Training in progress epoch 0

README.md

@@ -0,0 +1,53 @@
+---
+license: mit
+tags:
+- generated_from_keras_callback
+model-index:
+- name: pankaj10034/gbert-base-germaner
+  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. -->
+
+# pankaj10034/gbert-base-germaner
+
+This model is a fine-tuned version of [deepset/gbert-base](https://huggingface.co/deepset/gbert-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 0.1365
+- Validation Loss: 0.0820
+- 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: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 6960, '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}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
+- training_precision: mixed_float16
+
+### Training results
+
+| Train Loss | Validation Loss | Epoch |
+|:----------:|:---------------:|:-----:|
+| 0.1365     | 0.0820          | 0     |
+
+
+### Framework versions
+
+- Transformers 4.30.2
+- TensorFlow 2.12.0
+- Datasets 2.13.1
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "deepset/gbert-base",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-LOC",
+    "1": "B-ORG",
+    "2": "B-OTH",
+    "3": "B-PER",
+    "4": "I-LOC",
+    "5": "I-ORG",
+    "6": "I-OTH",
+    "7": "I-PER",
+    "8": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-LOC": "0",
+    "B-ORG": "1",
+    "B-OTH": "2",
+    "B-PER": "3",
+    "I-LOC": "4",
+    "I-ORG": "5",
+    "I-OTH": "6",
+    "I-PER": "7",
+    "O": "8"
+  },
+  "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": "4.30.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31102
+}

logs/train/events.out.tfevents.1689048549.784b5a50beba.386.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fef1cd3c8834c2eef465d598cc6f502621775e3e0cb23d77be766090084eb7a
+size 3599485

logs/validation/events.out.tfevents.1689048798.784b5a50beba.386.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28cc6bd6c2ee201f3d5e6bb49233cd65bb00baa3a5d30fdd93bafd664e3ae478
+size 232

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e301c0de7f8fb5414fa278f2ae75bce077fc4a79488b35ccdaca4528ad8f70d7
+size 437649388

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": false,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}