Hugging Face's logo

Slava
/
tiny-bert-sst2-distilled

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Slava commited on
Commit
38163e9
·
verified ·
1 Parent(s): 52c26bf

Training in progress, epoch 1

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. logs/events.out.tfevents.1706175299.A-FVFFG2C4Q05P.18450.1 +2 -2
  2. logs/events.out.tfevents.1706179873.A-FVFFG2C4Q05P.18450.2 +3 -0
  3. logs/events.out.tfevents.1706181411.A-FVFFG2C4Q05P.18450.3 +3 -0
  4. model.safetensors +1 -1
  5. run-0/checkpoint-1054/config.json +34 -0
  6. run-0/checkpoint-1054/model.safetensors +3 -0
  7. run-0/checkpoint-1054/optimizer.pt +3 -0
  8. run-0/checkpoint-1054/rng_state.pth +3 -0
  9. run-0/checkpoint-1054/scheduler.pt +3 -0
  10. run-0/checkpoint-1054/special_tokens_map.json +7 -0
  11. run-0/checkpoint-1054/tokenizer.json +0 -0
  12. run-0/checkpoint-1054/tokenizer_config.json +57 -0
  13. run-0/checkpoint-1054/trainer_state.json +56 -0
  14. run-0/checkpoint-1054/training_args.bin +3 -0
  15. run-0/checkpoint-1054/vocab.txt +0 -0
  16. run-0/checkpoint-2108/config.json +34 -0
  17. run-0/checkpoint-2108/model.safetensors +3 -0
  18. run-0/checkpoint-2108/optimizer.pt +3 -0
  19. run-0/checkpoint-2108/rng_state.pth +3 -0
  20. run-0/checkpoint-2108/scheduler.pt +3 -0
  21. run-0/checkpoint-2108/special_tokens_map.json +7 -0
  22. run-0/checkpoint-2108/tokenizer.json +0 -0
  23. run-0/checkpoint-2108/tokenizer_config.json +57 -0
  24. run-0/checkpoint-2108/trainer_state.json +86 -0
  25. run-0/checkpoint-2108/training_args.bin +3 -0
  26. run-0/checkpoint-2108/vocab.txt +0 -0
  27. run-1/checkpoint-1054/config.json +34 -0
  28. run-1/checkpoint-1054/model.safetensors +3 -0
  29. run-1/checkpoint-1054/optimizer.pt +3 -0
  30. run-1/checkpoint-1054/rng_state.pth +3 -0
  31. run-1/checkpoint-1054/scheduler.pt +3 -0
  32. run-1/checkpoint-1054/special_tokens_map.json +7 -0
  33. run-1/checkpoint-1054/tokenizer.json +0 -0
  34. run-1/checkpoint-1054/tokenizer_config.json +57 -0
  35. run-1/checkpoint-1054/trainer_state.json +56 -0
  36. run-1/checkpoint-1054/training_args.bin +3 -0
  37. run-1/checkpoint-1054/vocab.txt +0 -0
  38. run-1/checkpoint-527/config.json +34 -0
  39. run-1/checkpoint-527/model.safetensors +3 -0
  40. run-1/checkpoint-527/optimizer.pt +3 -0
  41. run-1/checkpoint-527/rng_state.pth +3 -0
  42. run-1/checkpoint-527/scheduler.pt +3 -0
  43. run-1/checkpoint-527/special_tokens_map.json +7 -0
  44. run-1/checkpoint-527/tokenizer.json +0 -0
  45. run-1/checkpoint-527/tokenizer_config.json +57 -0
  46. run-1/checkpoint-527/trainer_state.json +41 -0
  47. run-1/checkpoint-527/training_args.bin +3 -0
  48. run-1/checkpoint-527/vocab.txt +0 -0
  49. run-2/checkpoint-527/config.json +34 -0
  50. run-2/checkpoint-527/model.safetensors +3 -0
logs/events.out.tfevents.1706175299.A-FVFFG2C4Q05P.18450.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a4d0db3c48ada0b77c779b5020fea08aea26c28a05be97513507329065560e2
3
- size 4916
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5bfab1dfd484101fe96dbb6284f97385d0e20bf8b01a0d6d3568ef68b0f3645
3
+ size 6710
logs/events.out.tfevents.1706179873.A-FVFFG2C4Q05P.18450.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c68abaa16c79e642aa567e11ae443e9df9f1eab110c60b9cb0330a808fc1927
3
+ size 5749
logs/events.out.tfevents.1706181411.A-FVFFG2C4Q05P.18450.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5a6a2f9d11bd89c5bf9fe47b3ca950769c6e4a8fce23d176f20d627a79df975
3
+ size 4916
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c52e494c8a54e31d0905183277502473d55f04968f399572f68c03699d0896d
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e83acce2624e77c390e5e2ad5a75f47044332b4675d68f3ecbe5a56da25b3ff
3
  size 17549312
run-0/checkpoint-1054/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": "4.37.1",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-0/checkpoint-1054/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:908638c4664a16b2be1e4378ceae2501bd6c5c8980ac2e8e1c440c2a13417b84
3
+ size 17549312
run-0/checkpoint-1054/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2820bc83db3bc05fcedc9b2e3c0814ef2ae544eaacfc2e20c898ca87db47f3a3
3
+ size 35122373
run-0/checkpoint-1054/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:260bdbb59b5e150f75450cd4e9defbf6deeda9a4e5690f5284bcc9395a60f0af
3
+ size 13617
run-0/checkpoint-1054/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16e276f2a6209f1be03f0c62afe640f64e06f172ce4dd0006b8d39aabb5c7bee
3
+ size 627
run-0/checkpoint-1054/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-0/checkpoint-1054/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-1054/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-0/checkpoint-1054/trainer_state.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8245412844036697,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-1054",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1054,
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
+ "learning_rate": 9.507440967713177e-05,
14
+ "loss": 1.6043,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8107798165137615,
20
+ "eval_loss": 1.3382474184036255,
21
+ "eval_runtime": 7.7477,
22
+ "eval_samples_per_second": 112.55,
23
+ "eval_steps_per_second": 0.903,
24
+ "step": 527
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 6.338293978475452e-05,
29
+ "loss": 0.7901,
30
+ "step": 1054
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8245412844036697,
35
+ "eval_loss": 1.3008999824523926,
36
+ "eval_runtime": 7.5885,
37
+ "eval_samples_per_second": 114.91,
38
+ "eval_steps_per_second": 0.922,
39
+ "step": 1054
40
+ }
41
+ ],
42
+ "logging_steps": 500,
43
+ "max_steps": 2108,
44
+ "num_input_tokens_seen": 0,
45
+ "num_train_epochs": 4,
46
+ "save_steps": 500,
47
+ "total_flos": 16162868129520.0,
48
+ "train_batch_size": 128,
49
+ "trial_name": null,
50
+ "trial_params": {
51
+ "alpha": 0.46638270752374766,
52
+ "learning_rate": 0.00012676587956950903,
53
+ "num_train_epochs": 4,
54
+ "temperature": 20
55
+ }
56
+ }
run-0/checkpoint-1054/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b149b247816d0d72efcc0fd576feb131fc41a6f49009ffa81023f2608190ff20
3
+ size 4283
run-0/checkpoint-1054/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-0/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": "4.37.1",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-0/checkpoint-2108/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47c2b0b68f4a93871e9b62c559059b8205cf7ae27be11990e9f5c24e250c7948
3
+ size 17549312
run-0/checkpoint-2108/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab2791cb0e9001d567167af7c038963e5f74421ba519ef40a2bb912db89508a3
3
+ size 35122373
run-0/checkpoint-2108/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2aae3bffb74208d13dfae4d8b66eb00427742bd84752ee081ae0f135d90f179b
3
+ size 13617
run-0/checkpoint-2108/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bcf0159dd01ecec2ae12e2631a4d3ae44359cf26e62a349b7a0031ee07d2931
3
+ size 627
run-0/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-0/checkpoint-2108/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/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-0/checkpoint-2108/trainer_state.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8245412844036697,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-1054",
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
+ "learning_rate": 9.507440967713177e-05,
14
+ "loss": 1.6043,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8107798165137615,
20
+ "eval_loss": 1.3382474184036255,
21
+ "eval_runtime": 7.7477,
22
+ "eval_samples_per_second": 112.55,
23
+ "eval_steps_per_second": 0.903,
24
+ "step": 527
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 6.338293978475452e-05,
29
+ "loss": 0.7901,
30
+ "step": 1054
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8245412844036697,
35
+ "eval_loss": 1.3008999824523926,
36
+ "eval_runtime": 7.5885,
37
+ "eval_samples_per_second": 114.91,
38
+ "eval_steps_per_second": 0.922,
39
+ "step": 1054
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 3.169146989237726e-05,
44
+ "loss": 0.6181,
45
+ "step": 1581
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.8188073394495413,
50
+ "eval_loss": 1.3191856145858765,
51
+ "eval_runtime": 7.916,
52
+ "eval_samples_per_second": 110.157,
53
+ "eval_steps_per_second": 0.884,
54
+ "step": 1581
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 0.0,
59
+ "loss": 0.5387,
60
+ "step": 2108
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.819954128440367,
65
+ "eval_loss": 1.3426295518875122,
66
+ "eval_runtime": 9.3241,
67
+ "eval_samples_per_second": 93.521,
68
+ "eval_steps_per_second": 0.751,
69
+ "step": 2108
70
+ }
71
+ ],
72
+ "logging_steps": 500,
73
+ "max_steps": 2108,
74
+ "num_input_tokens_seen": 0,
75
+ "num_train_epochs": 4,
76
+ "save_steps": 500,
77
+ "total_flos": 32344049138640.0,
78
+ "train_batch_size": 128,
79
+ "trial_name": null,
80
+ "trial_params": {
81
+ "alpha": 0.46638270752374766,
82
+ "learning_rate": 0.00012676587956950903,
83
+ "num_train_epochs": 4,
84
+ "temperature": 20
85
+ }
86
+ }
run-0/checkpoint-2108/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b149b247816d0d72efcc0fd576feb131fc41a6f49009ffa81023f2608190ff20
3
+ size 4283
run-0/checkpoint-2108/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-1054/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": "4.37.1",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-1/checkpoint-1054/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a48f92c46c7e5026b38f2b3bf26873dd3ae9f5952ec78dfa9724da5d9e0ab0c2
3
+ size 17549312
run-1/checkpoint-1054/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b28bbcc0546d31f0198832865f505c9cf6e29ab2fd20d07ff939ad80196014e
3
+ size 35122373
run-1/checkpoint-1054/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:260bdbb59b5e150f75450cd4e9defbf6deeda9a4e5690f5284bcc9395a60f0af
3
+ size 13617
run-1/checkpoint-1054/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7ac61b823b02e9f174aebe61188f30c7365422c82ea4dfaaa2d4e8479e62b71
3
+ size 627
run-1/checkpoint-1054/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-1/checkpoint-1054/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-1054/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-1/checkpoint-1054/trainer_state.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6995412844036697,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-1054",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1054,
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
+ "learning_rate": 5.34694014828574e-06,
14
+ "loss": 4.485,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.6513761467889908,
20
+ "eval_loss": 3.9686293601989746,
21
+ "eval_runtime": 9.1719,
22
+ "eval_samples_per_second": 95.073,
23
+ "eval_steps_per_second": 0.763,
24
+ "step": 527
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 0.0,
29
+ "loss": 4.0805,
30
+ "step": 1054
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.6995412844036697,
35
+ "eval_loss": 3.6462810039520264,
36
+ "eval_runtime": 9.4456,
37
+ "eval_samples_per_second": 92.318,
38
+ "eval_steps_per_second": 0.741,
39
+ "step": 1054
40
+ }
41
+ ],
42
+ "logging_steps": 500,
43
+ "max_steps": 1054,
44
+ "num_input_tokens_seen": 0,
45
+ "num_train_epochs": 2,
46
+ "save_steps": 500,
47
+ "total_flos": 16162868129520.0,
48
+ "train_batch_size": 128,
49
+ "trial_name": null,
50
+ "trial_params": {
51
+ "alpha": 0.10705118382199963,
52
+ "learning_rate": 1.069388029657148e-05,
53
+ "num_train_epochs": 2,
54
+ "temperature": 16
55
+ }
56
+ }
run-1/checkpoint-1054/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70d09d03f84ec5e6f07e718b975ff8effb1d82efe0ca25ef5c8642902ec419c8
3
+ size 4283
run-1/checkpoint-1054/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/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": "4.37.1",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-1/checkpoint-527/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bcd7d0aec1de757ac2cdfe0bc6f7c2b14a91f1a613b624a2f0093d80ca6355a
3
+ size 17549312
run-1/checkpoint-527/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d52e5de6bd8997ddf8ca3a2a1d76c2c6d88bf42dbd60546f3891044f28d441fa
3
+ size 35122373
run-1/checkpoint-527/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f943a8d8f93fea7f44cad3b9bfb2d2b97d65b141eb704b9cba669cf42e776b14
3
+ size 13617
run-1/checkpoint-527/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4593c184c19c11a2f817520c5f5fdeb4ee376ac8d1c8d9f9c8b43128595f77d5
3
+ size 627
run-1/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-1/checkpoint-527/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/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-1/checkpoint-527/trainer_state.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6513761467889908,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/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
+ "learning_rate": 5.34694014828574e-06,
14
+ "loss": 4.485,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.6513761467889908,
20
+ "eval_loss": 3.9686293601989746,
21
+ "eval_runtime": 9.1719,
22
+ "eval_samples_per_second": 95.073,
23
+ "eval_steps_per_second": 0.763,
24
+ "step": 527
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 1054,
29
+ "num_input_tokens_seen": 0,
30
+ "num_train_epochs": 2,
31
+ "save_steps": 500,
32
+ "total_flos": 8069051778960.0,
33
+ "train_batch_size": 128,
34
+ "trial_name": null,
35
+ "trial_params": {
36
+ "alpha": 0.10705118382199963,
37
+ "learning_rate": 1.069388029657148e-05,
38
+ "num_train_epochs": 2,
39
+ "temperature": 16
40
+ }
41
+ }
run-1/checkpoint-527/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70d09d03f84ec5e6f07e718b975ff8effb1d82efe0ca25ef5c8642902ec419c8
3
+ size 4283
run-1/checkpoint-527/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/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": "4.37.1",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-2/checkpoint-527/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e83acce2624e77c390e5e2ad5a75f47044332b4675d68f3ecbe5a56da25b3ff
3
+ size 17549312