vesteinn commited on
Commit
82c026a
1 Parent(s): dccd8a7
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
README.md ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: agpl-3.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - conll2003
7
+ metrics:
8
+ - precision
9
+ - recall
10
+ - f1
11
+ - accuracy
12
+ model-index:
13
+ - name: XLMR-ENIS-finetuned-ner
14
+ results:
15
+ - task:
16
+ name: Token Classification
17
+ type: token-classification
18
+ dataset:
19
+ name: conll2003
20
+ type: conll2003
21
+ args: conll2003
22
+ metrics:
23
+ - name: Precision
24
+ type: precision
25
+ value: 0.9398313331170938
26
+ - name: Recall
27
+ type: recall
28
+ value: 0.9517943664285128
29
+ - name: F1
30
+ type: f1
31
+ value: 0.9457750214207026
32
+ - name: Accuracy
33
+ type: accuracy
34
+ value: 0.9853686150987764
35
+ ---
36
+
37
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
38
+ should probably proofread and complete it, then remove this comment. -->
39
+
40
+ # XLMR-ENIS-finetuned-ner
41
+
42
+ This model is a fine-tuned version of [vesteinn/XLMR-ENIS](https://huggingface.co/vesteinn/XLMR-ENIS) on the conll2003 dataset.
43
+ It achieves the following results on the evaluation set:
44
+ - Loss: 0.0671
45
+ - Precision: 0.9398
46
+ - Recall: 0.9518
47
+ - F1: 0.9458
48
+ - Accuracy: 0.9854
49
+
50
+ ## Model description
51
+
52
+ More information needed
53
+
54
+ ## Intended uses & limitations
55
+
56
+ More information needed
57
+
58
+ ## Training and evaluation data
59
+
60
+ More information needed
61
+
62
+ ## Training procedure
63
+
64
+ ### Training hyperparameters
65
+
66
+ The following hyperparameters were used during training:
67
+ - learning_rate: 2e-05
68
+ - train_batch_size: 16
69
+ - eval_batch_size: 16
70
+ - seed: 42
71
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
72
+ - lr_scheduler_type: linear
73
+ - num_epochs: 3
74
+
75
+ ### Training results
76
+
77
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
78
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
79
+ | 0.2825 | 1.0 | 878 | 0.0712 | 0.9220 | 0.9379 | 0.9299 | 0.9815 |
80
+ | 0.0688 | 2.0 | 1756 | 0.0689 | 0.9354 | 0.9477 | 0.9415 | 0.9839 |
81
+ | 0.039 | 3.0 | 2634 | 0.0671 | 0.9398 | 0.9518 | 0.9458 | 0.9854 |
82
+
83
+
84
+ ### Framework versions
85
+
86
+ - Transformers 4.10.3
87
+ - Pytorch 1.9.0+cu102
88
+ - Datasets 1.12.1
89
+ - Tokenizers 0.10.3
config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "vesteinn/XLMR-ENIS",
3
+ "architectures": [
4
+ "XLMRobertaForTokenClassification"
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
+ "id2label": {
15
+ "0": "LABEL_0",
16
+ "1": "LABEL_1",
17
+ "2": "LABEL_2",
18
+ "3": "LABEL_3",
19
+ "4": "LABEL_4",
20
+ "5": "LABEL_5",
21
+ "6": "LABEL_6",
22
+ "7": "LABEL_7",
23
+ "8": "LABEL_8"
24
+ },
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 3072,
27
+ "label2id": {
28
+ "LABEL_0": 0,
29
+ "LABEL_1": 1,
30
+ "LABEL_2": 2,
31
+ "LABEL_3": 3,
32
+ "LABEL_4": 4,
33
+ "LABEL_5": 5,
34
+ "LABEL_6": 6,
35
+ "LABEL_7": 7,
36
+ "LABEL_8": 8
37
+ },
38
+ "layer_norm_eps": 1e-05,
39
+ "max_position_embeddings": 514,
40
+ "model_type": "xlm-roberta",
41
+ "num_attention_heads": 12,
42
+ "num_hidden_layers": 12,
43
+ "pad_token_id": 1,
44
+ "position_embedding_type": "absolute",
45
+ "torch_dtype": "float32",
46
+ "transformers_version": "4.10.3",
47
+ "type_vocab_size": 1,
48
+ "use_cache": true,
49
+ "vocab_size": 50005
50
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee5d8ca01a88f68013a351f7ba5b433bd6e8be3ec0500085abda1f705c9b0966
3
+ size 495533809
runs/Sep27_16-13-59_d02bc503a637/1632759246.3365753/events.out.tfevents.1632759246.d02bc503a637.76.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1266ca46a0b5235d1e0f488048909a80f2fae6c97e8697fbe1d5a983b398c559
3
+ size 4199
runs/Sep27_16-13-59_d02bc503a637/events.out.tfevents.1632759246.d02bc503a637.76.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af22776f3438bb7e0471af632c813ba82f7e73e6ff5cb1531e3d432a982db2aa
3
+ size 5955
runs/Sep27_16-13-59_d02bc503a637/events.out.tfevents.1632760297.d02bc503a637.76.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a38500c6f7fbf92578d5c44c065655b6003ef0a514b4ead79b41a59b0cf272bf
3
+ size 512
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:c52749d5c7749f5022d419681670f40e4915ee91f47ad6a01258a758ddc237c5
3
+ size 2671