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
428b4ec
·
verified ·
1 Parent(s): 23026b7

Training in progress, epoch 1

Browse files
Files changed (38) hide show
  1. logs/events.out.tfevents.1709626841.404ecd1cf399.26000.53 +2 -2
  2. logs/events.out.tfevents.1709627322.404ecd1cf399.26000.54 +3 -0
  3. logs/events.out.tfevents.1709627440.404ecd1cf399.26000.55 +3 -0
  4. model.safetensors +1 -1
  5. run-47/checkpoint-288/config.json +34 -0
  6. run-47/checkpoint-288/model.safetensors +3 -0
  7. run-47/checkpoint-288/optimizer.pt +3 -0
  8. run-47/checkpoint-288/rng_state.pth +3 -0
  9. run-47/checkpoint-288/scheduler.pt +3 -0
  10. run-47/checkpoint-288/special_tokens_map.json +7 -0
  11. run-47/checkpoint-288/tokenizer.json +0 -0
  12. run-47/checkpoint-288/tokenizer_config.json +57 -0
  13. run-47/checkpoint-288/trainer_state.json +83 -0
  14. run-47/checkpoint-288/training_args.bin +3 -0
  15. run-47/checkpoint-288/vocab.txt +0 -0
  16. run-47/checkpoint-384/config.json +34 -0
  17. run-47/checkpoint-384/model.safetensors +3 -0
  18. run-47/checkpoint-384/optimizer.pt +3 -0
  19. run-47/checkpoint-384/rng_state.pth +3 -0
  20. run-47/checkpoint-384/scheduler.pt +3 -0
  21. run-47/checkpoint-384/special_tokens_map.json +7 -0
  22. run-47/checkpoint-384/tokenizer.json +0 -0
  23. run-47/checkpoint-384/tokenizer_config.json +57 -0
  24. run-47/checkpoint-384/trainer_state.json +102 -0
  25. run-47/checkpoint-384/training_args.bin +3 -0
  26. run-47/checkpoint-384/vocab.txt +0 -0
  27. run-49/checkpoint-96/config.json +34 -0
  28. run-49/checkpoint-96/model.safetensors +3 -0
  29. run-49/checkpoint-96/optimizer.pt +3 -0
  30. run-49/checkpoint-96/rng_state.pth +3 -0
  31. run-49/checkpoint-96/scheduler.pt +3 -0
  32. run-49/checkpoint-96/special_tokens_map.json +7 -0
  33. run-49/checkpoint-96/tokenizer.json +0 -0
  34. run-49/checkpoint-96/tokenizer_config.json +57 -0
  35. run-49/checkpoint-96/trainer_state.json +45 -0
  36. run-49/checkpoint-96/training_args.bin +3 -0
  37. run-49/checkpoint-96/vocab.txt +0 -0
  38. training_args.bin +1 -1
logs/events.out.tfevents.1709626841.404ecd1cf399.26000.53 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e0776857fc0e1603478abb2492058c9859225ce77ac20e40986366cef842db9
3
- size 5998
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d03712e17097bbd01f355310690136a7222044ef0aa73213d9799fbc8902c618
3
+ size 7718
logs/events.out.tfevents.1709627322.404ecd1cf399.26000.54 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2cd2b9a209a4d684fd2b5284a1a54714936b04e41fa0be639f7c86ba51dae97
3
+ size 5314
logs/events.out.tfevents.1709627440.404ecd1cf399.26000.55 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92bb8ff35c02c0322c04731a1ff51bc7eab4acac97005594ef0779c5ed2a092a
3
+ size 5314
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b650efa919f6a4973bb634fc29f097f7b8f22afbce00a3634222130b8799584e
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cdc0628accb17e8607787c5836da22761db6d6b5b5d5adc52400cec7227d8df
3
  size 17549312
run-47/checkpoint-288/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": "4.38.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-47/checkpoint-288/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8bdb06cc91abb27f8c94cd4374ed2d0c555041365954d6b861ce74b4604cc96
3
+ size 17549312
run-47/checkpoint-288/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76d4d6cbf796eb08ad8041196da4ad09ad550ccabe929d0cf24a405b86729654
3
+ size 35122746
run-47/checkpoint-288/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba3c2bb1d96a39a28ae1b66f234e351e3c13c700fc97347efd6308798b151790
3
+ size 14054
run-47/checkpoint-288/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:828bd68647525c508f22ebaec19840a51f6b75e618f14fd4b2e3736d361ebc2e
3
+ size 1064
run-47/checkpoint-288/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-47/checkpoint-288/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-47/checkpoint-288/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-47/checkpoint-288/trainer_state.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8297455968688845,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-47/checkpoint-192",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 288,
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": 10.090946197509766,
14
+ "learning_rate": 0.0002726931435690813,
15
+ "loss": 0.5743,
16
+ "step": 96
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7964774951076321,
21
+ "eval_f1": 0.8188153310104529,
22
+ "eval_loss": 0.4561440944671631,
23
+ "eval_precision": 0.7378335949764521,
24
+ "eval_recall": 0.9197651663405088,
25
+ "eval_runtime": 30.8585,
26
+ "eval_samples_per_second": 33.119,
27
+ "eval_steps_per_second": 1.037,
28
+ "step": 96
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 7.258547306060791,
33
+ "learning_rate": 0.00018179542904605417,
34
+ "loss": 0.4449,
35
+ "step": 192
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.8297455968688845,
40
+ "eval_f1": 0.8406593406593407,
41
+ "eval_loss": 0.4051818251609802,
42
+ "eval_precision": 0.7900172117039587,
43
+ "eval_recall": 0.898238747553816,
44
+ "eval_runtime": 31.0429,
45
+ "eval_samples_per_second": 32.922,
46
+ "eval_steps_per_second": 1.031,
47
+ "step": 192
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 5.823967933654785,
52
+ "learning_rate": 9.089771452302708e-05,
53
+ "loss": 0.4122,
54
+ "step": 288
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.8268101761252447,
59
+ "eval_f1": 0.8350419384902142,
60
+ "eval_loss": 0.42232340574264526,
61
+ "eval_precision": 0.797153024911032,
62
+ "eval_recall": 0.8767123287671232,
63
+ "eval_runtime": 32.2891,
64
+ "eval_samples_per_second": 31.652,
65
+ "eval_steps_per_second": 0.991,
66
+ "step": 288
67
+ }
68
+ ],
69
+ "logging_steps": 500,
70
+ "max_steps": 384,
71
+ "num_input_tokens_seen": 0,
72
+ "num_train_epochs": 4,
73
+ "save_steps": 500,
74
+ "total_flos": 707085591840.0,
75
+ "train_batch_size": 32,
76
+ "trial_name": null,
77
+ "trial_params": {
78
+ "alpha": 0.999132297568699,
79
+ "learning_rate": 0.00036359085809210834,
80
+ "num_train_epochs": 4,
81
+ "temperature": 14
82
+ }
83
+ }
run-47/checkpoint-288/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e52d4ef52e4ae3e7583492431957732ea2f0822ace3819ef8d07c56bc154648
3
+ size 4920
run-47/checkpoint-288/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-47/checkpoint-384/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": "4.38.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-47/checkpoint-384/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82100fed6bd2642f135e801c31b109caca2e2570da5c582b61b23bb72ee25390
3
+ size 17549312
run-47/checkpoint-384/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a909a1e60eaa356e7ce67bb12f76f859e4797bd0dfe643084fb8c9456c70af9
3
+ size 35122746
run-47/checkpoint-384/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45b1fc07ed8b121716021ec87c686f1cd9c3b89c82ea08a6a0792d47a39077c9
3
+ size 14054
run-47/checkpoint-384/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f654e145bba8373090998826fc6d18f469506f4221600f36a0f1570e2ea47b3
3
+ size 1064
run-47/checkpoint-384/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-47/checkpoint-384/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-47/checkpoint-384/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-47/checkpoint-384/trainer_state.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8356164383561644,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-47/checkpoint-384",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 384,
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": 10.090946197509766,
14
+ "learning_rate": 0.0002726931435690813,
15
+ "loss": 0.5743,
16
+ "step": 96
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7964774951076321,
21
+ "eval_f1": 0.8188153310104529,
22
+ "eval_loss": 0.4561440944671631,
23
+ "eval_precision": 0.7378335949764521,
24
+ "eval_recall": 0.9197651663405088,
25
+ "eval_runtime": 30.8585,
26
+ "eval_samples_per_second": 33.119,
27
+ "eval_steps_per_second": 1.037,
28
+ "step": 96
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 7.258547306060791,
33
+ "learning_rate": 0.00018179542904605417,
34
+ "loss": 0.4449,
35
+ "step": 192
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.8297455968688845,
40
+ "eval_f1": 0.8406593406593407,
41
+ "eval_loss": 0.4051818251609802,
42
+ "eval_precision": 0.7900172117039587,
43
+ "eval_recall": 0.898238747553816,
44
+ "eval_runtime": 31.0429,
45
+ "eval_samples_per_second": 32.922,
46
+ "eval_steps_per_second": 1.031,
47
+ "step": 192
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 5.823967933654785,
52
+ "learning_rate": 9.089771452302708e-05,
53
+ "loss": 0.4122,
54
+ "step": 288
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.8268101761252447,
59
+ "eval_f1": 0.8350419384902142,
60
+ "eval_loss": 0.42232340574264526,
61
+ "eval_precision": 0.797153024911032,
62
+ "eval_recall": 0.8767123287671232,
63
+ "eval_runtime": 32.2891,
64
+ "eval_samples_per_second": 31.652,
65
+ "eval_steps_per_second": 0.991,
66
+ "step": 288
67
+ },
68
+ {
69
+ "epoch": 4.0,
70
+ "grad_norm": 5.855549335479736,
71
+ "learning_rate": 0.0,
72
+ "loss": 0.3933,
73
+ "step": 384
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.8356164383561644,
78
+ "eval_f1": 0.8464351005484461,
79
+ "eval_loss": 0.40576428174972534,
80
+ "eval_precision": 0.7941680960548885,
81
+ "eval_recall": 0.9060665362035225,
82
+ "eval_runtime": 30.4475,
83
+ "eval_samples_per_second": 33.566,
84
+ "eval_steps_per_second": 1.051,
85
+ "step": 384
86
+ }
87
+ ],
88
+ "logging_steps": 500,
89
+ "max_steps": 384,
90
+ "num_input_tokens_seen": 0,
91
+ "num_train_epochs": 4,
92
+ "save_steps": 500,
93
+ "total_flos": 942780789120.0,
94
+ "train_batch_size": 32,
95
+ "trial_name": null,
96
+ "trial_params": {
97
+ "alpha": 0.999132297568699,
98
+ "learning_rate": 0.00036359085809210834,
99
+ "num_train_epochs": 4,
100
+ "temperature": 14
101
+ }
102
+ }
run-47/checkpoint-384/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e52d4ef52e4ae3e7583492431957732ea2f0822ace3819ef8d07c56bc154648
3
+ size 4920
run-47/checkpoint-384/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-49/checkpoint-96/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": "4.38.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-49/checkpoint-96/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cdc0628accb17e8607787c5836da22761db6d6b5b5d5adc52400cec7227d8df
3
+ size 17549312
run-49/checkpoint-96/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d77d8284afa40ba44a8bddc34fe6023484780eac40a942a6e42c4cf771278355
3
+ size 35122746
run-49/checkpoint-96/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24aa86019b8aea1c551cc1adaf38c4db2fc01de75a22af312230f6b592e0fd81
3
+ size 14054
run-49/checkpoint-96/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c665114f1a1d0ab649d1c7263b8eddfddad72cfe252d404a316896483e9c575e
3
+ size 1064
run-49/checkpoint-96/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-49/checkpoint-96/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-49/checkpoint-96/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-49/checkpoint-96/trainer_state.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7906066536203522,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-49/checkpoint-96",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 96,
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": 2.541956901550293,
14
+ "learning_rate": 0.00024123800395899447,
15
+ "loss": 0.5595,
16
+ "step": 96
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7906066536203522,
21
+ "eval_f1": 0.81740614334471,
22
+ "eval_loss": 0.45840805768966675,
23
+ "eval_precision": 0.7246596066565809,
24
+ "eval_recall": 0.9373776908023483,
25
+ "eval_runtime": 31.7044,
26
+ "eval_samples_per_second": 32.235,
27
+ "eval_steps_per_second": 1.009,
28
+ "step": 96
29
+ }
30
+ ],
31
+ "logging_steps": 500,
32
+ "max_steps": 288,
33
+ "num_input_tokens_seen": 0,
34
+ "num_train_epochs": 3,
35
+ "save_steps": 500,
36
+ "total_flos": 235695197280.0,
37
+ "train_batch_size": 32,
38
+ "trial_name": null,
39
+ "trial_params": {
40
+ "alpha": 0.8962876324259088,
41
+ "learning_rate": 0.0003618570059384917,
42
+ "num_train_epochs": 3,
43
+ "temperature": 11
44
+ }
45
+ }
run-49/checkpoint-96/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6361dbde25cb141ac0f5364fa642d9d3580a84ed6e436e95cd27ffb42bf5b0c
3
+ size 4920
run-49/checkpoint-96/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 sha256:6e52d4ef52e4ae3e7583492431957732ea2f0822ace3819ef8d07c56bc154648
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6361dbde25cb141ac0f5364fa642d9d3580a84ed6e436e95cd27ffb42bf5b0c
3
  size 4920