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
496df10
·
verified ·
1 Parent(s): 44e1378

Training in progress, epoch 1

Browse files
Files changed (38) hide show
  1. logs/events.out.tfevents.1709456138.49ae8f4e8e7b.1647.17 +2 -2
  2. logs/events.out.tfevents.1709456952.49ae8f4e8e7b.1647.18 +3 -0
  3. logs/events.out.tfevents.1709457155.49ae8f4e8e7b.1647.19 +3 -0
  4. model.safetensors +1 -1
  5. run-16/checkpoint-1581/config.json +34 -0
  6. run-16/checkpoint-1581/model.safetensors +3 -0
  7. run-16/checkpoint-1581/optimizer.pt +3 -0
  8. run-16/checkpoint-1581/rng_state.pth +3 -0
  9. run-16/checkpoint-1581/scheduler.pt +3 -0
  10. run-16/checkpoint-1581/special_tokens_map.json +7 -0
  11. run-16/checkpoint-1581/tokenizer.json +0 -0
  12. run-16/checkpoint-1581/tokenizer_config.json +57 -0
  13. run-16/checkpoint-1581/trainer_state.json +74 -0
  14. run-16/checkpoint-1581/training_args.bin +3 -0
  15. run-16/checkpoint-1581/vocab.txt +0 -0
  16. run-16/checkpoint-2108/config.json +34 -0
  17. run-16/checkpoint-2108/model.safetensors +3 -0
  18. run-16/checkpoint-2108/optimizer.pt +3 -0
  19. run-16/checkpoint-2108/rng_state.pth +3 -0
  20. run-16/checkpoint-2108/scheduler.pt +3 -0
  21. run-16/checkpoint-2108/special_tokens_map.json +7 -0
  22. run-16/checkpoint-2108/tokenizer.json +0 -0
  23. run-16/checkpoint-2108/tokenizer_config.json +57 -0
  24. run-16/checkpoint-2108/trainer_state.json +90 -0
  25. run-16/checkpoint-2108/training_args.bin +3 -0
  26. run-16/checkpoint-2108/vocab.txt +0 -0
  27. run-18/checkpoint-527/config.json +34 -0
  28. run-18/checkpoint-527/model.safetensors +3 -0
  29. run-18/checkpoint-527/optimizer.pt +3 -0
  30. run-18/checkpoint-527/rng_state.pth +3 -0
  31. run-18/checkpoint-527/scheduler.pt +3 -0
  32. run-18/checkpoint-527/special_tokens_map.json +7 -0
  33. run-18/checkpoint-527/tokenizer.json +0 -0
  34. run-18/checkpoint-527/tokenizer_config.json +57 -0
  35. run-18/checkpoint-527/trainer_state.json +42 -0
  36. run-18/checkpoint-527/training_args.bin +3 -0
  37. run-18/checkpoint-527/vocab.txt +0 -0
  38. training_args.bin +1 -1
logs/events.out.tfevents.1709456138.49ae8f4e8e7b.1647.17 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f193fd882e70d2c7b17680e3e4c742d22d7094e1c8b9673dce821a000167d46
3
- size 5714
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a925dd83aef4cfe404bdd2ae0ca4d16d9bf02fe3dc50a36e0f4c950615376002
3
+ size 7136
logs/events.out.tfevents.1709456952.49ae8f4e8e7b.1647.18 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21e4b69b5fca5c6ad40b225d7a27d884295dc710771ba19e50fb56a726246c4d
3
+ size 5179
logs/events.out.tfevents.1709457155.49ae8f4e8e7b.1647.19 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfcca19283a86b40e7a7dd44024bcdf71346deb599d401f75a4f90d2f3e90ec5
3
+ size 5180
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:baae0e2599ccc722a13e80c6e9258f193ca99257a480a583837d1858c2e1d357
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15d24fef4de6fa411e6f4ef73ade13534c9f8cf591a3680c51bfd54dc84c3ec3
3
  size 17549312
run-16/checkpoint-1581/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-16/checkpoint-1581/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecc00582a4d43ca5b34581d638bf3e00965a0d2146b22aaade79a5a50ea66be8
3
+ size 17549312
run-16/checkpoint-1581/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38177f94a713206230107fa1510b0634d1f6bd6cf892a73fe624b1a4cc21295d
3
+ size 35123898
run-16/checkpoint-1581/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46669ed40c03155d5eb7492631b00659805dbfc29b49abcca7edef225d9a6aae
3
+ size 14308
run-16/checkpoint-1581/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee1957347abf072b413404afea4a9c3c0fdc984eb4dd22840c5c969d29a72d86
3
+ size 1064
run-16/checkpoint-1581/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-16/checkpoint-1581/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-16/checkpoint-1581/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-16/checkpoint-1581/trainer_state.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8291284403669725,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-16/checkpoint-1054",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1581,
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": 15.605107307434082,
14
+ "learning_rate": 0.00011351736809377586,
15
+ "loss": 1.2624,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8256880733944955,
21
+ "eval_loss": 1.1314730644226074,
22
+ "eval_runtime": 2.8139,
23
+ "eval_samples_per_second": 309.89,
24
+ "eval_steps_per_second": 2.488,
25
+ "step": 527
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "grad_norm": 8.443777084350586,
30
+ "learning_rate": 7.567824539585057e-05,
31
+ "loss": 0.6363,
32
+ "step": 1054
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.8291284403669725,
37
+ "eval_loss": 1.1333012580871582,
38
+ "eval_runtime": 2.8147,
39
+ "eval_samples_per_second": 309.801,
40
+ "eval_steps_per_second": 2.487,
41
+ "step": 1054
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "grad_norm": Infinity,
46
+ "learning_rate": 3.791092368976196e-05,
47
+ "loss": 0.4911,
48
+ "step": 1581
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.8291284403669725,
53
+ "eval_loss": 1.1619139909744263,
54
+ "eval_runtime": 2.8192,
55
+ "eval_samples_per_second": 309.306,
56
+ "eval_steps_per_second": 2.483,
57
+ "step": 1581
58
+ }
59
+ ],
60
+ "logging_steps": 500,
61
+ "max_steps": 2108,
62
+ "num_input_tokens_seen": 0,
63
+ "num_train_epochs": 4,
64
+ "save_steps": 500,
65
+ "total_flos": 24228458327580.0,
66
+ "train_batch_size": 128,
67
+ "trial_name": null,
68
+ "trial_params": {
69
+ "alpha": 0.5930583577377427,
70
+ "learning_rate": 0.00015135649079170115,
71
+ "num_train_epochs": 4,
72
+ "temperature": 20
73
+ }
74
+ }
run-16/checkpoint-1581/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a57fdeab65524293cd0d615294bcf49a03ea5ac5a67936255d0dead2ac2a4c51
3
+ size 4984
run-16/checkpoint-1581/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-16/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-16/checkpoint-2108/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:077718682cb2c6116329d8eda10cad5e1014a45465c833754699a49b7fbb00d3
3
+ size 17549312
run-16/checkpoint-2108/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d26ef9e4675b393884575a5937dded06db31c0d2877207376690ddfdecee0ff
3
+ size 35123898
run-16/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-16/checkpoint-2108/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95e511a61e14a8dd17ee1ced52bdc3aa3cd5da23f481a36788c8e1b8f0feafb4
3
+ size 1064
run-16/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-16/checkpoint-2108/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-16/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-16/checkpoint-2108/trainer_state.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8325688073394495,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-16/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": 15.605107307434082,
14
+ "learning_rate": 0.00011351736809377586,
15
+ "loss": 1.2624,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8256880733944955,
21
+ "eval_loss": 1.1314730644226074,
22
+ "eval_runtime": 2.8139,
23
+ "eval_samples_per_second": 309.89,
24
+ "eval_steps_per_second": 2.488,
25
+ "step": 527
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "grad_norm": 8.443777084350586,
30
+ "learning_rate": 7.567824539585057e-05,
31
+ "loss": 0.6363,
32
+ "step": 1054
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.8291284403669725,
37
+ "eval_loss": 1.1333012580871582,
38
+ "eval_runtime": 2.8147,
39
+ "eval_samples_per_second": 309.801,
40
+ "eval_steps_per_second": 2.487,
41
+ "step": 1054
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "grad_norm": Infinity,
46
+ "learning_rate": 3.791092368976196e-05,
47
+ "loss": 0.4911,
48
+ "step": 1581
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.8291284403669725,
53
+ "eval_loss": 1.1619139909744263,
54
+ "eval_runtime": 2.8192,
55
+ "eval_samples_per_second": 309.306,
56
+ "eval_steps_per_second": 2.483,
57
+ "step": 1581
58
+ },
59
+ {
60
+ "epoch": 4.0,
61
+ "grad_norm": 9.381799697875977,
62
+ "learning_rate": 7.180099183667038e-08,
63
+ "loss": 0.4223,
64
+ "step": 2108
65
+ },
66
+ {
67
+ "epoch": 4.0,
68
+ "eval_accuracy": 0.8325688073394495,
69
+ "eval_loss": 1.175363540649414,
70
+ "eval_runtime": 2.8105,
71
+ "eval_samples_per_second": 310.267,
72
+ "eval_steps_per_second": 2.491,
73
+ "step": 2108
74
+ }
75
+ ],
76
+ "logging_steps": 500,
77
+ "max_steps": 2108,
78
+ "num_input_tokens_seen": 0,
79
+ "num_train_epochs": 4,
80
+ "save_steps": 500,
81
+ "total_flos": 32337743850420.0,
82
+ "train_batch_size": 128,
83
+ "trial_name": null,
84
+ "trial_params": {
85
+ "alpha": 0.5930583577377427,
86
+ "learning_rate": 0.00015135649079170115,
87
+ "num_train_epochs": 4,
88
+ "temperature": 20
89
+ }
90
+ }
run-16/checkpoint-2108/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a57fdeab65524293cd0d615294bcf49a03ea5ac5a67936255d0dead2ac2a4c51
3
+ size 4984
run-16/checkpoint-2108/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-18/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-18/checkpoint-527/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15d24fef4de6fa411e6f4ef73ade13534c9f8cf591a3680c51bfd54dc84c3ec3
3
+ size 17549312
run-18/checkpoint-527/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1aa646a6a895fc681437e21748e10b1b70f148e07a6722d672b246f64dcc1e6b
3
+ size 35123898
run-18/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-18/checkpoint-527/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6583a7ca40786b8f293c4e4c93172a79be4b62bcf871d7e1825038a0f43edf76
3
+ size 1064
run-18/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-18/checkpoint-527/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-18/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-18/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-18/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": 9.684267044067383,
14
+ "learning_rate": 0.00022228195193198518,
15
+ "loss": 0.8996,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8337155963302753,
21
+ "eval_loss": 0.9537320733070374,
22
+ "eval_runtime": 2.8076,
23
+ "eval_samples_per_second": 310.59,
24
+ "eval_steps_per_second": 2.493,
25
+ "step": 527
26
+ }
27
+ ],
28
+ "logging_steps": 500,
29
+ "max_steps": 2108,
30
+ "num_input_tokens_seen": 0,
31
+ "num_train_epochs": 4,
32
+ "save_steps": 500,
33
+ "total_flos": 8057768762220.0,
34
+ "train_batch_size": 128,
35
+ "trial_name": null,
36
+ "trial_params": {
37
+ "alpha": 0.6751548126223466,
38
+ "learning_rate": 0.00029637593590931357,
39
+ "num_train_epochs": 4,
40
+ "temperature": 11
41
+ }
42
+ }
run-18/checkpoint-527/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b97cc6462578c922b9ac1768d7bbbbab603bdadde59a91bae399aa292bcd4264
3
+ size 4984
run-18/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:a57fdeab65524293cd0d615294bcf49a03ea5ac5a67936255d0dead2ac2a4c51
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b97cc6462578c922b9ac1768d7bbbbab603bdadde59a91bae399aa292bcd4264
3
  size 4984