Hugging Face's logo

jnsu
/
my_model

Fill-Mask
Transformers
TensorBoard
Safetensors
roberta
Generated from Trainer
Model card Files
xet
Metrics Community
jnsu commited on
Commit
4be7a60
·
1 Parent(s): 0376b60

End of training

Browse files
Files changed (6) hide show
  1. README.md +106 -0
  2. config.json +29 -0
  3. model.safetensors +3 -0
  4. runs/Nov20_05-43-58_3dc480989c37/events.out.tfevents.1700459046.3dc480989c37.2469.0 +3 -0
  5. runs/Nov20_05-43-58_3dc480989c37/events.out.tfevents.1700480061.3dc480989c37.2469.1 +3 -0
  6. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: klue/roberta-small
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: my_model
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # my_model
14
+
15
+ This model is a fine-tuned version of [klue/roberta-small](https://huggingface.co/klue/roberta-small) on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 0.4546
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 2e-05
37
+ - train_batch_size: 8
38
+ - eval_batch_size: 8
39
+ - seed: 42
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - num_epochs: 50
43
+ - mixed_precision_training: Native AMP
44
+
45
+ ### Training results
46
+
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:------:|:---------------:|
49
+ | 1.5259 | 1.0 | 4820 | 1.3120 |
50
+ | 1.2116 | 2.0 | 9640 | 1.0790 |
51
+ | 1.0629 | 3.0 | 14460 | 0.9467 |
52
+ | 0.9722 | 4.0 | 19280 | 0.8650 |
53
+ | 0.912 | 5.0 | 24100 | 0.8258 |
54
+ | 0.8514 | 6.0 | 28920 | 0.7731 |
55
+ | 0.8308 | 7.0 | 33740 | 0.7558 |
56
+ | 0.7854 | 8.0 | 38560 | 0.7081 |
57
+ | 0.74 | 9.0 | 43380 | 0.6947 |
58
+ | 0.738 | 10.0 | 48200 | 0.6608 |
59
+ | 0.7335 | 11.0 | 53020 | 0.6485 |
60
+ | 0.675 | 12.0 | 57840 | 0.6354 |
61
+ | 0.6655 | 13.0 | 62660 | 0.6106 |
62
+ | 0.6458 | 14.0 | 67480 | 0.6029 |
63
+ | 0.6256 | 15.0 | 72300 | 0.5821 |
64
+ | 0.6191 | 16.0 | 77120 | 0.5737 |
65
+ | 0.5979 | 17.0 | 81940 | 0.5696 |
66
+ | 0.6 | 18.0 | 86760 | 0.5595 |
67
+ | 0.5812 | 19.0 | 91580 | 0.5317 |
68
+ | 0.5736 | 20.0 | 96400 | 0.5282 |
69
+ | 0.5597 | 21.0 | 101220 | 0.5407 |
70
+ | 0.5665 | 22.0 | 106040 | 0.5404 |
71
+ | 0.5546 | 23.0 | 110860 | 0.5320 |
72
+ | 0.5574 | 24.0 | 115680 | 0.5160 |
73
+ | 0.5346 | 25.0 | 120500 | 0.5220 |
74
+ | 0.5323 | 26.0 | 125320 | 0.5099 |
75
+ | 0.5251 | 27.0 | 130140 | 0.4943 |
76
+ | 0.5254 | 28.0 | 134960 | 0.4907 |
77
+ | 0.5154 | 29.0 | 139780 | 0.4761 |
78
+ | 0.4914 | 30.0 | 144600 | 0.4958 |
79
+ | 0.5085 | 31.0 | 149420 | 0.4595 |
80
+ | 0.4897 | 32.0 | 154240 | 0.4697 |
81
+ | 0.4868 | 33.0 | 159060 | 0.4664 |
82
+ | 0.4779 | 34.0 | 163880 | 0.4684 |
83
+ | 0.4732 | 35.0 | 168700 | 0.4781 |
84
+ | 0.4757 | 36.0 | 173520 | 0.4687 |
85
+ | 0.4702 | 37.0 | 178340 | 0.4484 |
86
+ | 0.4652 | 38.0 | 183160 | 0.4522 |
87
+ | 0.4522 | 39.0 | 187980 | 0.4622 |
88
+ | 0.4559 | 40.0 | 192800 | 0.4546 |
89
+ | 0.4558 | 41.0 | 197620 | 0.4370 |
90
+ | 0.4482 | 42.0 | 202440 | 0.4359 |
91
+ | 0.4451 | 43.0 | 207260 | 0.4467 |
92
+ | 0.4383 | 44.0 | 212080 | 0.4401 |
93
+ | 0.4489 | 45.0 | 216900 | 0.4309 |
94
+ | 0.4347 | 46.0 | 221720 | 0.4256 |
95
+ | 0.4356 | 47.0 | 226540 | 0.4423 |
96
+ | 0.4447 | 48.0 | 231360 | 0.4441 |
97
+ | 0.4324 | 49.0 | 236180 | 0.4405 |
98
+ | 0.4278 | 50.0 | 241000 | 0.4306 |
99
+
100
+
101
+ ### Framework versions
102
+
103
+ - Transformers 4.35.2
104
+ - Pytorch 2.1.0+cu118
105
+ - Datasets 2.15.0
106
+ - Tokenizers 0.15.0
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "klue/roberta-small",
3
+ "architectures": [
4
+ "RobertaForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 514,
18
+ "model_type": "roberta",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 6,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "tokenizer_class": "BertTokenizer",
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.35.2",
26
+ "type_vocab_size": 1,
27
+ "use_cache": true,
28
+ "vocab_size": 32000
29
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94e7e6e9f2555e90822096430ef0a0327eadf57b0bb49fedaac324205fbbe61b
3
+ size 272510264
runs/Nov20_05-43-58_3dc480989c37/events.out.tfevents.1700459046.3dc480989c37.2469.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2393dbdd7d3f8c58fb6cb7ce58029734e5cda1d213ddb1b4f66c1a523edbf284
3
+ size 95426
runs/Nov20_05-43-58_3dc480989c37/events.out.tfevents.1700480061.3dc480989c37.2469.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f38ea56d241c66c9c39c4b8891404ac8de8601557c8765d719a249a435e8a4af
3
+ size 364
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87a04e4b71830c2c689d17291aa3f9a6947901b1a2910c19a568a6dd3c053c07
3
+ size 4600