Training in progress epoch 0

README.md

@@ -0,0 +1,58 @@
+---
+license: apache-2.0
+base_model: distilbert/distilroberta-base
+tags:
+- generated_from_keras_callback
+model-index:
+- name: marksusol/distilroberta-base-finetuned-ner
+  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. -->
+
+# marksusol/distilroberta-base-finetuned-ner
+
+This model is a fine-tuned version of [distilbert/distilroberta-base](https://huggingface.co/distilbert/distilroberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 0.0609
+- Validation Loss: 0.0080
+- Train Precision: 0.9291
+- Train Recall: 0.9597
+- Train F1: 0.9585
+- Train Accuracy: 0.9985
+- 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': 5620, '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 |
+|:----------:|:---------------:|:---------------:|:------------:|:--------:|:--------------:|:-----:|
+| 0.0609     | 0.0080          | 0.9291          | 0.9597       | 0.9585   | 0.9985         | 0     |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- TensorFlow 2.15.0
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,56 @@
+{
+  "_name_or_path": "distilbert/distilroberta-base",
+  "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": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-EMAIL",
+    "2": "B-ID_NUM",
+    "3": "I-ID_NUM",
+    "4": "B-NAME_STUDENT",
+    "5": "I-NAME_STUDENT",
+    "6": "B-PHONE_NUM",
+    "7": "I-PHONE_NUM",
+    "8": "B-STREET_ADDRESS",
+    "9": "I-STREET_ADDRESS",
+    "10": "B-URL_PERSONAL",
+    "11": "I-URL_PERSONAL",
+    "12": "B-USERNAME"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-EMAIL": 1,
+    "B-ID_NUM": 2,
+    "B-NAME_STUDENT": 4,
+    "B-PHONE_NUM": 6,
+    "B-STREET_ADDRESS": 8,
+    "B-URL_PERSONAL": 10,
+    "B-USERNAME": 12,
+    "I-ID_NUM": 3,
+    "I-NAME_STUDENT": 5,
+    "I-PHONE_NUM": 7,
+    "I-STREET_ADDRESS": 9,
+    "I-URL_PERSONAL": 11,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:012e3f37402e30e85777c5fddca1ec326bc1823c3572e762f49098c95d665958
+size 326298984

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}