Junhoee commited on
Commit
60593c6
·
verified ·
1 Parent(s): 9258c92

Guess_Applicant_Information

Browse files
Files changed (4) hide show
  1. README.md +71 -0
  2. config.json +72 -0
  3. model.safetensors +3 -0
  4. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model: monologg/kobigbird-bert-base
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: results
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # results
15
+
16
+ This model is a fine-tuned version of [monologg/kobigbird-bert-base](https://huggingface.co/monologg/kobigbird-bert-base) on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 1.1542
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 5e-05
38
+ - train_batch_size: 16
39
+ - eval_batch_size: 16
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - num_epochs: 3
44
+
45
+ ### Training results
46
+
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:------:|:----:|:---------------:|
49
+ | 1.9046 | 0.1933 | 500 | 1.9136 |
50
+ | 1.7226 | 0.3865 | 1000 | 1.6339 |
51
+ | 1.5727 | 0.5798 | 1500 | 1.5731 |
52
+ | 1.4838 | 0.7731 | 2000 | 1.4854 |
53
+ | 1.3672 | 0.9664 | 2500 | 1.4381 |
54
+ | 1.2094 | 1.1596 | 3000 | 1.3175 |
55
+ | 1.1825 | 1.3529 | 3500 | 1.3117 |
56
+ | 1.1271 | 1.5462 | 4000 | 1.2556 |
57
+ | 1.1158 | 1.7395 | 4500 | 1.2205 |
58
+ | 1.069 | 1.9327 | 5000 | 1.2036 |
59
+ | 0.8221 | 2.1260 | 5500 | 1.2233 |
60
+ | 0.8467 | 2.3193 | 6000 | 1.1583 |
61
+ | 0.8238 | 2.5126 | 6500 | 1.1916 |
62
+ | 0.7993 | 2.7058 | 7000 | 1.1604 |
63
+ | 0.7687 | 2.8991 | 7500 | 1.1542 |
64
+
65
+
66
+ ### Framework versions
67
+
68
+ - Transformers 4.44.2
69
+ - Pytorch 2.4.0
70
+ - Datasets 3.0.0
71
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "monologg/kobigbird-bert-base",
3
+ "architectures": [
4
+ "BigBirdForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "attention_type": "block_sparse",
8
+ "block_size": 64,
9
+ "bos_token_id": 5,
10
+ "classifier_dropout": null,
11
+ "eos_token_id": 6,
12
+ "gradient_checkpointing": false,
13
+ "hidden_act": "gelu_new",
14
+ "hidden_dropout_prob": 0.1,
15
+ "hidden_size": 768,
16
+ "id2label": {
17
+ "0": "LABEL_0",
18
+ "1": "LABEL_1",
19
+ "2": "LABEL_2",
20
+ "3": "LABEL_3",
21
+ "4": "LABEL_4",
22
+ "5": "LABEL_5",
23
+ "6": "LABEL_6",
24
+ "7": "LABEL_7",
25
+ "8": "LABEL_8",
26
+ "9": "LABEL_9",
27
+ "10": "LABEL_10",
28
+ "11": "LABEL_11",
29
+ "12": "LABEL_12",
30
+ "13": "LABEL_13",
31
+ "14": "LABEL_14",
32
+ "15": "LABEL_15"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 3072,
36
+ "label2id": {
37
+ "LABEL_0": 0,
38
+ "LABEL_1": 1,
39
+ "LABEL_10": 10,
40
+ "LABEL_11": 11,
41
+ "LABEL_12": 12,
42
+ "LABEL_13": 13,
43
+ "LABEL_14": 14,
44
+ "LABEL_15": 15,
45
+ "LABEL_2": 2,
46
+ "LABEL_3": 3,
47
+ "LABEL_4": 4,
48
+ "LABEL_5": 5,
49
+ "LABEL_6": 6,
50
+ "LABEL_7": 7,
51
+ "LABEL_8": 8,
52
+ "LABEL_9": 9
53
+ },
54
+ "layer_norm_eps": 1e-12,
55
+ "max_position_embeddings": 4096,
56
+ "model_type": "big_bird",
57
+ "num_attention_heads": 12,
58
+ "num_hidden_layers": 12,
59
+ "num_random_blocks": 3,
60
+ "pad_token_id": 0,
61
+ "position_embedding_type": "absolute",
62
+ "problem_type": "single_label_classification",
63
+ "rescale_embeddings": false,
64
+ "sep_token_id": 3,
65
+ "tokenizer_class": "BertTokenizer",
66
+ "torch_dtype": "float32",
67
+ "transformers_version": "4.44.2",
68
+ "type_vocab_size": 2,
69
+ "use_bias": true,
70
+ "use_cache": true,
71
+ "vocab_size": 32500
72
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b536793ee8c5753592646a064ac8237196e2e73c8768a8ae08d7ab9278b192a8
3
+ size 457450752
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b832a3fe83f346cf7d32a212317973a80fc56750d2a354c97def41360bab505
3
+ size 5112