Hugging Face's logo

aravindhank
/
tiny-bert-sst2-distilled

Text Classification
Transformers
TensorBoard
Safetensors
bert
text-embeddings-inference
Model card Files
xet
Metrics Community
aravindhank commited on
Commit
cdf0c3d
·
verified ·
1 Parent(s): d1223cf

Training in progress, epoch 1

Browse files
Files changed (37) hide show
  1. logs/events.out.tfevents.1713970842.a9ae8da52b57.4950.1 +2 -2
  2. logs/events.out.tfevents.1713972412.a9ae8da52b57.4950.2 +3 -0
  3. model.safetensors +1 -1
  4. run-0/checkpoint-3689/config.json +34 -0
  5. run-0/checkpoint-3689/model.safetensors +3 -0
  6. run-0/checkpoint-3689/optimizer.pt +3 -0
  7. run-0/checkpoint-3689/rng_state.pth +3 -0
  8. run-0/checkpoint-3689/scheduler.pt +3 -0
  9. run-0/checkpoint-3689/special_tokens_map.json +7 -0
  10. run-0/checkpoint-3689/tokenizer.json +0 -0
  11. run-0/checkpoint-3689/tokenizer_config.json +57 -0
  12. run-0/checkpoint-3689/trainer_state.json +138 -0
  13. run-0/checkpoint-3689/training_args.bin +3 -0
  14. run-0/checkpoint-3689/vocab.txt +0 -0
  15. run-0/checkpoint-4216/config.json +34 -0
  16. run-0/checkpoint-4216/model.safetensors +3 -0
  17. run-0/checkpoint-4216/optimizer.pt +3 -0
  18. run-0/checkpoint-4216/rng_state.pth +3 -0
  19. run-0/checkpoint-4216/scheduler.pt +3 -0
  20. run-0/checkpoint-4216/special_tokens_map.json +7 -0
  21. run-0/checkpoint-4216/tokenizer.json +0 -0
  22. run-0/checkpoint-4216/tokenizer_config.json +57 -0
  23. run-0/checkpoint-4216/trainer_state.json +154 -0
  24. run-0/checkpoint-4216/training_args.bin +3 -0
  25. run-0/checkpoint-4216/vocab.txt +0 -0
  26. run-1/checkpoint-527/config.json +34 -0
  27. run-1/checkpoint-527/model.safetensors +3 -0
  28. run-1/checkpoint-527/optimizer.pt +3 -0
  29. run-1/checkpoint-527/rng_state.pth +3 -0
  30. run-1/checkpoint-527/scheduler.pt +3 -0
  31. run-1/checkpoint-527/special_tokens_map.json +7 -0
  32. run-1/checkpoint-527/tokenizer.json +0 -0
  33. run-1/checkpoint-527/tokenizer_config.json +57 -0
  34. run-1/checkpoint-527/trainer_state.json +42 -0
  35. run-1/checkpoint-527/training_args.bin +3 -0
  36. run-1/checkpoint-527/vocab.txt +0 -0
  37. training_args.bin +1 -1
logs/events.out.tfevents.1713970842.a9ae8da52b57.4950.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25a958b71d2d16cc3e78da2740a530a4024544c100a928b553545c73c24c56cf
3
- size 5822
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83f00e3dd4cab71124258bb32f5c87e7e538adbedc60a1d7d676e1e3d7a3ad67
3
+ size 9380
logs/events.out.tfevents.1713972412.a9ae8da52b57.4950.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:515aaa5d5b808698e8d7f876d48e5bf223cc149fdc0d63f24cefa9d7006364f8
3
+ size 5287
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef8a53367281448355780b7b0fdefb481ca9d156d7d13aa415fe1c61860e1f26
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc24eccafea43a9890bdd4d965b6c0abc379519d1f79ffdc746d7439ac8fb2fc
3
  size 17549312
run-0/checkpoint-3689/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
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": 128,
11
+ "id2label": {
12
+ "0": "negative",
13
+ "1": "positive"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 512,
17
+ "label2id": {
18
+ "negative": "0",
19
+ "positive": "1"
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 2,
25
+ "num_hidden_layers": 2,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.40.1",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-0/checkpoint-3689/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b9991c8318e0500e923ff73ab15d77890f81ce9a1c8a5155bef2b550cc5c7b8
3
+ size 17549312
run-0/checkpoint-3689/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c19a443faed29e9f7c624c2ad9ff4db2dda5dd8ba4b1231aa360ccf3d87dd45
3
+ size 35123898
run-0/checkpoint-3689/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d13a9fca2ec73f276977f9543d3bb73304bb3a986bf0809d2c7305e26c18047
3
+ size 14308
run-0/checkpoint-3689/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edbb3dac49bfeec292c5bd637c4453b104a115375c5a01b41b9b1e66caafb239
3
+ size 1064
run-0/checkpoint-3689/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-0/checkpoint-3689/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-3689/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-0/checkpoint-3689/trainer_state.json ADDED
@@ -0,0 +1,138 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7844036697247706,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-2635",
4
+ "epoch": 7.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3689,
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
+ "grad_norm": 17.1326904296875,
14
+ "learning_rate": 9.513173921403958e-06,
15
+ "loss": 3.6378,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.6915137614678899,
21
+ "eval_loss": 3.044344902038574,
22
+ "eval_runtime": 2.6844,
23
+ "eval_samples_per_second": 324.846,
24
+ "eval_steps_per_second": 2.608,
25
+ "step": 527
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "grad_norm": Infinity,
30
+ "learning_rate": 8.156727870263139e-06,
31
+ "loss": 2.9201,
32
+ "step": 1054
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.7763761467889908,
37
+ "eval_loss": 2.3391239643096924,
38
+ "eval_runtime": 2.6931,
39
+ "eval_samples_per_second": 323.787,
40
+ "eval_steps_per_second": 2.599,
41
+ "step": 1054
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "grad_norm": 45.30732345581055,
46
+ "learning_rate": 6.797703024348287e-06,
47
+ "loss": 2.3619,
48
+ "step": 1581
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.7752293577981652,
53
+ "eval_loss": 2.095879554748535,
54
+ "eval_runtime": 2.7528,
55
+ "eval_samples_per_second": 316.768,
56
+ "eval_steps_per_second": 2.543,
57
+ "step": 1581
58
+ },
59
+ {
60
+ "epoch": 4.0,
61
+ "grad_norm": 42.87710952758789,
62
+ "learning_rate": 5.4386781784334364e-06,
63
+ "loss": 2.0658,
64
+ "step": 2108
65
+ },
66
+ {
67
+ "epoch": 4.0,
68
+ "eval_accuracy": 0.7798165137614679,
69
+ "eval_loss": 1.9894497394561768,
70
+ "eval_runtime": 2.6956,
71
+ "eval_samples_per_second": 323.487,
72
+ "eval_steps_per_second": 2.597,
73
+ "step": 2108
74
+ },
75
+ {
76
+ "epoch": 5.0,
77
+ "grad_norm": 24.316022872924805,
78
+ "learning_rate": 4.0796533325185855e-06,
79
+ "loss": 1.9068,
80
+ "step": 2635
81
+ },
82
+ {
83
+ "epoch": 5.0,
84
+ "eval_accuracy": 0.7844036697247706,
85
+ "eval_loss": 1.9175504446029663,
86
+ "eval_runtime": 2.6587,
87
+ "eval_samples_per_second": 327.984,
88
+ "eval_steps_per_second": 2.633,
89
+ "step": 2635
90
+ },
91
+ {
92
+ "epoch": 6.0,
93
+ "grad_norm": 22.026918411254883,
94
+ "learning_rate": 2.723207281377766e-06,
95
+ "loss": 1.7844,
96
+ "step": 3162
97
+ },
98
+ {
99
+ "epoch": 6.0,
100
+ "eval_accuracy": 0.7844036697247706,
101
+ "eval_loss": 1.8753291368484497,
102
+ "eval_runtime": 2.7064,
103
+ "eval_samples_per_second": 322.195,
104
+ "eval_steps_per_second": 2.586,
105
+ "step": 3162
106
+ },
107
+ {
108
+ "epoch": 7.0,
109
+ "grad_norm": 28.347148895263672,
110
+ "learning_rate": 1.3641824354629153e-06,
111
+ "loss": 1.7245,
112
+ "step": 3689
113
+ },
114
+ {
115
+ "epoch": 7.0,
116
+ "eval_accuracy": 0.7844036697247706,
117
+ "eval_loss": 1.8515244722366333,
118
+ "eval_runtime": 2.7066,
119
+ "eval_samples_per_second": 322.171,
120
+ "eval_steps_per_second": 2.586,
121
+ "step": 3689
122
+ }
123
+ ],
124
+ "logging_steps": 500,
125
+ "max_steps": 4216,
126
+ "num_input_tokens_seen": 0,
127
+ "num_train_epochs": 8,
128
+ "save_steps": 500,
129
+ "total_flos": 56628612372420.0,
130
+ "train_batch_size": 128,
131
+ "trial_name": null,
132
+ "trial_params": {
133
+ "alpha": 0.283430275721788,
134
+ "learning_rate": 1.0872198767318809e-05,
135
+ "num_train_epochs": 8,
136
+ "temperature": 13
137
+ }
138
+ }
run-0/checkpoint-3689/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:685c5ca76e50efcbdad73bed43aea4bc7cc0fe066757f948d6ec7618865f3672
3
+ size 5048
run-0/checkpoint-3689/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-4216/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
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": 128,
11
+ "id2label": {
12
+ "0": "negative",
13
+ "1": "positive"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 512,
17
+ "label2id": {
18
+ "negative": "0",
19
+ "positive": "1"
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 2,
25
+ "num_hidden_layers": 2,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.40.1",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-0/checkpoint-4216/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c4f11014b1492f4244c5b7ad50dd95e62e9d03f68be73bfd5adb5311ce44534
3
+ size 17549312
run-0/checkpoint-4216/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b517a3a8eb743a1e2217af964879dc99acd7c4e2c85599e63b232c715cf9fca
3
+ size 35123898
run-0/checkpoint-4216/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a2719006b61f28d7e37d68afe179a1c4b2eedc673365947492e106cb79f976c
3
+ size 14308
run-0/checkpoint-4216/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c45d3a74cd3e8c2ba393c07a93b0979e460b8019a3592fab539522d72eb31561
3
+ size 1064
run-0/checkpoint-4216/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-0/checkpoint-4216/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-4216/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-0/checkpoint-4216/trainer_state.json ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7878440366972477,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-4216",
4
+ "epoch": 8.0,
5
+ "eval_steps": 500,
6
+ "global_step": 4216,
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
+ "grad_norm": 17.1326904296875,
14
+ "learning_rate": 9.513173921403958e-06,
15
+ "loss": 3.6378,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.6915137614678899,
21
+ "eval_loss": 3.044344902038574,
22
+ "eval_runtime": 2.6844,
23
+ "eval_samples_per_second": 324.846,
24
+ "eval_steps_per_second": 2.608,
25
+ "step": 527
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "grad_norm": Infinity,
30
+ "learning_rate": 8.156727870263139e-06,
31
+ "loss": 2.9201,
32
+ "step": 1054
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.7763761467889908,
37
+ "eval_loss": 2.3391239643096924,
38
+ "eval_runtime": 2.6931,
39
+ "eval_samples_per_second": 323.787,
40
+ "eval_steps_per_second": 2.599,
41
+ "step": 1054
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "grad_norm": 45.30732345581055,
46
+ "learning_rate": 6.797703024348287e-06,
47
+ "loss": 2.3619,
48
+ "step": 1581
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.7752293577981652,
53
+ "eval_loss": 2.095879554748535,
54
+ "eval_runtime": 2.7528,
55
+ "eval_samples_per_second": 316.768,
56
+ "eval_steps_per_second": 2.543,
57
+ "step": 1581
58
+ },
59
+ {
60
+ "epoch": 4.0,
61
+ "grad_norm": 42.87710952758789,
62
+ "learning_rate": 5.4386781784334364e-06,
63
+ "loss": 2.0658,
64
+ "step": 2108
65
+ },
66
+ {
67
+ "epoch": 4.0,
68
+ "eval_accuracy": 0.7798165137614679,
69
+ "eval_loss": 1.9894497394561768,
70
+ "eval_runtime": 2.6956,
71
+ "eval_samples_per_second": 323.487,
72
+ "eval_steps_per_second": 2.597,
73
+ "step": 2108
74
+ },
75
+ {
76
+ "epoch": 5.0,
77
+ "grad_norm": 24.316022872924805,
78
+ "learning_rate": 4.0796533325185855e-06,
79
+ "loss": 1.9068,
80
+ "step": 2635
81
+ },
82
+ {
83
+ "epoch": 5.0,
84
+ "eval_accuracy": 0.7844036697247706,
85
+ "eval_loss": 1.9175504446029663,
86
+ "eval_runtime": 2.6587,
87
+ "eval_samples_per_second": 327.984,
88
+ "eval_steps_per_second": 2.633,
89
+ "step": 2635
90
+ },
91
+ {
92
+ "epoch": 6.0,
93
+ "grad_norm": 22.026918411254883,
94
+ "learning_rate": 2.723207281377766e-06,
95
+ "loss": 1.7844,
96
+ "step": 3162
97
+ },
98
+ {
99
+ "epoch": 6.0,
100
+ "eval_accuracy": 0.7844036697247706,
101
+ "eval_loss": 1.8753291368484497,
102
+ "eval_runtime": 2.7064,
103
+ "eval_samples_per_second": 322.195,
104
+ "eval_steps_per_second": 2.586,
105
+ "step": 3162
106
+ },
107
+ {
108
+ "epoch": 7.0,
109
+ "grad_norm": 28.347148895263672,
110
+ "learning_rate": 1.3641824354629153e-06,
111
+ "loss": 1.7245,
112
+ "step": 3689
113
+ },
114
+ {
115
+ "epoch": 7.0,
116
+ "eval_accuracy": 0.7844036697247706,
117
+ "eval_loss": 1.8515244722366333,
118
+ "eval_runtime": 2.7066,
119
+ "eval_samples_per_second": 322.171,
120
+ "eval_steps_per_second": 2.586,
121
+ "step": 3689
122
+ },
123
+ {
124
+ "epoch": 8.0,
125
+ "grad_norm": Infinity,
126
+ "learning_rate": 7.736384322095927e-09,
127
+ "loss": 1.705,
128
+ "step": 4216
129
+ },
130
+ {
131
+ "epoch": 8.0,
132
+ "eval_accuracy": 0.7878440366972477,
133
+ "eval_loss": 1.8409373760223389,
134
+ "eval_runtime": 2.6794,
135
+ "eval_samples_per_second": 325.446,
136
+ "eval_steps_per_second": 2.613,
137
+ "step": 4216
138
+ }
139
+ ],
140
+ "logging_steps": 500,
141
+ "max_steps": 4216,
142
+ "num_input_tokens_seen": 0,
143
+ "num_train_epochs": 8,
144
+ "save_steps": 500,
145
+ "total_flos": 64687167744780.0,
146
+ "train_batch_size": 128,
147
+ "trial_name": null,
148
+ "trial_params": {
149
+ "alpha": 0.283430275721788,
150
+ "learning_rate": 1.0872198767318809e-05,
151
+ "num_train_epochs": 8,
152
+ "temperature": 13
153
+ }
154
+ }
run-0/checkpoint-4216/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:685c5ca76e50efcbdad73bed43aea4bc7cc0fe066757f948d6ec7618865f3672
3
+ size 5048
run-0/checkpoint-4216/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-527/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
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": 128,
11
+ "id2label": {
12
+ "0": "negative",
13
+ "1": "positive"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 512,
17
+ "label2id": {
18
+ "negative": "0",
19
+ "positive": "1"
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 2,
25
+ "num_hidden_layers": 2,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.40.1",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-1/checkpoint-527/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc24eccafea43a9890bdd4d965b6c0abc379519d1f79ffdc746d7439ac8fb2fc
3
+ size 17549312
run-1/checkpoint-527/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d384bbf3d41f0e47458ba9f69d17326e12d83103bd9281bee133584b1779283
3
+ size 35123898
run-1/checkpoint-527/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a32291cb0c1329fbb9596dcc47c5d9b0d1f71ecc09dad1791e0b193314659e4
3
+ size 14308
run-1/checkpoint-527/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12a6f3dd92736c7f9195c374b40969f60dded8b46a5e2be99124f35680f33a73
3
+ size 1064
run-1/checkpoint-527/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-527/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-527/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-527/trainer_state.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8360091743119266,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-527",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 527,
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
+ "grad_norm": 22.49123764038086,
14
+ "learning_rate": 0.0002780733463240362,
15
+ "loss": 1.7444,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8360091743119266,
21
+ "eval_loss": 1.752740740776062,
22
+ "eval_runtime": 2.7351,
23
+ "eval_samples_per_second": 318.815,
24
+ "eval_steps_per_second": 2.559,
25
+ "step": 527
26
+ }
27
+ ],
28
+ "logging_steps": 500,
29
+ "max_steps": 2635,
30
+ "num_input_tokens_seen": 0,
31
+ "num_train_epochs": 5,
32
+ "save_steps": 500,
33
+ "total_flos": 8057768762220.0,
34
+ "train_batch_size": 128,
35
+ "trial_name": null,
36
+ "trial_params": {
37
+ "alpha": 0.08970692378937972,
38
+ "learning_rate": 0.0003475916829050453,
39
+ "num_train_epochs": 5,
40
+ "temperature": 30
41
+ }
42
+ }
run-1/checkpoint-527/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2608572d74b285a65dbc7ad54bc17bf582a54f334d1b1780f3914acbfa4a4cbe
3
+ size 5048
run-1/checkpoint-527/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 sha256:685c5ca76e50efcbdad73bed43aea4bc7cc0fe066757f948d6ec7618865f3672
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2608572d74b285a65dbc7ad54bc17bf582a54f334d1b1780f3914acbfa4a4cbe
3
  size 5048