Hugging Face's logo

joseph10
/
tiny-bert-sst2-distilled

Text Classification
Transformers
TensorBoard
Safetensors
bert
text-embeddings-inference
Model card Files
xet
 Metrics Community
joseph10 commited on
Commit
2c689c1
·
1 Parent(s): 70516f0

Training in progress, epoch 7

Browse files
Files changed (13) hide show
  1. logs/events.out.tfevents.1701760669.joseph_legion.10272.19 +2 -2
  2. model.safetensors +1 -1
  3. run-18/checkpoint-3689/config.json +34 -0
  4. run-18/checkpoint-3689/model.safetensors +3 -0
  5. run-18/checkpoint-3689/optimizer.pt +3 -0
  6. run-18/checkpoint-3689/rng_state.pth +3 -0
  7. run-18/checkpoint-3689/scheduler.pt +3 -0
  8. run-18/checkpoint-3689/special_tokens_map.json +7 -0
  9. run-18/checkpoint-3689/tokenizer.json +0 -0
  10. run-18/checkpoint-3689/tokenizer_config.json +57 -0
  11. run-18/checkpoint-3689/trainer_state.json +129 -0
  12. run-18/checkpoint-3689/training_args.bin +3 -0
  13. run-18/checkpoint-3689/vocab.txt +0 -0
logs/events.out.tfevents.1701760669.joseph_legion.10272.19 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e51a6d541b4d03452ea4300182a467d632779502e87ddeff5e1e961fd10481f9
3
- size 6695
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eacea7a19fcc2631e457b3cf03b4ab72e98d56e1573110a93189a5de9bcbedac
3
+ size 7655
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d15299e3bd40b31f6491e1a6d91e260c63525153ab29bbd4f19509433c8aff34
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ed9c78ec1f0e088f447238bfad612262522e2912abe0a54c53e99e2bd60cfd4
3
  size 17549312
run-18/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": "4.35.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-18/checkpoint-3689/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ed9c78ec1f0e088f447238bfad612262522e2912abe0a54c53e99e2bd60cfd4
3
+ size 17549312
run-18/checkpoint-3689/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e4236d076cfa57b6fe73a39f1502357d7145ebb6a1bcad7c19359a33f259ba7
3
+ size 35123898
run-18/checkpoint-3689/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc20784aa2bd9699f06a4a044cc4eca9a0a372503deca38139c95e84a56ccd04
3
+ size 14308
run-18/checkpoint-3689/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b45035388b47bd3a5de21e9c6ab3d86d1d74e866f28d5858d1f29ad9d31be5f
3
+ size 1064
run-18/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-18/checkpoint-3689/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-18/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-18/checkpoint-3689/trainer_state.json ADDED
@@ -0,0 +1,129 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8325688073394495,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled\\run-18\\checkpoint-1054",
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
+ "learning_rate": 0.00011463680857374876,
14
+ "loss": 1.2587,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.819954128440367,
20
+ "eval_loss": 1.0965343713760376,
21
+ "eval_runtime": 1.7615,
22
+ "eval_samples_per_second": 495.026,
23
+ "eval_steps_per_second": 3.974,
24
+ "step": 527
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 0.00010030720750203018,
29
+ "loss": 0.6372,
30
+ "step": 1054
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8325688073394495,
35
+ "eval_loss": 1.0634759664535522,
36
+ "eval_runtime": 1.8008,
37
+ "eval_samples_per_second": 484.238,
38
+ "eval_steps_per_second": 3.887,
39
+ "step": 1054
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 8.597760643031157e-05,
44
+ "loss": 0.481,
45
+ "step": 1581
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.8211009174311926,
50
+ "eval_loss": 1.1469666957855225,
51
+ "eval_runtime": 1.806,
52
+ "eval_samples_per_second": 482.838,
53
+ "eval_steps_per_second": 3.876,
54
+ "step": 1581
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 7.164800535859298e-05,
59
+ "loss": 0.3938,
60
+ "step": 2108
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.8291284403669725,
65
+ "eval_loss": 1.240983009338379,
66
+ "eval_runtime": 1.7946,
67
+ "eval_samples_per_second": 485.909,
68
+ "eval_steps_per_second": 3.901,
69
+ "step": 2108
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "learning_rate": 5.731840428687438e-05,
74
+ "loss": 0.3439,
75
+ "step": 2635
76
+ },
77
+ {
78
+ "epoch": 5.0,
79
+ "eval_accuracy": 0.8188073394495413,
80
+ "eval_loss": 1.2216026782989502,
81
+ "eval_runtime": 1.7815,
82
+ "eval_samples_per_second": 489.477,
83
+ "eval_steps_per_second": 3.929,
84
+ "step": 2635
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "learning_rate": 4.2988803215155787e-05,
89
+ "loss": 0.3056,
90
+ "step": 3162
91
+ },
92
+ {
93
+ "epoch": 6.0,
94
+ "eval_accuracy": 0.8279816513761468,
95
+ "eval_loss": 1.2263576984405518,
96
+ "eval_runtime": 1.7901,
97
+ "eval_samples_per_second": 487.134,
98
+ "eval_steps_per_second": 3.91,
99
+ "step": 3162
100
+ },
101
+ {
102
+ "epoch": 7.0,
103
+ "learning_rate": 2.865920214343719e-05,
104
+ "loss": 0.2772,
105
+ "step": 3689
106
+ },
107
+ {
108
+ "epoch": 7.0,
109
+ "eval_accuracy": 0.8302752293577982,
110
+ "eval_loss": 1.2873445749282837,
111
+ "eval_runtime": 1.8403,
112
+ "eval_samples_per_second": 473.833,
113
+ "eval_steps_per_second": 3.804,
114
+ "step": 3689
115
+ }
116
+ ],
117
+ "logging_steps": 500,
118
+ "max_steps": 4743,
119
+ "num_train_epochs": 9,
120
+ "save_steps": 500,
121
+ "total_flos": 56626835675700.0,
122
+ "trial_name": null,
123
+ "trial_params": {
124
+ "alpha": 0.612333452003034,
125
+ "learning_rate": 0.00012896640964546737,
126
+ "num_train_epochs": 9,
127
+ "temperature": 21
128
+ }
129
+ }
run-18/checkpoint-3689/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d11ae7f69a6836e22ab7ce08bf09b6029ed79c5f0a056488527f9d7fd818e4b8
3
+ size 4664
run-18/checkpoint-3689/vocab.txt ADDED
The diff for this file is too large to render. See raw diff