Hugging Face's logo

eunzzang
/
results

Text Classification
Transformers
TensorBoard
Safetensors
roberta
Generated from Trainer
Model card Files
xet
 Metrics Community
eunzzang commited on
Commit
2ebd495
·
verified ·
1 Parent(s): 38eb138

eunzzang/roberta-base-klue-ynat-classification

Browse files
Files changed (10) hide show
  1. README.md +60 -0
  2. config.json +47 -0
  3. model.safetensors +3 -0
  4. runs/Mar17_06-03-19_2add666987c0/events.out.tfevents.1773727404.2add666987c0.986.0 +3 -0
  5. runs/Mar17_07-04-28_2add666987c0/events.out.tfevents.1773731074.2add666987c0.10252.0 +3 -0
  6. runs/Mar17_07-11-47_2add666987c0/events.out.tfevents.1773731512.2add666987c0.25968.0 +3 -0
  7. runs/Mar17_07-13-59_2add666987c0/events.out.tfevents.1773731643.2add666987c0.25968.1 +3 -0
  8. runs/Mar17_07-16-02_2add666987c0/events.out.tfevents.1773731782.2add666987c0.27497.0 +3 -0
  9. runs/Mar17_07-16-02_2add666987c0/events.out.tfevents.1773732868.2add666987c0.27497.1 +3 -0
  10. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model: klue/roberta-base
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: results
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # results
17
+
18
+ This model is a fine-tuned version of [klue/roberta-base](https://huggingface.co/klue/roberta-base) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.4681
21
+ - Accuracy: 0.856
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 5e-05
41
+ - train_batch_size: 8
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 1
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | 0.5353 | 1.0 | 1250 | 0.5378 | 0.834 |
53
+
54
+
55
+ ### Framework versions
56
+
57
+ - Transformers 4.50.0
58
+ - Pytorch 2.10.0+cu128
59
+ - Datasets 3.5.0
60
+ - Tokenizers 0.21.4
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5",
20
+ "6": "LABEL_6"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "LABEL_0": 0,
26
+ "LABEL_1": 1,
27
+ "LABEL_2": 2,
28
+ "LABEL_3": 3,
29
+ "LABEL_4": 4,
30
+ "LABEL_5": 5,
31
+ "LABEL_6": 6
32
+ },
33
+ "layer_norm_eps": 1e-05,
34
+ "max_position_embeddings": 514,
35
+ "model_type": "roberta",
36
+ "num_attention_heads": 12,
37
+ "num_hidden_layers": 12,
38
+ "pad_token_id": 1,
39
+ "position_embedding_type": "absolute",
40
+ "problem_type": "single_label_classification",
41
+ "tokenizer_class": "BertTokenizer",
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.50.0",
44
+ "type_vocab_size": 1,
45
+ "use_cache": true,
46
+ "vocab_size": 32000
47
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58e4b07567984f40c274ac2a21b97ef972d75c8276c7291327e7efbeeeed2593
3
+ size 442518124
runs/Mar17_06-03-19_2add666987c0/events.out.tfevents.1773727404.2add666987c0.986.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:474b52157338da97b9043937fc1a4256cfe443d92e79084b9114afa4e5c43bf8
3
+ size 4184
runs/Mar17_07-04-28_2add666987c0/events.out.tfevents.1773731074.2add666987c0.10252.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:596925e5ce9e1441945467730aacbd03efaf589baafd106b92c723e8abf6c729
3
+ size 5422
runs/Mar17_07-11-47_2add666987c0/events.out.tfevents.1773731512.2add666987c0.25968.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95c61f25ec58c45f4ad7380e5774119021a8d883ea27b7b89033b29dfa0247aa
3
+ size 5422
runs/Mar17_07-13-59_2add666987c0/events.out.tfevents.1773731643.2add666987c0.25968.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1e8a5eebaedb0a8291b363540e80b86d64631aac3e254bee14365199e683b0c
3
+ size 4184
runs/Mar17_07-16-02_2add666987c0/events.out.tfevents.1773731782.2add666987c0.27497.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb83b389fa8db6b4345a841bdafb14df905c991c77be10f598c31824f38c511a
3
+ size 6518
runs/Mar17_07-16-02_2add666987c0/events.out.tfevents.1773732868.2add666987c0.27497.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cd4981a85da6824ba375a1c3fd96a48707ad2f98a56f6b566653a9247fea716
3
+ size 411
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c628dbf03772e36044b1471eacc39f96035ad4aea298fc6d8a4f2506bb797a0
3
+ size 5777