add model

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,89 @@
+---
+license: agpl-3.0
+tags:
+- generated_from_trainer
+datasets:
+- conll2003
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: XLMR-ENIS-finetuned-ner
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: conll2003
+      type: conll2003
+      args: conll2003
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.9398313331170938
+    - name: Recall
+      type: recall
+      value: 0.9517943664285128
+    - name: F1
+      type: f1
+      value: 0.9457750214207026
+    - name: Accuracy
+      type: accuracy
+      value: 0.9853686150987764
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# XLMR-ENIS-finetuned-ner
+
+This model is a fine-tuned version of [vesteinn/XLMR-ENIS](https://huggingface.co/vesteinn/XLMR-ENIS) on the conll2003 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0671
+- Precision: 0.9398
+- Recall: 0.9518
+- F1: 0.9458
+- Accuracy: 0.9854
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.2825        | 1.0   | 878  | 0.0712          | 0.9220    | 0.9379 | 0.9299 | 0.9815   |
+| 0.0688        | 2.0   | 1756 | 0.0689          | 0.9354    | 0.9477 | 0.9415 | 0.9839   |
+| 0.039         | 3.0   | 2634 | 0.0671          | 0.9398    | 0.9518 | 0.9458 | 0.9854   |
+
+
+### Framework versions
+
+- Transformers 4.10.3
+- Pytorch 1.9.0+cu102
+- Datasets 1.12.1
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "vesteinn/XLMR-ENIS",
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50005
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee5d8ca01a88f68013a351f7ba5b433bd6e8be3ec0500085abda1f705c9b0966
+size 495533809

runs/Sep27_16-13-59_d02bc503a637/1632759246.3365753/events.out.tfevents.1632759246.d02bc503a637.76.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1266ca46a0b5235d1e0f488048909a80f2fae6c97e8697fbe1d5a983b398c559
+size 4199

runs/Sep27_16-13-59_d02bc503a637/events.out.tfevents.1632759246.d02bc503a637.76.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af22776f3438bb7e0471af632c813ba82f7e73e6ff5cb1531e3d432a982db2aa
+size 5955

runs/Sep27_16-13-59_d02bc503a637/events.out.tfevents.1632760297.d02bc503a637.76.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a38500c6f7fbf92578d5c44c065655b6003ef0a514b4ead79b41a59b0cf272bf
+size 512

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>"}

tokenizer_config.json

@@ -0,0 +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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c52749d5c7749f5022d419681670f40e4915ee91f47ad6a01258a758ddc237c5
+size 2671