takedarn commited on
Commit
3aa50a2
·
verified ·
1 Parent(s): 12d76c0

Upload fine-tuned model

Browse files
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 128,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 512,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 2,
17
+ "num_hidden_layers": 2,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "transformers_version": "4.56.0",
21
+ "type_vocab_size": 2,
22
+ "use_cache": true,
23
+ "vocab_size": 30522
24
+ }
evaluation_validation_wnli.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "task": "wnli",
3
+ "split": "validation",
4
+ "model_path": "/home/ubuntu/master-research/not-trust-quivalent/models/wnli/prajjwal1-bert-tiny",
5
+ "metrics": {
6
+ "accuracy": 0.5633802816901409
7
+ },
8
+ "loss": 0.6922902266184489,
9
+ "total_examples": 71,
10
+ "evaluation_time": 0.4282684326171875
11
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b91271eb1ba82a64ca623240aa7562fec6560338ed2ec6d8f6732833d0284a62
3
+ size 17549312
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
+ }
summary.txt ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ =======================================
2
+ Model Training Summary
3
+ =======================================
4
+ Model: prajjwal1/bert-tiny
5
+ Task: wnli
6
+ Training Date: Sat Sep 6 02:53:11 PM JST 2025
7
+
8
+ Hyperparameters:
9
+ - Epochs: 5
10
+ - Batch Size: 32
11
+ - Learning Rate: 2e-5
12
+ - Warmup Steps: 200
13
+ - Weight Decay: 0.01
14
+ - Max Sequence Length: 128
15
+
16
+ Training Status: SUCCESS
17
+ Job: 15/15
18
+
19
+ Model Directory: /home/ubuntu/master-research/not-trust-quivalent/models/wnli/prajjwal1-bert-tiny
20
+ Script Path: /home/ubuntu/master-research/not-trust-quivalent/src/finetune/train.py
21
+ Output Directory: /home/ubuntu/master-research/not-trust-quivalent/models
22
+
23
+ =======================================
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
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
+ }
training_summary.txt ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ Task: wnli
2
+ Model: prajjwal1/bert-tiny
3
+ Epochs: 5
4
+ Best val_loss: 0.6942809224128723
5
+ Best checkpoint: /home/ubuntu/master-research/not-trust-quivalent/models/checkpoints/wnli-best-00-0.6943.ckpt
6
+ Training completed at: 2025-09-06 14:53:07.500323
vocab.txt ADDED
The diff for this file is too large to render. See raw diff