Hugging Face's logo

hassanalsawadi
/
tiny-bert-sst2-distilled

Text Classification
Transformers
TensorBoard
Safetensors
bert
Inference Endpoints
Model card Files Metrics Community
hassanalsawadi commited on
Commit
4cf0771
·
verified ·
1 Parent(s): bbdd12c

Training in progress, epoch 1

Browse files
Files changed (37) hide show
  1. logs/events.out.tfevents.1721415086.f39e781deb18.907.4 +2 -2
  2. logs/events.out.tfevents.1721415792.f39e781deb18.907.5 +3 -0
  3. model.safetensors +1 -1
  4. run-3/checkpoint-1581/config.json +34 -0
  5. run-3/checkpoint-1581/model.safetensors +3 -0
  6. run-3/checkpoint-1581/optimizer.pt +3 -0
  7. run-3/checkpoint-1581/rng_state.pth +3 -0
  8. run-3/checkpoint-1581/scheduler.pt +3 -0
  9. run-3/checkpoint-1581/special_tokens_map.json +7 -0
  10. run-3/checkpoint-1581/tokenizer.json +0 -0
  11. run-3/checkpoint-1581/tokenizer_config.json +57 -0
  12. run-3/checkpoint-1581/trainer_state.json +86 -0
  13. run-3/checkpoint-1581/training_args.bin +3 -0
  14. run-3/checkpoint-1581/vocab.txt +0 -0
  15. run-3/checkpoint-2108/config.json +34 -0
  16. run-3/checkpoint-2108/model.safetensors +3 -0
  17. run-3/checkpoint-2108/optimizer.pt +3 -0
  18. run-3/checkpoint-2108/rng_state.pth +3 -0
  19. run-3/checkpoint-2108/scheduler.pt +3 -0
  20. run-3/checkpoint-2108/special_tokens_map.json +7 -0
  21. run-3/checkpoint-2108/tokenizer.json +0 -0
  22. run-3/checkpoint-2108/tokenizer_config.json +57 -0
  23. run-3/checkpoint-2108/trainer_state.json +102 -0
  24. run-3/checkpoint-2108/training_args.bin +3 -0
  25. run-3/checkpoint-2108/vocab.txt +0 -0
  26. run-4/checkpoint-527/config.json +34 -0
  27. run-4/checkpoint-527/model.safetensors +3 -0
  28. run-4/checkpoint-527/optimizer.pt +3 -0
  29. run-4/checkpoint-527/rng_state.pth +3 -0
  30. run-4/checkpoint-527/scheduler.pt +3 -0
  31. run-4/checkpoint-527/special_tokens_map.json +7 -0
  32. run-4/checkpoint-527/tokenizer.json +0 -0
  33. run-4/checkpoint-527/tokenizer_config.json +57 -0
  34. run-4/checkpoint-527/trainer_state.json +54 -0
  35. run-4/checkpoint-527/training_args.bin +3 -0
  36. run-4/checkpoint-527/vocab.txt +0 -0
  37. training_args.bin +1 -1
logs/events.out.tfevents.1721415086.f39e781deb18.907.4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:882e319a895e0a0d0851cedefaefffd3aee6944d6f43f0edf8b41d5ce809971d
3
- size 5986
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e612ccb05d27ce02ffb1714dc5897143309892e194e6bb7b3744679b2321cc2
3
+ size 7408
logs/events.out.tfevents.1721415792.f39e781deb18.907.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce9da192663be5f9364fe6e349fa6095ad1d17e992f92ed702306ca9c27823ff
3
+ size 5451
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d1163596c23bde6689f269bfdf56841932a8d67c0530dba355ccf20644faaaa1
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:589a75644e9a9ac800961bf9c60eb699e45e079476c5f7da0f9757b5d2ba4339
3
  size 17549312
run-3/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": "4.42.4",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-3/checkpoint-1581/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6cfb6da4565f703d6c438dfe7745d9ccc15e971100b00f1721634d1e907e064
3
+ size 17549312
run-3/checkpoint-1581/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:531aa781cd633e32de9466fa0740b73053e81bc61e3f3c0f03f284e2c319d951
3
+ size 35123898
run-3/checkpoint-1581/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a82df51000915659b456ad52af3debde383df68929936f84f551af1b1989186
3
+ size 14308
run-3/checkpoint-1581/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cbcb8c5157f605cbbc021906084a4269367078b716e3f7163422add00a2374f
3
+ size 1064
run-3/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-3/checkpoint-1581/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/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-3/checkpoint-1581/trainer_state.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.801605504587156,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-3/checkpoint-1581",
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": 12.261916160583496,
14
+ "learning_rate": 2.0618934912556048e-05,
15
+ "loss": 1.857,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7717889908256881,
21
+ "eval_loss": 1.388199806213379,
22
+ "eval_runtime": 2.3917,
23
+ "eval_samples_per_second": 364.592,
24
+ "eval_steps_per_second": 2.927,
25
+ "step": 527
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "grad_norm": Infinity,
30
+ "learning_rate": 1.375899831293272e-05,
31
+ "loss": 1.2749,
32
+ "step": 1054
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.7924311926605505,
37
+ "eval_loss": 1.2368603944778442,
38
+ "eval_runtime": 2.3919,
39
+ "eval_samples_per_second": 364.569,
40
+ "eval_steps_per_second": 2.927,
41
+ "step": 1054
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "grad_norm": 40.54018020629883,
46
+ "learning_rate": 6.886020008747371e-06,
47
+ "loss": 1.0775,
48
+ "step": 1581
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.801605504587156,
53
+ "eval_loss": 1.1893019676208496,
54
+ "eval_runtime": 2.4067,
55
+ "eval_samples_per_second": 362.322,
56
+ "eval_steps_per_second": 2.909,
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
+ "stateful_callbacks": {
66
+ "TrainerControl": {
67
+ "args": {
68
+ "should_epoch_stop": false,
69
+ "should_evaluate": false,
70
+ "should_log": false,
71
+ "should_save": true,
72
+ "should_training_stop": false
73
+ },
74
+ "attributes": {}
75
+ }
76
+ },
77
+ "total_flos": 24228458327580.0,
78
+ "train_batch_size": 128,
79
+ "trial_name": null,
80
+ "trial_params": {
81
+ "alpha": 0.6528305938616039,
82
+ "learning_rate": 2.7491913216741395e-05,
83
+ "num_train_epochs": 4,
84
+ "temperature": 25
85
+ }
86
+ }
run-3/checkpoint-1581/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba36240ce7e4505d3864ee5746a44018d28b263fd65bd3b7dcb20202ab87ba59
3
+ size 5176
run-3/checkpoint-1581/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-3/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": "4.42.4",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-3/checkpoint-2108/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:137c7cc203c8d7e1d231205ae2a22dfbd1c2abade0ea565d6dd3f89045e807d4
3
+ size 17549312
run-3/checkpoint-2108/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd401cd07d14b31e449d67dc891a211f13d0f88f8e95903d2c6f32a7367aa5e7
3
+ size 35123898
run-3/checkpoint-2108/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37554b2d10e31eaeff51183dc670fea3e7982972d731e9e9b6dff48f2395e37d
3
+ size 14308
run-3/checkpoint-2108/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f92e78078a560a01e830751e01b9bb5a57e031b7cd6d28e6b27138ce39a6f7a
3
+ size 1064
run-3/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-3/checkpoint-2108/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/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-3/checkpoint-2108/trainer_state.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.801605504587156,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-3/checkpoint-1581",
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": 12.261916160583496,
14
+ "learning_rate": 2.0618934912556048e-05,
15
+ "loss": 1.857,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7717889908256881,
21
+ "eval_loss": 1.388199806213379,
22
+ "eval_runtime": 2.3917,
23
+ "eval_samples_per_second": 364.592,
24
+ "eval_steps_per_second": 2.927,
25
+ "step": 527
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "grad_norm": Infinity,
30
+ "learning_rate": 1.375899831293272e-05,
31
+ "loss": 1.2749,
32
+ "step": 1054
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.7924311926605505,
37
+ "eval_loss": 1.2368603944778442,
38
+ "eval_runtime": 2.3919,
39
+ "eval_samples_per_second": 364.569,
40
+ "eval_steps_per_second": 2.927,
41
+ "step": 1054
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "grad_norm": 40.54018020629883,
46
+ "learning_rate": 6.886020008747371e-06,
47
+ "loss": 1.0775,
48
+ "step": 1581
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.801605504587156,
53
+ "eval_loss": 1.1893019676208496,
54
+ "eval_runtime": 2.4067,
55
+ "eval_samples_per_second": 362.322,
56
+ "eval_steps_per_second": 2.909,
57
+ "step": 1581
58
+ },
59
+ {
60
+ "epoch": 4.0,
61
+ "grad_norm": 20.87686538696289,
62
+ "learning_rate": 1.3041704562021534e-08,
63
+ "loss": 0.9999,
64
+ "step": 2108
65
+ },
66
+ {
67
+ "epoch": 4.0,
68
+ "eval_accuracy": 0.7993119266055045,
69
+ "eval_loss": 1.1638764142990112,
70
+ "eval_runtime": 2.3976,
71
+ "eval_samples_per_second": 363.694,
72
+ "eval_steps_per_second": 2.92,
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
+ "stateful_callbacks": {
82
+ "TrainerControl": {
83
+ "args": {
84
+ "should_epoch_stop": false,
85
+ "should_evaluate": false,
86
+ "should_log": false,
87
+ "should_save": true,
88
+ "should_training_stop": true
89
+ },
90
+ "attributes": {}
91
+ }
92
+ },
93
+ "total_flos": 32337743850420.0,
94
+ "train_batch_size": 128,
95
+ "trial_name": null,
96
+ "trial_params": {
97
+ "alpha": 0.6528305938616039,
98
+ "learning_rate": 2.7491913216741395e-05,
99
+ "num_train_epochs": 4,
100
+ "temperature": 25
101
+ }
102
+ }
run-3/checkpoint-2108/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba36240ce7e4505d3864ee5746a44018d28b263fd65bd3b7dcb20202ab87ba59
3
+ size 5176
run-3/checkpoint-2108/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-4/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": "4.42.4",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-4/checkpoint-527/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:589a75644e9a9ac800961bf9c60eb699e45e079476c5f7da0f9757b5d2ba4339
3
+ size 17549312
run-4/checkpoint-527/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a0a96302daf508b6f9e1c5387540e1d722c00278d98e6a0e5aa13c3dffe8c8d
3
+ size 35123898
run-4/checkpoint-527/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9733f27bb728718f7284348156186daf975855376673d9de7e218a8cff476307
3
+ size 14308
run-4/checkpoint-527/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8532e8cae1562f9b55fea2c5086078d8350f04c65052c2af66c3649cf2ec7897
3
+ size 1064
run-4/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-4/checkpoint-527/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/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-4/checkpoint-527/trainer_state.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7694954128440367,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-4/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": 5.9670329093933105,
14
+ "learning_rate": 1.3453457724318434e-05,
15
+ "loss": 1.5275,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7694954128440367,
21
+ "eval_loss": 1.2012722492218018,
22
+ "eval_runtime": 2.3974,
23
+ "eval_samples_per_second": 363.727,
24
+ "eval_steps_per_second": 2.92,
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
+ "stateful_callbacks": {
34
+ "TrainerControl": {
35
+ "args": {
36
+ "should_epoch_stop": false,
37
+ "should_evaluate": false,
38
+ "should_log": false,
39
+ "should_save": true,
40
+ "should_training_stop": false
41
+ },
42
+ "attributes": {}
43
+ }
44
+ },
45
+ "total_flos": 8057768762220.0,
46
+ "train_batch_size": 128,
47
+ "trial_name": null,
48
+ "trial_params": {
49
+ "alpha": 0.77657862481259,
50
+ "learning_rate": 1.681682215539804e-05,
51
+ "num_train_epochs": 5,
52
+ "temperature": 29
53
+ }
54
+ }
run-4/checkpoint-527/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5bb70b1600d5c5da481e01af865c9d36466185b3e0b68ac4b5a23277f4478cc
3
+ size 5176
run-4/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:ba36240ce7e4505d3864ee5746a44018d28b263fd65bd3b7dcb20202ab87ba59
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5bb70b1600d5c5da481e01af865c9d36466185b3e0b68ac4b5a23277f4478cc
3
  size 5176