Hugging Face's logo

xuancoblab2023
/
Bert_tinybert-distilled

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
xuancoblab2023 commited on
Commit
55eabbf
•
1 Parent(s): feb83e0

Training in progress, epoch 1

Browse files
Files changed (16) hide show
  1. logs/events.out.tfevents.1721967385.98acc6742512.15262.40 +2 -2
  2. logs/events.out.tfevents.1721967475.98acc6742512.15262.41 +3 -0
  3. logs/events.out.tfevents.1721967505.98acc6742512.15262.42 +3 -0
  4. model.safetensors +1 -1
  5. run-41/checkpoint-172/config.json +34 -0
  6. run-41/checkpoint-172/model.safetensors +3 -0
  7. run-41/checkpoint-172/optimizer.pt +3 -0
  8. run-41/checkpoint-172/rng_state.pth +3 -0
  9. run-41/checkpoint-172/scheduler.pt +3 -0
  10. run-41/checkpoint-172/special_tokens_map.json +7 -0
  11. run-41/checkpoint-172/tokenizer.json +0 -0
  12. run-41/checkpoint-172/tokenizer_config.json +55 -0
  13. run-41/checkpoint-172/trainer_state.json +58 -0
  14. run-41/checkpoint-172/training_args.bin +3 -0
  15. run-41/checkpoint-172/vocab.txt +0 -0
  16. training_args.bin +1 -1
logs/events.out.tfevents.1721967385.98acc6742512.15262.40 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38f2fc42cfaedddfe181e99076eba131e92ff07915a3d69c3c244b1ab08efabb
3
- size 6433
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d762be8b106646c9e7a75fbf5494df7bba2cb35c5ea0fb0414ff14dd3624b23
3
+ size 7158
logs/events.out.tfevents.1721967475.98acc6742512.15262.41 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50da8863c1dc93c7d3daf039dd2c7cd567913968eed30f224fdac26fb685c6c6
3
+ size 5707
logs/events.out.tfevents.1721967505.98acc6742512.15262.42 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8eb7e97c742e63bb979323aae0a1f20ff8db4f5b87b2619675eba965607623f
3
+ size 5706
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aece714db1ad88f374468affe7d78ad2c676b47a3f859854fdaa2e9e4263e9b2
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:043c220a9817e02b138a51abc1cde0d0fdc6209b6324544d66f40377bd4a2311
3
  size 17549312
run-41/checkpoint-172/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": "4.43.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-41/checkpoint-172/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:043c220a9817e02b138a51abc1cde0d0fdc6209b6324544d66f40377bd4a2311
3
+ size 17549312
run-41/checkpoint-172/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55da2f71d53d7bb277707b28e9f1788122bae20e3d623665be3c9f7e03834dc7
3
+ size 35123898
run-41/checkpoint-172/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b99cb6263c36c5c191e9bbbef2d3167790018df547076ed69608752e2b4353d4
3
+ size 14308
run-41/checkpoint-172/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55d9b80eeb3fa397f5dc3816c18a650bb3c7806c273579202f3a2d400ec46e1d
3
+ size 1064
run-41/checkpoint-172/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-41/checkpoint-172/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-41/checkpoint-172/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-41/checkpoint-172/trainer_state.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7413333333333333,
3
+ "best_model_checkpoint": "Bert_tinybert-distilled/run-41/checkpoint-172",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 172,
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": 1.023292899131775,
14
+ "learning_rate": 0.00013414703695256762,
15
+ "loss": 0.5108,
16
+ "step": 172
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_AUC": 0.8195857777777777,
21
+ "eval_BAC": 0.7413333333333334,
22
+ "eval_MCC": 0.4826941273803735,
23
+ "eval_PR_AUC": 0.7801986097000582,
24
+ "eval_accuracy": 0.7413333333333333,
25
+ "eval_loss": 0.4535185992717743,
26
+ "eval_runtime": 6.2428,
27
+ "eval_samples_per_second": 240.277,
28
+ "eval_steps_per_second": 7.529,
29
+ "step": 172
30
+ }
31
+ ],
32
+ "logging_steps": 500,
33
+ "max_steps": 1376,
34
+ "num_input_tokens_seen": 0,
35
+ "num_train_epochs": 8,
36
+ "save_steps": 500,
37
+ "stateful_callbacks": {
38
+ "TrainerControl": {
39
+ "args": {
40
+ "should_epoch_stop": false,
41
+ "should_evaluate": false,
42
+ "should_log": false,
43
+ "should_save": true,
44
+ "should_training_stop": false
45
+ },
46
+ "attributes": {}
47
+ }
48
+ },
49
+ "total_flos": 450377730000.0,
50
+ "train_batch_size": 32,
51
+ "trial_name": null,
52
+ "trial_params": {
53
+ "alpha": 0.7837073808557267,
54
+ "learning_rate": 0.000153310899374363,
55
+ "num_train_epochs": 8,
56
+ "temperature": 5
57
+ }
58
+ }
run-41/checkpoint-172/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b63a069bb5435af15d718ff7191dbe33ed43dec9bc5dfdfded6fbe4bb0f55cbe
3
+ size 5240
run-41/checkpoint-172/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 sha256:9e8a1be64d362b369012eed476baffc2d06787e5ee79078bb527d723978136e8
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b63a069bb5435af15d718ff7191dbe33ed43dec9bc5dfdfded6fbe4bb0f55cbe
3
  size 5240