vesteinn commited on
Commit
1892718
1 Parent(s): 242b9fc
.gitignore ADDED
@@ -0,0 +1 @@
 
1
+ checkpoint-*/
README.md ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: agpl-3.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - glue
7
+ metrics:
8
+ - matthews_correlation
9
+ model-index:
10
+ - name: XLMR-ENIS-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
+ metrics:
20
+ - name: Matthews Correlation
21
+ type: matthews_correlation
22
+ value: 0.6306425398187112
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
+ # XLMR-ENIS-finetuned-cola
29
+
30
+ This model is a fine-tuned version of [vesteinn/XLMR-ENIS](https://huggingface.co/vesteinn/XLMR-ENIS) on the glue dataset.
31
+ It achieves the following results on the evaluation set:
32
+ - Loss: 0.7311
33
+ - Matthews Correlation: 0.6306
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: 5
59
+
60
+ ### Training results
61
+
62
+ | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
63
+ |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
64
+ | 0.5216 | 1.0 | 535 | 0.5836 | 0.4855 |
65
+ | 0.3518 | 2.0 | 1070 | 0.4426 | 0.5962 |
66
+ | 0.2538 | 3.0 | 1605 | 0.5091 | 0.6110 |
67
+ | 0.1895 | 4.0 | 2140 | 0.6955 | 0.6136 |
68
+ | 0.1653 | 5.0 | 2675 | 0.7311 | 0.6306 |
69
+
70
+
71
+ ### Framework versions
72
+
73
+ - Transformers 4.10.3
74
+ - Pytorch 1.9.0+cu102
75
+ - Datasets 1.12.1
76
+ - Tokenizers 0.10.3
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "vesteinn/XLMR-ENIS",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
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": "xlm-roberta",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "problem_type": "single_label_classification",
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.10.3",
26
+ "type_vocab_size": 1,
27
+ "use_cache": true,
28
+ "vocab_size": 50005
29
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:260d03a9e6834a9d88e40f64f0ae0b89fb74f742def15f570f0baa1bae332369
3
+ size 497875373
runs/Sep27_15-32-17_1380f0078246/1632756753.8818982/events.out.tfevents.1632756753.1380f0078246.75.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6ce090e5d9fbd9af372dc47fe0a44158c3978d538303f46b932eea3d9003a1b
3
+ size 4222
runs/Sep27_15-32-17_1380f0078246/events.out.tfevents.1632756753.1380f0078246.75.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f413a7cdc4466264edcc151b3cd3d50f0816eb4d812d62ea4f4030b25ff55f6
3
+ size 5853
runs/Sep27_15-32-17_1380f0078246/events.out.tfevents.1632757458.1380f0078246.75.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a9d6b928a070a64c2c75cd41958aa2e2c2e6b3d0500cb5e82ac19e3133edd96
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": "<mask>"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "special_tokens_map_file": "/root/.cache/huggingface/transformers/0a741e436e3f4773f4fbd20aaad263d91214fcbc60d3b45bb6e39f0d745dba77.0dc5b1041f62041ebbd23b1297f2f573769d5c97d8b7c28180ec86b8f6185aa8", "name_or_path": "vesteinn/XLMR-ENIS", "tokenizer_class": "XLMRobertaTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c5ddc62e5d25b2b3a59946439b6d2a13785c5f377c3411e7cd68c62bb790867
3
+ size 2671