Upload TFXLMRobertaForTokenClassification

README.md

@@ -0,0 +1,48 @@
+---
+license: mit
+tags:
+- generated_from_keras_callback
+model-index:
+- name: fourth_iteration_model
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information Keras had access to. You should
+probably proofread and complete it, then remove this comment. -->
+
+# fourth_iteration_model
+
+This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+
+
+## 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:
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 65805, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
+- training_precision: mixed_float16
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.25.1
+- TensorFlow 2.6.5
+- Datasets 2.3.2
+- Tokenizers 0.13.2

config.json

@@ -0,0 +1,65 @@
+{
+  "_name_or_path": "xlm-roberta-base",
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-occupation",
+    "10": "I-nace_code",
+    "11": "B-location",
+    "12": "I-location",
+    "13": "B-emplyoment-/contract_type",
+    "14": "I-emplyoment-/contract_type",
+    "15": "B-skill",
+    "16": "I-skill",
+    "2": "I-occupation",
+    "3": "B-company_name",
+    "4": "I-company_name",
+    "5": "B-working_type",
+    "6": "I-working_type",
+    "7": "B-experience/seniority",
+    "8": "I-experience/seniority",
+    "9": "B-nace_code"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-company_name": "3",
+    "B-emplyoment-/contract_type": "13",
+    "B-experience/seniority": "7",
+    "B-location": "11",
+    "B-nace_code": "9",
+    "B-occupation": "1",
+    "B-skill": "15",
+    "B-working_type": "5",
+    "I-company_name": "4",
+    "I-emplyoment-/contract_type": "14",
+    "I-experience/seniority": "8",
+    "I-location": "12",
+    "I-nace_code": "10",
+    "I-occupation": "2",
+    "I-skill": "16",
+    "I-working_type": "6",
+    "O": "0"
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.25.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb596f6477bd91b02ca31cdb9e92eaaec11365ba02b333df39f455343ebe5fbc
+size 1110152336