Upload TFRobertaForTokenClassification

README.md

@@ -1,3 +1,58 @@
 ---
-license: apache-2.0
+license: mit
+base_model: FacebookAI/roberta-large
+tags:
+- generated_from_keras_callback
+model-index:
+- name: ner-test
+  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. -->
+
+# ner-test
+
+This model is a fine-tuned version of [FacebookAI/roberta-large](https://huggingface.co/FacebookAI/roberta-large) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 0.1164
+- Validation Loss: 0.0878
+- Train Precision: 0.8442
+- Train Recall: 0.8358
+- Train F1: 0.8400
+- Train Accuracy: 0.9718
+- Epoch: 0
+
+## 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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 4795, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_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: float32
+
+### Training results
+
+| Train Loss | Validation Loss | Train Precision | Train Recall | Train F1 | Train Accuracy | Epoch |
+|:----------:|:---------------:|:---------------:|:------------:|:--------:|:--------------:|:-----:|
+| 0.1164     | 0.0878          | 0.8442          | 0.8358       | 0.8400   | 0.9718         | 0     |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- TensorFlow 2.15.0
+- Datasets 2.17.1
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,64 @@
+{
+  "_name_or_path": "FacebookAI/roberta-large",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "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": 1024,
+  "id2label": {
+    "0": "O",
+    "1": "B-eve",
+    "2": "I-eve",
+    "3": "B-org",
+    "4": "I-org",
+    "5": "B-gpe",
+    "6": "I-gpe",
+    "7": "B-geo",
+    "8": "I-geo",
+    "9": "B-nat",
+    "10": "I-nat",
+    "11": "B-per",
+    "12": "I-per",
+    "13": "B-art",
+    "14": "I-art",
+    "15": "B-tim",
+    "16": "I-tim"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-art": 13,
+    "B-eve": 1,
+    "B-geo": 7,
+    "B-gpe": 5,
+    "B-nat": 9,
+    "B-org": 3,
+    "B-per": 11,
+    "B-tim": 15,
+    "I-art": 14,
+    "I-eve": 2,
+    "I-geo": 8,
+    "I-gpe": 6,
+    "I-nat": 10,
+    "I-org": 4,
+    "I-per": 12,
+    "I-tim": 16,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef7f2e05428de7a6b0785660dc009450f1fdcc1d8027d314a4170105d4d93e9f
+size 1417861992