Hugging Face's logo

xuancoblab2023
/
tiny-bert-sst2-distilled

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
xuancoblab2023 commited on
Commit
40e2fd5
·
verified ·
1 Parent(s): e310f4f

Training in progress, epoch 1

Browse files
Files changed (42) hide show
  1. logs/events.out.tfevents.1713437232.ec9626078864.14834.15 +2 -2
  2. logs/events.out.tfevents.1713437655.ec9626078864.14834.16 +3 -0
  3. logs/events.out.tfevents.1713437708.ec9626078864.14834.17 +3 -0
  4. logs/events.out.tfevents.1713437761.ec9626078864.14834.18 +3 -0
  5. logs/events.out.tfevents.1713437814.ec9626078864.14834.19 +3 -0
  6. logs/events.out.tfevents.1713437867.ec9626078864.14834.20 +3 -0
  7. logs/events.out.tfevents.1713437920.ec9626078864.14834.21 +3 -0
  8. model.safetensors +1 -1
  9. run-14/checkpoint-4515/config.json +34 -0
  10. run-14/checkpoint-4515/model.safetensors +3 -0
  11. run-14/checkpoint-4515/optimizer.pt +3 -0
  12. run-14/checkpoint-4515/rng_state.pth +3 -0
  13. run-14/checkpoint-4515/scheduler.pt +3 -0
  14. run-14/checkpoint-4515/special_tokens_map.json +7 -0
  15. run-14/checkpoint-4515/tokenizer.json +0 -0
  16. run-14/checkpoint-4515/tokenizer_config.json +57 -0
  17. run-14/checkpoint-4515/trainer_state.json +166 -0
  18. run-14/checkpoint-4515/training_args.bin +3 -0
  19. run-14/checkpoint-4515/vocab.txt +0 -0
  20. run-14/checkpoint-5160/config.json +34 -0
  21. run-14/checkpoint-5160/model.safetensors +3 -0
  22. run-14/checkpoint-5160/optimizer.pt +3 -0
  23. run-14/checkpoint-5160/rng_state.pth +3 -0
  24. run-14/checkpoint-5160/scheduler.pt +3 -0
  25. run-14/checkpoint-5160/special_tokens_map.json +7 -0
  26. run-14/checkpoint-5160/tokenizer.json +0 -0
  27. run-14/checkpoint-5160/tokenizer_config.json +57 -0
  28. run-14/checkpoint-5160/trainer_state.json +186 -0
  29. run-14/checkpoint-5160/training_args.bin +3 -0
  30. run-14/checkpoint-5160/vocab.txt +0 -0
  31. run-20/checkpoint-645/config.json +34 -0
  32. run-20/checkpoint-645/model.safetensors +3 -0
  33. run-20/checkpoint-645/optimizer.pt +3 -0
  34. run-20/checkpoint-645/rng_state.pth +3 -0
  35. run-20/checkpoint-645/scheduler.pt +3 -0
  36. run-20/checkpoint-645/special_tokens_map.json +7 -0
  37. run-20/checkpoint-645/tokenizer.json +0 -0
  38. run-20/checkpoint-645/tokenizer_config.json +57 -0
  39. run-20/checkpoint-645/trainer_state.json +46 -0
  40. run-20/checkpoint-645/training_args.bin +3 -0
  41. run-20/checkpoint-645/vocab.txt +0 -0
  42. training_args.bin +1 -1
logs/events.out.tfevents.1713437232.ec9626078864.14834.15 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:77cd57f26ba2bf71b6339ddc9113f30f55b418c7411a87f1ccb2fc483af216a1
3
- size 6136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2aa3dde0d7f9462b315696745e0ba568b70e655dd9e48cb7df6b62641cec3d1
3
+ size 10870
logs/events.out.tfevents.1713437655.ec9626078864.14834.16 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b68a1c5f6c06db1ec45ed4eb19ddfe75e09625f95c419f420e1305394149238
3
+ size 5407
logs/events.out.tfevents.1713437708.ec9626078864.14834.17 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee4318dc583a874e97790538ebe3c2459c3c9f60f0fbd01a42b1570d5016f488
3
+ size 5406
logs/events.out.tfevents.1713437761.ec9626078864.14834.18 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27022ec6d75625eb8a9d64074e414c2b1c72714568c6dcace652e96a08034777
3
+ size 5406
logs/events.out.tfevents.1713437814.ec9626078864.14834.19 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b269ffa599e015e89f797c236860c8f37b5859699a0c229933712861b3fb3bd7
3
+ size 5407
logs/events.out.tfevents.1713437867.ec9626078864.14834.20 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d525e40a09bb956d023d3ea8ad93d38a292e9654aab05de1140381ea9924d6cf
3
+ size 5406
logs/events.out.tfevents.1713437920.ec9626078864.14834.21 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca44b71382a7788149556d573c1a2bd5a4db505ec2d14c32d0fdca4c1d61d591
3
+ size 5406
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:254d6bc2c35cdaee340edf24d21bdafa1db6398c1bad0dad264664a76309220b
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:440e4e3d69ce39c36a7f0dacd7a850f3842602d50c6d9ccbe441a4dca564738e
3
  size 17549312
run-14/checkpoint-4515/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": "4.39.3",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-14/checkpoint-4515/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4657820488f39b4b9c97357b877e9b1bc51911f4246c1da5eb3d1eee387bc931
3
+ size 17549312
run-14/checkpoint-4515/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6c3659acccb50113e7d8ce70d36247d43be50537bc37f6838665fbc593e8e66
3
+ size 35123898
run-14/checkpoint-4515/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a96e86d3d3d0591475970004e3cc12c4fa77897439ac6269f6ad54a0b10cb2f
3
+ size 14308
run-14/checkpoint-4515/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:495d8cf27c9e38e91351acc0354985b308e39acc95f766dd1c28f9a4c0649f28
3
+ size 1064
run-14/checkpoint-4515/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-14/checkpoint-4515/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-14/checkpoint-4515/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-14/checkpoint-4515/trainer_state.json ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9015122140364482,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-14/checkpoint-4515",
4
+ "epoch": 7.0,
5
+ "eval_steps": 500,
6
+ "global_step": 4515,
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": 1.9803465604782104,
14
+ "learning_rate": 0.00027230837357094026,
15
+ "loss": 0.327,
16
+ "step": 645
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8887165568049632,
21
+ "eval_f1": 0.19154929577464788,
22
+ "eval_loss": 0.3063199520111084,
23
+ "eval_mcc": 0.1990419339488759,
24
+ "eval_precision": 0.48226950354609927,
25
+ "eval_recall": 0.1195079086115993,
26
+ "eval_runtime": 9.9261,
27
+ "eval_samples_per_second": 519.642,
28
+ "eval_steps_per_second": 16.321,
29
+ "step": 645
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 1.0405207872390747,
34
+ "learning_rate": 0.00023340717734652024,
35
+ "loss": 0.3025,
36
+ "step": 1290
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.8914307871267934,
41
+ "eval_f1": 0.14893617021276595,
42
+ "eval_loss": 0.3057989478111267,
43
+ "eval_mcc": 0.18620749231762276,
44
+ "eval_precision": 0.550561797752809,
45
+ "eval_recall": 0.08611599297012303,
46
+ "eval_runtime": 9.9284,
47
+ "eval_samples_per_second": 519.521,
48
+ "eval_steps_per_second": 16.317,
49
+ "step": 1290
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 0.7381914854049683,
54
+ "learning_rate": 0.0001945059811221002,
55
+ "loss": 0.29,
56
+ "step": 1935
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.8951143854207056,
61
+ "eval_f1": 0.16640986132511557,
62
+ "eval_loss": 0.2883821427822113,
63
+ "eval_mcc": 0.2262412458871255,
64
+ "eval_precision": 0.675,
65
+ "eval_recall": 0.09490333919156414,
66
+ "eval_runtime": 9.951,
67
+ "eval_samples_per_second": 518.339,
68
+ "eval_steps_per_second": 16.28,
69
+ "step": 1935
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 2.401355743408203,
74
+ "learning_rate": 0.00015560478489768016,
75
+ "loss": 0.2831,
76
+ "step": 2580
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.8933695230709577,
81
+ "eval_f1": 0.2782152230971129,
82
+ "eval_loss": 0.29702696204185486,
83
+ "eval_mcc": 0.2762227316232168,
84
+ "eval_precision": 0.5492227979274611,
85
+ "eval_recall": 0.18629173989455183,
86
+ "eval_runtime": 9.9249,
87
+ "eval_samples_per_second": 519.701,
88
+ "eval_steps_per_second": 16.323,
89
+ "step": 2580
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "grad_norm": 1.1628026962280273,
94
+ "learning_rate": 0.00011670358867326012,
95
+ "loss": 0.278,
96
+ "step": 3225
97
+ },
98
+ {
99
+ "epoch": 5.0,
100
+ "eval_accuracy": 0.8929817758821249,
101
+ "eval_f1": 0.3284671532846716,
102
+ "eval_loss": 0.27827948331832886,
103
+ "eval_mcc": 0.30685804485965024,
104
+ "eval_precision": 0.5335968379446641,
105
+ "eval_recall": 0.23725834797891038,
106
+ "eval_runtime": 9.9217,
107
+ "eval_samples_per_second": 519.869,
108
+ "eval_steps_per_second": 16.328,
109
+ "step": 3225
110
+ },
111
+ {
112
+ "epoch": 6.0,
113
+ "grad_norm": 1.1073917150497437,
114
+ "learning_rate": 7.780239244884008e-05,
115
+ "loss": 0.272,
116
+ "step": 3870
117
+ },
118
+ {
119
+ "epoch": 6.0,
120
+ "eval_accuracy": 0.8997673516867003,
121
+ "eval_f1": 0.31158455392809586,
122
+ "eval_loss": 0.2726772427558899,
123
+ "eval_mcc": 0.3250995883258456,
124
+ "eval_precision": 0.6428571428571429,
125
+ "eval_recall": 0.2056239015817223,
126
+ "eval_runtime": 9.9563,
127
+ "eval_samples_per_second": 518.063,
128
+ "eval_steps_per_second": 16.271,
129
+ "step": 3870
130
+ },
131
+ {
132
+ "epoch": 7.0,
133
+ "grad_norm": 0.8763220310211182,
134
+ "learning_rate": 3.890119622442004e-05,
135
+ "loss": 0.2672,
136
+ "step": 4515
137
+ },
138
+ {
139
+ "epoch": 7.0,
140
+ "eval_accuracy": 0.9015122140364482,
141
+ "eval_f1": 0.3665835411471322,
142
+ "eval_loss": 0.2725670337677002,
143
+ "eval_mcc": 0.36143858618325836,
144
+ "eval_precision": 0.630901287553648,
145
+ "eval_recall": 0.2583479789103691,
146
+ "eval_runtime": 9.9527,
147
+ "eval_samples_per_second": 518.25,
148
+ "eval_steps_per_second": 16.277,
149
+ "step": 4515
150
+ }
151
+ ],
152
+ "logging_steps": 500,
153
+ "max_steps": 5160,
154
+ "num_input_tokens_seen": 0,
155
+ "num_train_epochs": 8,
156
+ "save_steps": 500,
157
+ "total_flos": 11108597728200.0,
158
+ "train_batch_size": 32,
159
+ "trial_name": null,
160
+ "trial_params": {
161
+ "alpha": 0.9932188265495786,
162
+ "learning_rate": 0.0003112095697953603,
163
+ "num_train_epochs": 8,
164
+ "temperature": 21
165
+ }
166
+ }
run-14/checkpoint-4515/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:477fc5e0a8a4f66ce89d996de5d48a66ce5157517c69b38a9deeba1e7b63e8ee
3
+ size 4984
run-14/checkpoint-4515/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-14/checkpoint-5160/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": "4.39.3",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-14/checkpoint-5160/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bb0902cd3f54ca0d1c29ac8630c9581cb5c8a8655207de81a7dc93c8196cf22
3
+ size 17549312
run-14/checkpoint-5160/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:703615df5523baa56b2133221c07b6bd5d8d60b875c18a11058cf29fd2d3c428
3
+ size 35123898
run-14/checkpoint-5160/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ed5a1bcacb8f805a3e185fc051790dcd56ca255fa1cf31728dea9662b0a4562
3
+ size 14308
run-14/checkpoint-5160/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3890a0a26aa43cc95b9b375816bc446d72d1bcfe4d5d7504d280aa8cc53ea89
3
+ size 1064
run-14/checkpoint-5160/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-14/checkpoint-5160/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-14/checkpoint-5160/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-14/checkpoint-5160/trainer_state.json ADDED
@@ -0,0 +1,186 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9034509499806126,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-14/checkpoint-5160",
4
+ "epoch": 8.0,
5
+ "eval_steps": 500,
6
+ "global_step": 5160,
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": 1.9803465604782104,
14
+ "learning_rate": 0.00027230837357094026,
15
+ "loss": 0.327,
16
+ "step": 645
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8887165568049632,
21
+ "eval_f1": 0.19154929577464788,
22
+ "eval_loss": 0.3063199520111084,
23
+ "eval_mcc": 0.1990419339488759,
24
+ "eval_precision": 0.48226950354609927,
25
+ "eval_recall": 0.1195079086115993,
26
+ "eval_runtime": 9.9261,
27
+ "eval_samples_per_second": 519.642,
28
+ "eval_steps_per_second": 16.321,
29
+ "step": 645
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 1.0405207872390747,
34
+ "learning_rate": 0.00023340717734652024,
35
+ "loss": 0.3025,
36
+ "step": 1290
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.8914307871267934,
41
+ "eval_f1": 0.14893617021276595,
42
+ "eval_loss": 0.3057989478111267,
43
+ "eval_mcc": 0.18620749231762276,
44
+ "eval_precision": 0.550561797752809,
45
+ "eval_recall": 0.08611599297012303,
46
+ "eval_runtime": 9.9284,
47
+ "eval_samples_per_second": 519.521,
48
+ "eval_steps_per_second": 16.317,
49
+ "step": 1290
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 0.7381914854049683,
54
+ "learning_rate": 0.0001945059811221002,
55
+ "loss": 0.29,
56
+ "step": 1935
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.8951143854207056,
61
+ "eval_f1": 0.16640986132511557,
62
+ "eval_loss": 0.2883821427822113,
63
+ "eval_mcc": 0.2262412458871255,
64
+ "eval_precision": 0.675,
65
+ "eval_recall": 0.09490333919156414,
66
+ "eval_runtime": 9.951,
67
+ "eval_samples_per_second": 518.339,
68
+ "eval_steps_per_second": 16.28,
69
+ "step": 1935
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 2.401355743408203,
74
+ "learning_rate": 0.00015560478489768016,
75
+ "loss": 0.2831,
76
+ "step": 2580
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.8933695230709577,
81
+ "eval_f1": 0.2782152230971129,
82
+ "eval_loss": 0.29702696204185486,
83
+ "eval_mcc": 0.2762227316232168,
84
+ "eval_precision": 0.5492227979274611,
85
+ "eval_recall": 0.18629173989455183,
86
+ "eval_runtime": 9.9249,
87
+ "eval_samples_per_second": 519.701,
88
+ "eval_steps_per_second": 16.323,
89
+ "step": 2580
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "grad_norm": 1.1628026962280273,
94
+ "learning_rate": 0.00011670358867326012,
95
+ "loss": 0.278,
96
+ "step": 3225
97
+ },
98
+ {
99
+ "epoch": 5.0,
100
+ "eval_accuracy": 0.8929817758821249,
101
+ "eval_f1": 0.3284671532846716,
102
+ "eval_loss": 0.27827948331832886,
103
+ "eval_mcc": 0.30685804485965024,
104
+ "eval_precision": 0.5335968379446641,
105
+ "eval_recall": 0.23725834797891038,
106
+ "eval_runtime": 9.9217,
107
+ "eval_samples_per_second": 519.869,
108
+ "eval_steps_per_second": 16.328,
109
+ "step": 3225
110
+ },
111
+ {
112
+ "epoch": 6.0,
113
+ "grad_norm": 1.1073917150497437,
114
+ "learning_rate": 7.780239244884008e-05,
115
+ "loss": 0.272,
116
+ "step": 3870
117
+ },
118
+ {
119
+ "epoch": 6.0,
120
+ "eval_accuracy": 0.8997673516867003,
121
+ "eval_f1": 0.31158455392809586,
122
+ "eval_loss": 0.2726772427558899,
123
+ "eval_mcc": 0.3250995883258456,
124
+ "eval_precision": 0.6428571428571429,
125
+ "eval_recall": 0.2056239015817223,
126
+ "eval_runtime": 9.9563,
127
+ "eval_samples_per_second": 518.063,
128
+ "eval_steps_per_second": 16.271,
129
+ "step": 3870
130
+ },
131
+ {
132
+ "epoch": 7.0,
133
+ "grad_norm": 0.8763220310211182,
134
+ "learning_rate": 3.890119622442004e-05,
135
+ "loss": 0.2672,
136
+ "step": 4515
137
+ },
138
+ {
139
+ "epoch": 7.0,
140
+ "eval_accuracy": 0.9015122140364482,
141
+ "eval_f1": 0.3665835411471322,
142
+ "eval_loss": 0.2725670337677002,
143
+ "eval_mcc": 0.36143858618325836,
144
+ "eval_precision": 0.630901287553648,
145
+ "eval_recall": 0.2583479789103691,
146
+ "eval_runtime": 9.9527,
147
+ "eval_samples_per_second": 518.25,
148
+ "eval_steps_per_second": 16.277,
149
+ "step": 4515
150
+ },
151
+ {
152
+ "epoch": 8.0,
153
+ "grad_norm": 3.0882771015167236,
154
+ "learning_rate": 0.0,
155
+ "loss": 0.2607,
156
+ "step": 5160
157
+ },
158
+ {
159
+ "epoch": 8.0,
160
+ "eval_accuracy": 0.9034509499806126,
161
+ "eval_f1": 0.36153846153846153,
162
+ "eval_loss": 0.2719564735889435,
163
+ "eval_mcc": 0.36780532061343757,
164
+ "eval_precision": 0.6682464454976303,
165
+ "eval_recall": 0.2478031634446397,
166
+ "eval_runtime": 9.9867,
167
+ "eval_samples_per_second": 516.488,
168
+ "eval_steps_per_second": 16.222,
169
+ "step": 5160
170
+ }
171
+ ],
172
+ "logging_steps": 500,
173
+ "max_steps": 5160,
174
+ "num_input_tokens_seen": 0,
175
+ "num_train_epochs": 8,
176
+ "save_steps": 500,
177
+ "total_flos": 12695540260800.0,
178
+ "train_batch_size": 32,
179
+ "trial_name": null,
180
+ "trial_params": {
181
+ "alpha": 0.9932188265495786,
182
+ "learning_rate": 0.0003112095697953603,
183
+ "num_train_epochs": 8,
184
+ "temperature": 21
185
+ }
186
+ }
run-14/checkpoint-5160/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:477fc5e0a8a4f66ce89d996de5d48a66ce5157517c69b38a9deeba1e7b63e8ee
3
+ size 4984
run-14/checkpoint-5160/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-20/checkpoint-645/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": "4.39.3",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-20/checkpoint-645/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:440e4e3d69ce39c36a7f0dacd7a850f3842602d50c6d9ccbe441a4dca564738e
3
+ size 17549312
run-20/checkpoint-645/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fade4289d48717ab4d12a794ff2142d984057ae013fa139a2fdcd65102edbe2
3
+ size 35123898
run-20/checkpoint-645/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f64cda8af0c2d214cf65bdf171fde38f18025a5a08f9a451c61fdf726867d7c2
3
+ size 14308
run-20/checkpoint-645/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48cbbd60a33e752d822c1848edac457dc6f56aefd2e413ac4b272b2d0d47bce5
3
+ size 1064
run-20/checkpoint-645/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-20/checkpoint-645/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-20/checkpoint-645/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-20/checkpoint-645/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8889104303993796,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-20/checkpoint-645",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 645,
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": 1.6259269714355469,
14
+ "learning_rate": 0.0003431069228198171,
15
+ "loss": 0.3055,
16
+ "step": 645
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8889104303993796,
21
+ "eval_f1": 0.19409282700421943,
22
+ "eval_loss": 0.2940736413002014,
23
+ "eval_mcc": 0.20172457395808635,
24
+ "eval_precision": 0.4859154929577465,
25
+ "eval_recall": 0.12126537785588752,
26
+ "eval_runtime": 9.9362,
27
+ "eval_samples_per_second": 519.111,
28
+ "eval_steps_per_second": 16.304,
29
+ "step": 645
30
+ }
31
+ ],
32
+ "logging_steps": 500,
33
+ "max_steps": 4515,
34
+ "num_input_tokens_seen": 0,
35
+ "num_train_epochs": 7,
36
+ "save_steps": 500,
37
+ "total_flos": 1586942532600.0,
38
+ "train_batch_size": 32,
39
+ "trial_name": null,
40
+ "trial_params": {
41
+ "alpha": 0.8743805278290786,
42
+ "learning_rate": 0.0004002914099564533,
43
+ "num_train_epochs": 7,
44
+ "temperature": 27
45
+ }
46
+ }
run-20/checkpoint-645/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbe36ec58db211b259b67da56dd68bab1173e0379eb4df2b16394348319aa391
3
+ size 4984
run-20/checkpoint-645/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 sha256:477fc5e0a8a4f66ce89d996de5d48a66ce5157517c69b38a9deeba1e7b63e8ee
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbe36ec58db211b259b67da56dd68bab1173e0379eb4df2b16394348319aa391
3
  size 4984