abdulllah01 commited on
Commit
76a5aef
·
verified ·
1 Parent(s): 42e79de

Upload java KD Optuna tinyBERT checkpoint

Browse files
checkpoints/java/config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "cell": {},
7
+ "classifier_dropout": null,
8
+ "dtype": "float32",
9
+ "emb_size": 312,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 312,
13
+ "id2label": {
14
+ "0": "summary",
15
+ "1": "Ownership",
16
+ "2": "Expand",
17
+ "3": "usage",
18
+ "4": "Pointer",
19
+ "5": "deprecation",
20
+ "6": "rational"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 1200,
24
+ "label2id": {
25
+ "Expand": 2,
26
+ "Ownership": 1,
27
+ "Pointer": 4,
28
+ "deprecation": 5,
29
+ "rational": 6,
30
+ "summary": 0,
31
+ "usage": 3
32
+ },
33
+ "layer_norm_eps": 1e-12,
34
+ "max_position_embeddings": 512,
35
+ "model_type": "bert",
36
+ "num_attention_heads": 12,
37
+ "num_hidden_layers": 4,
38
+ "pad_token_id": 0,
39
+ "position_embedding_type": "absolute",
40
+ "pre_trained": "",
41
+ "problem_type": "multi_label_classification",
42
+ "structure": [],
43
+ "transformers_version": "4.57.3",
44
+ "type_vocab_size": 2,
45
+ "use_cache": true,
46
+ "vocab_size": 30522
47
+ }
checkpoints/java/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e485433726cdf70fad60bf95efce8e5003982fc744e2cbbf317eb8a2ac7f06a
3
+ size 57418068
checkpoints/java/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
+ }
checkpoints/java/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/java/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
checkpoints/java/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:819270d41da27fa6be6a9d52bc28e54d9262004cfef66b708c2c5f98ae588c80
3
+ size 5969
checkpoints/java/trial_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "lr": 3.4075797197083935e-05,
3
+ "batch_size": 32,
4
+ "epochs": 13,
5
+ "temperature": 3.1294846623568833,
6
+ "lambda_hard": 0.12043941050403753
7
+ }
checkpoints/java/trial_metrics.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eval_loss": 6.039793491363525,
3
+ "eval_macro_f1": 0.7331317403287982,
4
+ "eval_micro_f1": 0.815702479338843,
5
+ "eval_macro_precision": 0.7664941745813351,
6
+ "eval_macro_recall": 0.7112470380951198,
7
+ "eval_thresholds": {
8
+ "summary": 0.5000000000000001,
9
+ "Ownership": 0.4800000000000001,
10
+ "Expand": 0.56,
11
+ "usage": 0.5000000000000001,
12
+ "Pointer": 0.5000000000000001,
13
+ "deprecation": 0.42000000000000004,
14
+ "rational": 0.5200000000000001
15
+ },
16
+ "eval_f1_summary": 0.8860759493670886,
17
+ "eval_f1_Ownership": 1.0,
18
+ "eval_f1_Expand": 0.34065934065934067,
19
+ "eval_f1_usage": 0.8503649635036497,
20
+ "eval_f1_Pointer": 0.8979591836734694,
21
+ "eval_f1_deprecation": 0.8235294117647058,
22
+ "eval_f1_rational": 0.3333333333333333,
23
+ "eval_runtime": 0.3898,
24
+ "eval_samples_per_second": 3081.05,
25
+ "eval_steps_per_second": 97.485,
26
+ "epoch": 13.0
27
+ }
checkpoints/java/vocab.txt ADDED
The diff for this file is too large to render. See raw diff