Added model

README.md

@@ -0,0 +1,158 @@
+---
+
+license: apache-2.0
+
+tags:
+
+- token-classification
+
+datasets:
+
+- wikiann
+
+metrics:
+
+- precision
+
+- recall
+
+- f1
+
+- accuracy
+
+model-index:
+
+- name: distilroberta-base-ner-wikiann
+
+  results:
+
+  - task:
+
+      name: Token Classification
+
+      type: token-classification
+
+    dataset:
+
+      name: wikiann
+
+      type: wikiann
+
+    metrics:
+
+      - name: Precision
+
+        type: precision
+
+        value: 0.8331921416757433
+
+      - name: Recall
+
+        type: recall
+
+        value: 0.84243586083126
+
+      - name: F1
+
+        type: f1
+
+        value: 0.8377885044416501
+
+      - name: Accuracy
+
+        type: accuracy
+
+        value: 0.91930707459758
+
+---
+
+<!-- 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. -->
+
+# distilroberta-base-ner-wikiann
+
+This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the wikiann dataset.
+
+eval F1-Score: **83,78** 
+
+test F1-Score: **83,76** 
+
+## Model Usage
+
+```python
+
+from transformers import AutoTokenizer, AutoModelForTokenClassification
+
+from transformers import pipeline
+
+tokenizer = AutoTokenizer.from_pretrained("philschmid/distilroberta-base-ner-wikiann")
+
+model = AutoModelForTokenClassification.from_pretrained("philschmid/distilroberta-base-ner-wikiann")
+
+nlp = pipeline("ner", model=model, tokenizer=tokenizer, grouped_entities=True)
+
+example = "Jag heter Per och jag jobbar på KTH"
+
+nlp(example)
+
+```
+<!-- 
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+
+- learning_rate: 4.9086903597787154e-05
+
+- train_batch_size: 32
+
+- eval_batch_size: 16
+
+- seed: 42
+
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+
+- lr_scheduler_type: linear
+
+- num_epochs: 5.0
+
+- mixed_precision_training: Native AMP
+
+### Training results
+
+It achieves the following results on the evaluation set:
+
+- Loss: 0.3156
+
+- Precision: 0.8332
+
+- Recall: 0.8424
+
+- F1: 0.8378
+
+- Accuracy: 0.9193
+
+It achieves the following results on the test set:
+
+- Loss: 0.3023
+
+- Precision: 0.8301
+
+- Recall: 0.8452
+
+- F1: 0.8376
+
+- Accuracy: 0.92
+
+### Framework versions
+
+- Transformers 4.6.1
+
+- Pytorch 1.8.1+cu101
+
+- Datasets 1.6.2
+
+- Tokenizers 0.10.2
+ -->

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9848601595201899,
+    "eval_f1": 0.9434072987346416,
+    "eval_loss": 0.08223789930343628,
+    "eval_precision": 0.939307624890447,
+    "eval_recall": 0.9475429160834009,
+    "eval_runtime": 148.4881,
+    "eval_samples": 10000,
+    "eval_samples_per_second": 67.345,
+    "eval_steps_per_second": 8.418,
+    "train_loss": 0.06440118865966797,
+    "train_runtime": 4082.003,
+    "train_samples": 20000,
+    "train_samples_per_second": 14.699,
+    "train_steps_per_second": 1.837
+}

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "flax-community/nordic-roberta-wiki",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "finetuning_task": "ner",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": 0,
+    "1": 1,
+    "2": 2,
+    "3": 3,
+    "4": 4,
+    "5": 5,
+    "6": 6
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1,
+    "2": 2,
+    "3": 3,
+    "4": 4,
+    "5": 5,
+    "6": 6
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9abff09592158fcd4c18cce638554873ef69517584f1f4fb07e7ad355cff9e3e
+size 496323633

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": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": true, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "special_tokens_map_file": null, "name_or_path": "flax-community/nordic-roberta-wiki", "tokenizer_class": "RobertaTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.06440118865966797,
+    "train_runtime": 4082.003,
+    "train_samples": 20000,
+    "train_samples_per_second": 14.699,
+    "train_steps_per_second": 1.837
+}

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 7500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 0.2034,
+      "step": 500
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 0.1179,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4e-05,
+      "loss": 0.1084,
+      "step": 1500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 0.1066,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.0912,
+      "step": 2500
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 3e-05,
+      "loss": 0.0487,
+      "step": 3000
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.0465,
+      "step": 3500
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 0.0521,
+      "step": 4000
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 2e-05,
+      "loss": 0.0455,
+      "step": 4500
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.0466,
+      "step": 5000
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.0165,
+      "step": 5500
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 1e-05,
+      "loss": 0.0222,
+      "step": 6000
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.0196,
+      "step": 6500
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.0219,
+      "step": 7000
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.0189,
+      "step": 7500
+    },
+    {
+      "epoch": 3.0,
+      "step": 7500,
+      "total_flos": 741030271017696.0,
+      "train_loss": 0.06440118865966797,
+      "train_runtime": 4082.003,
+      "train_samples_per_second": 14.699,
+      "train_steps_per_second": 1.837
+    }
+  ],
+  "max_steps": 7500,
+  "num_train_epochs": 3,
+  "total_flos": 741030271017696.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9712f30498e58843c4a1c5253bfc62ddc1e6bab728243ca91311aed3aac5fa5
+size 2671