Upload TFBertForTokenClassification

README.md

@@ -0,0 +1,60 @@
+---
+license: apache-2.0
+base_model: bert-base-uncased
+tags:
+- generated_from_keras_callback
+model-index:
+- name: drugobert_spec
+  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. -->
+
+# drugobert_spec
+
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 0.2531
+- Train Precision: 0.4705
+- Train Recall: 0.2187
+- Train F1: 0.2986
+- Train Accuracy: 0.9374
+- Epoch: 3
+
+## 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': 177, '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 | Train Precision | Train Recall | Train F1 | Train Accuracy | Epoch |
+|:----------:|:---------------:|:------------:|:--------:|:--------------:|:-----:|
+| 0.5777     | 0.0             | 0.0          | 0.0      | 0.9210         | 0     |
+| 0.3068     | 0.5824          | 0.1243       | 0.2049   | 0.9306         | 1     |
+| 0.2659     | 0.4706          | 0.2191       | 0.2990   | 0.9374         | 2     |
+| 0.2531     | 0.4705          | 0.2187       | 0.2986   | 0.9374         | 3     |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- TensorFlow 2.14.0
+- Datasets 2.16.1
+- Tokenizers 0.15.1

config.json

@@ -0,0 +1,51 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-fentanyl",
+    "2": "B-mushrooms",
+    "3": "B-marijuana",
+    "4": "B-lsd",
+    "5": "B-heroin",
+    "6": "B-cocaine",
+    "7": "B-amphetamine",
+    "8": "B-ketamine",
+    "9": "B-mdma",
+    "10": "B-methamphetamine"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-amphetamine": 7,
+    "B-cocaine": 6,
+    "B-fentanyl": 1,
+    "B-heroin": 5,
+    "B-ketamine": 8,
+    "B-lsd": 4,
+    "B-marijuana": 3,
+    "B-mdma": 9,
+    "B-methamphetamine": 10,
+    "B-mushrooms": 2,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8158afb2a21b93fcb080247dfe0413bb80cd9b90b6c2c7f0c526d850eb58271
+size 435886068