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
cfdfd39
·
verified ·
1 Parent(s): 461a247

Training in progress, epoch 1

Browse files
Files changed (37) hide show
  1. logs/events.out.tfevents.1709880245.6c1c016b0e3e.7263.21 +2 -2
  2. logs/events.out.tfevents.1709880700.6c1c016b0e3e.7263.22 +3 -0
  3. model.safetensors +1 -1
  4. run-21/checkpoint-144/config.json +34 -0
  5. run-21/checkpoint-144/model.safetensors +3 -0
  6. run-21/checkpoint-144/optimizer.pt +3 -0
  7. run-21/checkpoint-144/rng_state.pth +3 -0
  8. run-21/checkpoint-144/scheduler.pt +3 -0
  9. run-21/checkpoint-144/special_tokens_map.json +7 -0
  10. run-21/checkpoint-144/tokenizer.json +0 -0
  11. run-21/checkpoint-144/tokenizer_config.json +57 -0
  12. run-21/checkpoint-144/trainer_state.json +83 -0
  13. run-21/checkpoint-144/training_args.bin +3 -0
  14. run-21/checkpoint-144/vocab.txt +0 -0
  15. run-21/checkpoint-192/config.json +34 -0
  16. run-21/checkpoint-192/model.safetensors +3 -0
  17. run-21/checkpoint-192/optimizer.pt +3 -0
  18. run-21/checkpoint-192/rng_state.pth +3 -0
  19. run-21/checkpoint-192/scheduler.pt +3 -0
  20. run-21/checkpoint-192/special_tokens_map.json +7 -0
  21. run-21/checkpoint-192/tokenizer.json +0 -0
  22. run-21/checkpoint-192/tokenizer_config.json +57 -0
  23. run-21/checkpoint-192/trainer_state.json +102 -0
  24. run-21/checkpoint-192/training_args.bin +3 -0
  25. run-21/checkpoint-192/vocab.txt +0 -0
  26. run-22/checkpoint-48/config.json +34 -0
  27. run-22/checkpoint-48/model.safetensors +3 -0
  28. run-22/checkpoint-48/optimizer.pt +3 -0
  29. run-22/checkpoint-48/rng_state.pth +3 -0
  30. run-22/checkpoint-48/scheduler.pt +3 -0
  31. run-22/checkpoint-48/special_tokens_map.json +7 -0
  32. run-22/checkpoint-48/tokenizer.json +0 -0
  33. run-22/checkpoint-48/tokenizer_config.json +57 -0
  34. run-22/checkpoint-48/trainer_state.json +45 -0
  35. run-22/checkpoint-48/training_args.bin +3 -0
  36. run-22/checkpoint-48/vocab.txt +0 -0
  37. training_args.bin +1 -1
logs/events.out.tfevents.1709880245.6c1c016b0e3e.7263.21 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:73378be4e979aa5b881b9c7eb82dae2143f0c4528728f71fafc95f927d949bde
3
- size 5983
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5efa21f0c405f9c0a69329f51dcb1fe3f27ec229470a39307cf72ac1a8141aac
3
+ size 7703
logs/events.out.tfevents.1709880700.6c1c016b0e3e.7263.22 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6abe5ce1bfc1be58b6a8d72360018b4fda3dd4ff9d0508bc7e83ad4f73f621e
3
+ size 5314
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:828ceb7d32c6581e2fd14e14862fb233ab3c436cfab8154a2703a7e38d1b837f
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:321d23ca82d0435e27df095584be4f7765ba34dcb1170dc45c03da5fa0f2852b
3
  size 17549312
run-21/checkpoint-144/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-21/checkpoint-144/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1380e41fc918cfd2abc66ca3e9641162642a7b52f56b4ecd53b367aca7c3ec4c
3
+ size 17549312
run-21/checkpoint-144/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fb1b4d940104e1d47a8b966d70821175bc0882253f47892c9306f6660612e71
3
+ size 35122746
run-21/checkpoint-144/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:117413c2e4c616775c2a2540a012ac63a1e136326812b679f4206af03d68f7d5
3
+ size 14054
run-21/checkpoint-144/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d0ca26460c451293c7f760713981cd2285befb8b7b69efc7447c566217d840c
3
+ size 1064
run-21/checkpoint-144/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-21/checkpoint-144/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-21/checkpoint-144/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-21/checkpoint-144/trainer_state.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8277886497064579,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-21/checkpoint-144",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 144,
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": 1.955494999885559,
14
+ "learning_rate": 0.00045025211447661823,
15
+ "loss": 0.583,
16
+ "step": 48
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7544031311154599,
21
+ "eval_f1": 0.7957689178193653,
22
+ "eval_loss": 0.48823896050453186,
23
+ "eval_precision": 0.6810584958217271,
24
+ "eval_recall": 0.9569471624266145,
25
+ "eval_runtime": 27.5121,
26
+ "eval_samples_per_second": 37.147,
27
+ "eval_steps_per_second": 0.582,
28
+ "step": 48
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 5.347569942474365,
33
+ "learning_rate": 0.0003001680763177455,
34
+ "loss": 0.4846,
35
+ "step": 96
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.815068493150685,
40
+ "eval_f1": 0.8205128205128206,
41
+ "eval_loss": 0.4311129152774811,
42
+ "eval_precision": 0.7970479704797048,
43
+ "eval_recall": 0.8454011741682974,
44
+ "eval_runtime": 27.1948,
45
+ "eval_samples_per_second": 37.581,
46
+ "eval_steps_per_second": 0.588,
47
+ "step": 96
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 3.818072557449341,
52
+ "learning_rate": 0.00015008403815887274,
53
+ "loss": 0.4238,
54
+ "step": 144
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.8277886497064579,
59
+ "eval_f1": 0.8361266294227189,
60
+ "eval_loss": 0.41256558895111084,
61
+ "eval_precision": 0.7975133214920072,
62
+ "eval_recall": 0.8786692759295499,
63
+ "eval_runtime": 27.3265,
64
+ "eval_samples_per_second": 37.4,
65
+ "eval_steps_per_second": 0.586,
66
+ "step": 144
67
+ }
68
+ ],
69
+ "logging_steps": 500,
70
+ "max_steps": 192,
71
+ "num_input_tokens_seen": 0,
72
+ "num_train_epochs": 4,
73
+ "save_steps": 500,
74
+ "total_flos": 707085591840.0,
75
+ "train_batch_size": 64,
76
+ "trial_name": null,
77
+ "trial_params": {
78
+ "alpha": 0.9858291446272915,
79
+ "learning_rate": 0.000600336152635491,
80
+ "num_train_epochs": 4,
81
+ "temperature": 30
82
+ }
83
+ }
run-21/checkpoint-144/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72e8bb06dbc2abff20995cef6ab363b1eddd8cc3c373524e26c6b52497059996
3
+ size 4920
run-21/checkpoint-144/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-21/checkpoint-192/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-21/checkpoint-192/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83263f0e160242d7333019e2bef3daed122fbb54a151ba8f536404edb36b2725
3
+ size 17549312
run-21/checkpoint-192/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00799743409f2ce9d857be0747e1f9e874cfc2f6f65cee22727c3456919fe132
3
+ size 35122746
run-21/checkpoint-192/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d267b33c0df8c744bb62ca8fc0e243d0ddded8c46ea62639c56f51d1dc7a548
3
+ size 14054
run-21/checkpoint-192/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39c79fa4bb032ea6305450d7ee7a26cac716fb28388b42dd0b961a4d2f44f4b2
3
+ size 1064
run-21/checkpoint-192/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-21/checkpoint-192/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-21/checkpoint-192/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-21/checkpoint-192/trainer_state.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8326810176125244,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-21/checkpoint-192",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 192,
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": 1.955494999885559,
14
+ "learning_rate": 0.00045025211447661823,
15
+ "loss": 0.583,
16
+ "step": 48
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7544031311154599,
21
+ "eval_f1": 0.7957689178193653,
22
+ "eval_loss": 0.48823896050453186,
23
+ "eval_precision": 0.6810584958217271,
24
+ "eval_recall": 0.9569471624266145,
25
+ "eval_runtime": 27.5121,
26
+ "eval_samples_per_second": 37.147,
27
+ "eval_steps_per_second": 0.582,
28
+ "step": 48
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 5.347569942474365,
33
+ "learning_rate": 0.0003001680763177455,
34
+ "loss": 0.4846,
35
+ "step": 96
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.815068493150685,
40
+ "eval_f1": 0.8205128205128206,
41
+ "eval_loss": 0.4311129152774811,
42
+ "eval_precision": 0.7970479704797048,
43
+ "eval_recall": 0.8454011741682974,
44
+ "eval_runtime": 27.1948,
45
+ "eval_samples_per_second": 37.581,
46
+ "eval_steps_per_second": 0.588,
47
+ "step": 96
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 3.818072557449341,
52
+ "learning_rate": 0.00015008403815887274,
53
+ "loss": 0.4238,
54
+ "step": 144
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.8277886497064579,
59
+ "eval_f1": 0.8361266294227189,
60
+ "eval_loss": 0.41256558895111084,
61
+ "eval_precision": 0.7975133214920072,
62
+ "eval_recall": 0.8786692759295499,
63
+ "eval_runtime": 27.3265,
64
+ "eval_samples_per_second": 37.4,
65
+ "eval_steps_per_second": 0.586,
66
+ "step": 144
67
+ },
68
+ {
69
+ "epoch": 4.0,
70
+ "grad_norm": 2.925151824951172,
71
+ "learning_rate": 0.0,
72
+ "loss": 0.397,
73
+ "step": 192
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.8326810176125244,
78
+ "eval_f1": 0.8455284552845528,
79
+ "eval_loss": 0.3960628807544708,
80
+ "eval_precision": 0.785234899328859,
81
+ "eval_recall": 0.9158512720156555,
82
+ "eval_runtime": 27.2535,
83
+ "eval_samples_per_second": 37.5,
84
+ "eval_steps_per_second": 0.587,
85
+ "step": 192
86
+ }
87
+ ],
88
+ "logging_steps": 500,
89
+ "max_steps": 192,
90
+ "num_input_tokens_seen": 0,
91
+ "num_train_epochs": 4,
92
+ "save_steps": 500,
93
+ "total_flos": 942780789120.0,
94
+ "train_batch_size": 64,
95
+ "trial_name": null,
96
+ "trial_params": {
97
+ "alpha": 0.9858291446272915,
98
+ "learning_rate": 0.000600336152635491,
99
+ "num_train_epochs": 4,
100
+ "temperature": 30
101
+ }
102
+ }
run-21/checkpoint-192/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72e8bb06dbc2abff20995cef6ab363b1eddd8cc3c373524e26c6b52497059996
3
+ size 4920
run-21/checkpoint-192/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-22/checkpoint-48/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-22/checkpoint-48/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:321d23ca82d0435e27df095584be4f7765ba34dcb1170dc45c03da5fa0f2852b
3
+ size 17549312
run-22/checkpoint-48/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c65daf84c95200abd0a040c9435d8733ff60121b781ab249eeb9b43f8dc4efa1
3
+ size 35122746
run-22/checkpoint-48/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f731098665929ed6a815501631b54240caaac6508207c5c55cf0fe36ad39b17
3
+ size 14054
run-22/checkpoint-48/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:791de8cc86d23e60a9b4942194673218e636b5965a35f8a42db592808c0d227e
3
+ size 1064
run-22/checkpoint-48/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-22/checkpoint-48/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-22/checkpoint-48/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-22/checkpoint-48/trainer_state.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7504892367906066,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-22/checkpoint-48",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 48,
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": 1.2523858547210693,
14
+ "learning_rate": 0.0004199316455808347,
15
+ "loss": 0.5365,
16
+ "step": 48
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7504892367906066,
21
+ "eval_f1": 0.7921760391198044,
22
+ "eval_loss": 0.47587937116622925,
23
+ "eval_precision": 0.6787709497206704,
24
+ "eval_recall": 0.9510763209393346,
25
+ "eval_runtime": 27.0541,
26
+ "eval_samples_per_second": 37.776,
27
+ "eval_steps_per_second": 0.591,
28
+ "step": 48
29
+ }
30
+ ],
31
+ "logging_steps": 500,
32
+ "max_steps": 192,
33
+ "num_input_tokens_seen": 0,
34
+ "num_train_epochs": 4,
35
+ "save_steps": 500,
36
+ "total_flos": 235695197280.0,
37
+ "train_batch_size": 64,
38
+ "trial_name": null,
39
+ "trial_params": {
40
+ "alpha": 0.8212346430734099,
41
+ "learning_rate": 0.0005599088607744462,
42
+ "num_train_epochs": 4,
43
+ "temperature": 30
44
+ }
45
+ }
run-22/checkpoint-48/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a3368b5b0af1d21214eacb240625f81c73bbf2fea6c8e26456256938e253883
3
+ size 4920
run-22/checkpoint-48/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 sha256:72e8bb06dbc2abff20995cef6ab363b1eddd8cc3c373524e26c6b52497059996
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a3368b5b0af1d21214eacb240625f81c73bbf2fea6c8e26456256938e253883
3
  size 4920