jxuhf commited on
Commit
5305a1f
1 Parent(s): 9cade1d
.gitignore ADDED
@@ -0,0 +1 @@
 
1
+ checkpoint-*/
README.md ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - glue
7
+ metrics:
8
+ - matthews_correlation
9
+ model_index:
10
+ - name: roberta-base-finetuned-cola
11
+ results:
12
+ - task:
13
+ name: Text Classification
14
+ type: text-classification
15
+ dataset:
16
+ name: glue
17
+ type: glue
18
+ args: cola
19
+ metric:
20
+ name: Matthews Correlation
21
+ type: matthews_correlation
22
+ value: 0.557882735147727
23
+ ---
24
+
25
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
26
+ should probably proofread and complete it, then remove this comment. -->
27
+
28
+ # roberta-base-finetuned-cola
29
+
30
+ This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the glue dataset.
31
+ It achieves the following results on the evaluation set:
32
+ - Loss: 0.4716
33
+ - Matthews Correlation: 0.5579
34
+
35
+ ## Model description
36
+
37
+ More information needed
38
+
39
+ ## Intended uses & limitations
40
+
41
+ More information needed
42
+
43
+ ## Training and evaluation data
44
+
45
+ More information needed
46
+
47
+ ## Training procedure
48
+
49
+ ### Training hyperparameters
50
+
51
+ The following hyperparameters were used during training:
52
+ - learning_rate: 2e-05
53
+ - train_batch_size: 16
54
+ - eval_batch_size: 16
55
+ - seed: 42
56
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
57
+ - lr_scheduler_type: linear
58
+ - num_epochs: 2
59
+
60
+ ### Training results
61
+
62
+ | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
63
+ |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
64
+ | 0.4981 | 1.0 | 535 | 0.5162 | 0.5081 |
65
+ | 0.314 | 2.0 | 1070 | 0.4716 | 0.5579 |
66
+
67
+
68
+ ### Framework versions
69
+
70
+ - Transformers 4.9.0
71
+ - Pytorch 1.9.0+cu102
72
+ - Datasets 1.10.2
73
+ - Tokenizers 0.10.3
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 2,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "problem_type": "single_label_classification",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.9.0",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 50265
28
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f984d6d845a14f8b47b6c1195d32788b46a1da497204addecec1139e60e53bee
3
+ size 498671277
runs/Jul23_19-11-45_a081e161bb08/1627067532.9195855/events.out.tfevents.1627067532.a081e161bb08.62.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:478f3f85a7f66db4667b64d1a0adc9d5f8b1e948d442936bfbe3f18198632a7c
3
+ size 4210
runs/Jul23_19-11-45_a081e161bb08/events.out.tfevents.1627067532.a081e161bb08.62.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32d7656e29eb22e69efdcd751ded757cd69ca1e656c1dcbfa34f82993e08f42d
3
+ size 4319
runs/Jul23_19-11-45_a081e161bb08/events.out.tfevents.1627073618.a081e161bb08.62.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f54d15250a5b73dd70db6d7bb5376e02bfc48a778d1d258352821a61abad357
3
+ size 375
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base", "tokenizer_class": "RobertaTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:088b8f634bdedf3c9f8f8a8e3ed5f21c469caad1331c9637b464f43a35821970
3
+ size 2671
vocab.json ADDED
The diff for this file is too large to render. See raw diff