens_map.json +7 -0
  30. run-2/checkpoint-197/tokenizer_config.json +57 -0
  31. run-2/checkpoint-197/trainer_state.json +40 -0
  32. run-2/checkpoint-197/training_args.bin +3 -0
  33. run-2/checkpoint-197/vocab.txt +0 -0
  34. training_args.bin +1 -1
logs/events.out.tfevents.1702265532.joseph_legion.22340.14 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e1e27813786bf2c5caa0e1bc63f8a8c318a2f90cdff9e055cf1cb4a8b1a9eb3d
3
- size 5886
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5ae32032993f745ed4c439c51d8ca260abff103dad532e7ffacf2d0e08cfafd
3
+ size 7200
logs/events.out.tfevents.1702267900.joseph_legion.22340.15 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7793f3d5fc98636d74490f33b7eec49df847d92ebcb1ff25926b17ac80a96d16
3
+ size 4924
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a1c6a94dffdc02620690ebcb57f67bc44e2a082137ee9789d8dbe7ade6f1113
3
  size 44692608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:099969a8f9094d860312b22490b527b3f2eebc0134ba7da3c3ff41f683603a11
3
  size 44692608
run-1/checkpoint-788/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-4_H-256_A-4",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 256,
11
+ "id2label": {
12
+ "0": 0,
13
+ "1": 1
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 1024,
17
+ "label2id": {
18
+ "0": 0,
19
+ "1": 1
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 4,
25
+ "num_hidden_layers": 4,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.36.0.dev0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-1/checkpoint-788/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e1c65f671d7e3946a709121c497299cedc55cf9e1467e538bc44ccfde6f51a6
3
+ size 44692608
run-1/checkpoint-788/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac1249ebe056fde424a0278f14a8c3b3bd7bf6c8ee44298cc9e1d0ec2d1ba925
3
+ size 89430010
run-1/checkpoint-788/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e39bb59d0602913d0446fb1b887e3bef027f47ac31f57a5e1aad549eeef7f347
3
+ size 14308
run-1/checkpoint-788/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c766dc58ac818f0770237a7067b869cc69aeb50b6cd62cffb1746ca52af04d33
3
+ size 1064
run-1/checkpoint-788/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-1/checkpoint-788/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": 512,
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-788/trainer_state.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.778071150639244,
3
+ "best_model_checkpoint": "tinybert-TG-HS-HX-parentpretrained\\run-1\\checkpoint-788",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 788,
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
+ "learning_rate": 4.6037225390588216e-06,
14
+ "loss": 0.2825,
15
+ "step": 197
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.7523624235686492,
20
+ "eval_loss": 0.26902320981025696,
21
+ "eval_runtime": 126.6156,
22
+ "eval_samples_per_second": 56.833,
23
+ "eval_steps_per_second": 0.45,
24
+ "step": 197
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 3.4527919042941157e-06,
29
+ "loss": 0.2724,
30
+ "step": 394
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.7718176764869372,
35
+ "eval_loss": 0.2650889456272125,
36
+ "eval_runtime": 126.546,
37
+ "eval_samples_per_second": 56.865,
38
+ "eval_steps_per_second": 0.45,
39
+ "step": 394
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 2.3018612695294108e-06,
44
+ "loss": 0.2692,
45
+ "step": 591
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.7759866592551418,
50
+ "eval_loss": 0.2634750008583069,
51
+ "eval_runtime": 126.5942,
52
+ "eval_samples_per_second": 56.843,
53
+ "eval_steps_per_second": 0.45,
54
+ "step": 591
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 1.1509306347647054e-06,
59
+ "loss": 0.2681,
60
+ "step": 788
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.778071150639244,
65
+ "eval_loss": 0.2624979019165039,
66
+ "eval_runtime": 126.5477,
67
+ "eval_samples_per_second": 56.864,
68
+ "eval_steps_per_second": 0.45,
69
+ "step": 788
70
+ }
71
+ ],
72
+ "logging_steps": 500,
73
+ "max_steps": 985,
74
+ "num_input_tokens_seen": 0,
75
+ "num_train_epochs": 5,
76
+ "save_steps": 500,
77
+ "total_flos": 177030409545900.0,
78
+ "trial_name": null,
79
+ "trial_params": {
80
+ "alpha": 0.4394092153370026,
81
+ "learning_rate": 5.7546531738235265e-06,
82
+ "num_train_epochs": 5,
83
+ "temperature": 23
84
+ }
85
+ }
run-1/checkpoint-788/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebe907fa2c71e3e43a89d80ee43fe99adc34e72494d59b4f8a29ae3ebf5591db
3
+ size 4792
run-1/checkpoint-788/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-985/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-4_H-256_A-4",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 256,
11
+ "id2label": {
12
+ "0": 0,
13
+ "1": 1
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 1024,
17
+ "label2id": {
18
+ "0": 0,
19
+ "1": 1
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 4,
25
+ "num_hidden_layers": 4,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.36.0.dev0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-1/checkpoint-985/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f6551f2f39c8a41bb4e9571adc2e7aba6e0b4bf50e0a734c4506220b928dcd3
3
+ size 44692608
run-1/checkpoint-985/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75c304431c5c1399f72d1d8de85722309df120e374f27bb3a1b829eff6d386bc
3
+ size 89430010
run-1/checkpoint-985/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50a364bebceef36329237a96faee9e2da941c96eff10dae0acfc327c86066983
3
+ size 14308
run-1/checkpoint-985/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a01c42abe7d71676246ef5c1c1f8026a3924b2fa252e6dba16c381b8329aa63
3
+ size 1064
run-1/checkpoint-985/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-1/checkpoint-985/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": 512,
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-985/trainer_state.json ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7794608115619789,
3
+ "best_model_checkpoint": "tinybert-TG-HS-HX-parentpretrained\\run-1\\checkpoint-985",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 985,
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
+ "learning_rate": 4.6037225390588216e-06,
14
+ "loss": 0.2825,
15
+ "step": 197
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.7523624235686492,
20
+ "eval_loss": 0.26902320981025696,
21
+ "eval_runtime": 126.6156,
22
+ "eval_samples_per_second": 56.833,
23
+ "eval_steps_per_second": 0.45,
24
+ "step": 197
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 3.4527919042941157e-06,
29
+ "loss": 0.2724,
30
+ "step": 394
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.7718176764869372,
35
+ "eval_loss": 0.2650889456272125,
36
+ "eval_runtime": 126.546,
37
+ "eval_samples_per_second": 56.865,
38
+ "eval_steps_per_second": 0.45,
39
+ "step": 394
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 2.3018612695294108e-06,
44
+ "loss": 0.2692,
45
+ "step": 591
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.7759866592551418,
50
+ "eval_loss": 0.2634750008583069,
51
+ "eval_runtime": 126.5942,
52
+ "eval_samples_per_second": 56.843,
53
+ "eval_steps_per_second": 0.45,
54
+ "step": 591
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 1.1509306347647054e-06,
59
+ "loss": 0.2681,
60
+ "step": 788
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.778071150639244,
65
+ "eval_loss": 0.2624979019165039,
66
+ "eval_runtime": 126.5477,
67
+ "eval_samples_per_second": 56.864,
68
+ "eval_steps_per_second": 0.45,
69
+ "step": 788
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "learning_rate": 0.0,
74
+ "loss": 0.2674,
75
+ "step": 985
76
+ },
77
+ {
78
+ "epoch": 5.0,
79
+ "eval_accuracy": 0.7794608115619789,
80
+ "eval_loss": 0.26234734058380127,
81
+ "eval_runtime": 126.6403,
82
+ "eval_samples_per_second": 56.822,
83
+ "eval_steps_per_second": 0.45,
84
+ "step": 985
85
+ }
86
+ ],
87
+ "logging_steps": 500,
88
+ "max_steps": 985,
89
+ "num_input_tokens_seen": 0,
90
+ "num_train_epochs": 5,
91
+ "save_steps": 500,
92
+ "total_flos": 221342066021952.0,
93
+ "trial_name": null,
94
+ "trial_params": {
95
+ "alpha": 0.4394092153370026,
96
+ "learning_rate": 5.7546531738235265e-06,
97
+ "num_train_epochs": 5,
98
+ "temperature": 23
99
+ }
100
+ }
run-1/checkpoint-985/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebe907fa2c71e3e43a89d80ee43fe99adc34e72494d59b4f8a29ae3ebf5591db
3
+ size 4792
run-1/checkpoint-985/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-197/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-4_H-256_A-4",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 256,
11
+ "id2label": {
12
+ "0": 0,
13
+ "1": 1
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 1024,
17
+ "label2id": {
18
+ "0": 0,
19
+ "1": 1
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 4,
25
+ "num_hidden_layers": 4,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.36.0.dev0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-2/checkpoint-197/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:099969a8f9094d860312b22490b527b3f2eebc0134ba7da3c3ff41f683603a11
3
+ size 44692608
run-2/checkpoint-197/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6f7f9e7926d82ce022ce312ece9ab8979ca9d600e7ca8733304773e4ed56fcf
3
+ size 89430010
run-2/checkpoint-197/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfce427b13a79881b8dd7c1ca79db1eca136c641f9f35f4f0773c5f01a793672
3
+ size 14308
run-2/checkpoint-197/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bf7e64f392f8f2013bf9b8896e9980d172541e15b046e15741aa21c1c2f4f2c
3
+ size 1064
run-2/checkpoint-197/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-2/checkpoint-197/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": 512,
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-2/checkpoint-197/trainer_state.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6989994441356309,
3
+ "best_model_checkpoint": "tinybert-TG-HS-HX-parentpretrained\\run-2\\checkpoint-197",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 197,
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
+ "learning_rate": 1.6784454644765522e-06,
14
+ "loss": 0.564,
15
+ "step": 197
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.6989994441356309,
20
+ "eval_loss": 0.5322139859199524,
21
+ "eval_runtime": 125.0015,
22
+ "eval_samples_per_second": 57.567,
23
+ "eval_steps_per_second": 0.456,
24
+ "step": 197
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 985,
29
+ "num_input_tokens_seen": 0,
30
+ "num_train_epochs": 5,
31
+ "save_steps": 500,
32
+ "total_flos": 44298765947484.0,
33
+ "trial_name": null,
34
+ "trial_params": {
35
+ "alpha": 0.8786599620319323,
36
+ "learning_rate": 2.09805683059569e-06,
37
+ "num_train_epochs": 5,
38
+ "temperature": 9
39
+ }
40
+ }
run-2/checkpoint-197/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c03531167986b5590a04d8bd7d50baf3ca6f53132698a5ba9216e4386d4bf3c
3
+ size 4792
run-2/checkpoint-197/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ebe907fa2c71e3e43a89d80ee43fe99adc34e72494d59b4f8a29ae3ebf5591db
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c03531167986b5590a04d8bd7d50baf3ca6f53132698a5ba9216e4386d4bf3c
3
  size 4792