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
4213358
·
verified ·
1 Parent(s): 40922c4

Training in progress, epoch 1

Browse files
Files changed (39) hide show
  1. logs/events.out.tfevents.1709458374.49ae8f4e8e7b.1647.22 +2 -2
  2. logs/events.out.tfevents.1709459802.49ae8f4e8e7b.1647.23 +3 -0
  3. logs/events.out.tfevents.1709460004.49ae8f4e8e7b.1647.24 +3 -0
  4. logs/events.out.tfevents.1709460206.49ae8f4e8e7b.1647.25 +3 -0
  5. model.safetensors +1 -1
  6. run-21/checkpoint-2108/config.json +34 -0
  7. run-21/checkpoint-2108/model.safetensors +3 -0
  8. run-21/checkpoint-2108/optimizer.pt +3 -0
  9. run-21/checkpoint-2108/rng_state.pth +3 -0
  10. run-21/checkpoint-2108/scheduler.pt +3 -0
  11. run-21/checkpoint-2108/special_tokens_map.json +7 -0
  12. run-21/checkpoint-2108/tokenizer.json +0 -0
  13. run-21/checkpoint-2108/tokenizer_config.json +57 -0
  14. run-21/checkpoint-2108/trainer_state.json +90 -0
  15. run-21/checkpoint-2108/training_args.bin +3 -0
  16. run-21/checkpoint-2108/vocab.txt +0 -0
  17. run-21/checkpoint-3689/config.json +34 -0
  18. run-21/checkpoint-3689/model.safetensors +3 -0
  19. run-21/checkpoint-3689/optimizer.pt +3 -0
  20. run-21/checkpoint-3689/rng_state.pth +3 -0
  21. run-21/checkpoint-3689/scheduler.pt +3 -0
  22. run-21/checkpoint-3689/special_tokens_map.json +7 -0
  23. run-21/checkpoint-3689/tokenizer.json +0 -0
  24. run-21/checkpoint-3689/tokenizer_config.json +57 -0
  25. run-21/checkpoint-3689/trainer_state.json +138 -0
  26. run-21/checkpoint-3689/training_args.bin +3 -0
  27. run-21/checkpoint-3689/vocab.txt +0 -0
  28. run-24/checkpoint-527/config.json +34 -0
  29. run-24/checkpoint-527/model.safetensors +3 -0
  30. run-24/checkpoint-527/optimizer.pt +3 -0
  31. run-24/checkpoint-527/rng_state.pth +3 -0
  32. run-24/checkpoint-527/scheduler.pt +3 -0
  33. run-24/checkpoint-527/special_tokens_map.json +7 -0
  34. run-24/checkpoint-527/tokenizer.json +0 -0
  35. run-24/checkpoint-527/tokenizer_config.json +57 -0
  36. run-24/checkpoint-527/trainer_state.json +42 -0
  37. run-24/checkpoint-527/training_args.bin +3 -0
  38. run-24/checkpoint-527/vocab.txt +0 -0
  39. training_args.bin +1 -1
logs/events.out.tfevents.1709458374.49ae8f4e8e7b.1647.22 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4bde5ae21230cb057e309edef5b01beda2890b1b0942408f73a45e6c62996d49
3
- size 5714
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c415b11244f68a0fb483ff5639eb58c3618862e8f1fad9f4e1295e52a0f73c4e
3
+ size 8738
logs/events.out.tfevents.1709459802.49ae8f4e8e7b.1647.23 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10cb0d6e98a525d0365573cdb8ee94d669fd8884d8fa7853f57937a68cb39b1a
3
+ size 5179
logs/events.out.tfevents.1709460004.49ae8f4e8e7b.1647.24 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fbfd73e7bbdce648d7978b1d80e886fb8337eb40d4d0418bc51ea3a68ea8118
3
+ size 5180
logs/events.out.tfevents.1709460206.49ae8f4e8e7b.1647.25 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb4d1b0f2ddfe581b4ed0e95f3387fbce80265ff11ebfe49966fc82bbc2ec3d9
3
+ size 5180
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f68cc76e16bbcae1bbd144e8eecc36e7e1d21ef7d2e0c1cfd80b97f530b2e07d
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8f374cf06af1becedf5e2131acdc5bacc84757b1430d749e6be53f5fa38836b
3
  size 17549312
run-21/checkpoint-2108/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-2108/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60f4e312022f9ab3afda6244a465a6854cae7f6c8d7b334a24403172fb4df2ce
3
+ size 17549312
run-21/checkpoint-2108/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2622acfcc3fe6837ab6d49cb8c5c42f507b68c0db1b59f4870fb02de4ab667a2
3
+ size 35123898
run-21/checkpoint-2108/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:156b964b8b8d6a91ffdb147bae8680ec9176dd914174ff8673c354a99142bf22
3
+ size 14308
run-21/checkpoint-2108/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34b53bc0ddf247a0ce7823cb1cba12e354605ab50cc9ac37f7cd833bec999120
3
+ size 1064
run-21/checkpoint-2108/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-2108/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-21/checkpoint-2108/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-2108/trainer_state.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8360091743119266,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-21/checkpoint-2108",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2108,
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": 16.87346649169922,
14
+ "learning_rate": 0.00013104269686993426,
15
+ "loss": 1.2895,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8222477064220184,
21
+ "eval_loss": 1.1431264877319336,
22
+ "eval_runtime": 2.8225,
23
+ "eval_samples_per_second": 308.945,
24
+ "eval_steps_per_second": 2.48,
25
+ "step": 527
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "grad_norm": 7.701562881469727,
30
+ "learning_rate": 0.00010920224739161189,
31
+ "loss": 0.6357,
32
+ "step": 1054
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.8279816513761468,
37
+ "eval_loss": 1.1658384799957275,
38
+ "eval_runtime": 2.8051,
39
+ "eval_samples_per_second": 310.866,
40
+ "eval_steps_per_second": 2.495,
41
+ "step": 1054
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "grad_norm": NaN,
46
+ "learning_rate": 8.740324089142675e-05,
47
+ "loss": 0.4772,
48
+ "step": 1581
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.8279816513761468,
53
+ "eval_loss": 1.2185826301574707,
54
+ "eval_runtime": 2.8164,
55
+ "eval_samples_per_second": 309.615,
56
+ "eval_steps_per_second": 2.485,
57
+ "step": 1581
58
+ },
59
+ {
60
+ "epoch": 4.0,
61
+ "grad_norm": 7.373347759246826,
62
+ "learning_rate": 6.556279141310437e-05,
63
+ "loss": 0.3914,
64
+ "step": 2108
65
+ },
66
+ {
67
+ "epoch": 4.0,
68
+ "eval_accuracy": 0.8360091743119266,
69
+ "eval_loss": 1.2047698497772217,
70
+ "eval_runtime": 2.8054,
71
+ "eval_samples_per_second": 310.831,
72
+ "eval_steps_per_second": 2.495,
73
+ "step": 2108
74
+ }
75
+ ],
76
+ "logging_steps": 500,
77
+ "max_steps": 3689,
78
+ "num_input_tokens_seen": 0,
79
+ "num_train_epochs": 7,
80
+ "save_steps": 500,
81
+ "total_flos": 32337743850420.0,
82
+ "train_batch_size": 128,
83
+ "trial_name": null,
84
+ "trial_params": {
85
+ "alpha": 0.576065854907962,
86
+ "learning_rate": 0.00015288314634825665,
87
+ "num_train_epochs": 7,
88
+ "temperature": 26
89
+ }
90
+ }
run-21/checkpoint-2108/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9654abdb5f62732a424d7155ea430f81cc5be6aacc3e9d6d92833bbcf23a5462
3
+ size 4984
run-21/checkpoint-2108/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-21/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": "4.38.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-21/checkpoint-3689/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bf580fbfd491633b0921580d1910a762a064a66455dcd0b0201d274dbdae810
3
+ size 17549312
run-21/checkpoint-3689/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14eb1b11e226cc09fe3b424da0df77241a8f0e0491a4b47acdd692731308c884
3
+ size 35123898
run-21/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-21/checkpoint-3689/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41ac6d7524ba3021dae0474ba805734479e2355a940319a91249cc804b0926b4
3
+ size 1064
run-21/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-21/checkpoint-3689/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-21/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-21/checkpoint-3689/trainer_state.json ADDED
@@ -0,0 +1,138 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8360091743119266,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-21/checkpoint-2108",
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": 16.87346649169922,
14
+ "learning_rate": 0.00013104269686993426,
15
+ "loss": 1.2895,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8222477064220184,
21
+ "eval_loss": 1.1431264877319336,
22
+ "eval_runtime": 2.8225,
23
+ "eval_samples_per_second": 308.945,
24
+ "eval_steps_per_second": 2.48,
25
+ "step": 527
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "grad_norm": 7.701562881469727,
30
+ "learning_rate": 0.00010920224739161189,
31
+ "loss": 0.6357,
32
+ "step": 1054
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.8279816513761468,
37
+ "eval_loss": 1.1658384799957275,
38
+ "eval_runtime": 2.8051,
39
+ "eval_samples_per_second": 310.866,
40
+ "eval_steps_per_second": 2.495,
41
+ "step": 1054
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "grad_norm": NaN,
46
+ "learning_rate": 8.740324089142675e-05,
47
+ "loss": 0.4772,
48
+ "step": 1581
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.8279816513761468,
53
+ "eval_loss": 1.2185826301574707,
54
+ "eval_runtime": 2.8164,
55
+ "eval_samples_per_second": 309.615,
56
+ "eval_steps_per_second": 2.485,
57
+ "step": 1581
58
+ },
59
+ {
60
+ "epoch": 4.0,
61
+ "grad_norm": 7.373347759246826,
62
+ "learning_rate": 6.556279141310437e-05,
63
+ "loss": 0.3914,
64
+ "step": 2108
65
+ },
66
+ {
67
+ "epoch": 4.0,
68
+ "eval_accuracy": 0.8360091743119266,
69
+ "eval_loss": 1.2047698497772217,
70
+ "eval_runtime": 2.8054,
71
+ "eval_samples_per_second": 310.831,
72
+ "eval_steps_per_second": 2.495,
73
+ "step": 2108
74
+ },
75
+ {
76
+ "epoch": 5.0,
77
+ "grad_norm": 10.365816116333008,
78
+ "learning_rate": 4.3722341934781995e-05,
79
+ "loss": 0.3378,
80
+ "step": 2635
81
+ },
82
+ {
83
+ "epoch": 5.0,
84
+ "eval_accuracy": 0.8188073394495413,
85
+ "eval_loss": 1.2625073194503784,
86
+ "eval_runtime": 2.8244,
87
+ "eval_samples_per_second": 308.743,
88
+ "eval_steps_per_second": 2.478,
89
+ "step": 2635
90
+ },
91
+ {
92
+ "epoch": 6.0,
93
+ "grad_norm": 26.717870712280273,
94
+ "learning_rate": 2.1881892456459614e-05,
95
+ "loss": 0.3013,
96
+ "step": 3162
97
+ },
98
+ {
99
+ "epoch": 6.0,
100
+ "eval_accuracy": 0.8256880733944955,
101
+ "eval_loss": 1.29058837890625,
102
+ "eval_runtime": 2.835,
103
+ "eval_samples_per_second": 307.584,
104
+ "eval_steps_per_second": 2.469,
105
+ "step": 3162
106
+ },
107
+ {
108
+ "epoch": 7.0,
109
+ "grad_norm": 13.21130084991455,
110
+ "learning_rate": 4.144297813723411e-08,
111
+ "loss": 0.2864,
112
+ "step": 3689
113
+ },
114
+ {
115
+ "epoch": 7.0,
116
+ "eval_accuracy": 0.8291284403669725,
117
+ "eval_loss": 1.2824370861053467,
118
+ "eval_runtime": 2.8223,
119
+ "eval_samples_per_second": 308.97,
120
+ "eval_steps_per_second": 2.48,
121
+ "step": 3689
122
+ }
123
+ ],
124
+ "logging_steps": 500,
125
+ "max_steps": 3689,
126
+ "num_input_tokens_seen": 0,
127
+ "num_train_epochs": 7,
128
+ "save_steps": 500,
129
+ "total_flos": 56628612372420.0,
130
+ "train_batch_size": 128,
131
+ "trial_name": null,
132
+ "trial_params": {
133
+ "alpha": 0.576065854907962,
134
+ "learning_rate": 0.00015288314634825665,
135
+ "num_train_epochs": 7,
136
+ "temperature": 26
137
+ }
138
+ }
run-21/checkpoint-3689/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9654abdb5f62732a424d7155ea430f81cc5be6aacc3e9d6d92833bbcf23a5462
3
+ size 4984
run-21/checkpoint-3689/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-24/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": "4.38.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-24/checkpoint-527/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8f374cf06af1becedf5e2131acdc5bacc84757b1430d749e6be53f5fa38836b
3
+ size 17549312
run-24/checkpoint-527/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67c804e63ff323e1ef85ecd421562ff0fbca79a67c552e821214c4de7341f630
3
+ size 35123898
run-24/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-24/checkpoint-527/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6727734481baf92b7a1c8c8d288a241d826bf2406f8d0a418c4169d58fff256
3
+ size 1064
run-24/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-24/checkpoint-527/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-24/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-24/checkpoint-527/trainer_state.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8337155963302753,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-24/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": 17.628143310546875,
14
+ "learning_rate": 0.00018567149458255904,
15
+ "loss": 1.3968,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8337155963302753,
21
+ "eval_loss": 1.3282397985458374,
22
+ "eval_runtime": 2.8214,
23
+ "eval_samples_per_second": 309.061,
24
+ "eval_steps_per_second": 2.481,
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": 0.4205009910693592,
38
+ "learning_rate": 0.00023208936822819877,
39
+ "num_train_epochs": 5,
40
+ "temperature": 21
41
+ }
42
+ }
run-24/checkpoint-527/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c22b334783d23b2099fc16003e87298409a4c3cae8698d8fc8241196e2543e45
3
+ size 4984
run-24/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 sha256:9654abdb5f62732a424d7155ea430f81cc5be6aacc3e9d6d92833bbcf23a5462
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c22b334783d23b2099fc16003e87298409a4c3cae8698d8fc8241196e2543e45
3
  size 4984