Training in progress epoch 0

README.md

@@ -0,0 +1,53 @@
+---
+license: mit
+tags:
+- generated_from_keras_callback
+model-index:
+- name: HuggingAlex1247/gbert-large-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. -->
+
+# HuggingAlex1247/gbert-large-germaner
+
+This model is a fine-tuned version of [deepset/gbert-large](https://huggingface.co/deepset/gbert-large) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 0.1216
+- Validation Loss: 0.0809
+- 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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 13915, '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: float32
+
+### Training results
+
+| Train Loss | Validation Loss | Epoch |
+|:----------:|:---------------:|:-----:|
+| 0.1216     | 0.0809          | 0     |
+
+
+### Framework versions
+
+- Transformers 4.21.3
+- TensorFlow 2.6.2
+- Datasets 1.18.0
+- Tokenizers 0.12.1

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "deepset/gbert-large",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "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": 4096,
+  "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": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.21.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31102
+}

logs/train/events.out.tfevents.1662714507.ec36290bf41f.121.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c78b214f2261f05ddbbb84fc0e1cca496f8d62a06cd5ea0f31e33f72d10f753b
+size 5702766

logs/train/events.out.tfevents.1662714521.ec36290bf41f.profile-empty

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:567461086b07b2db3d3c66b5a3dfec7144811a4a4781ebf608d281b73c5feef0
+size 40

logs/train/plugins/profile/2022_09_09_09_08_41/ec36290bf41f.input_pipeline.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8866855d54b50c631e063cb6171fa0fedc82e61d18a281cee6c958f1aea274ef
+size 3048

logs/train/plugins/profile/2022_09_09_09_08_41/ec36290bf41f.kernel_stats.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f8f0cd428b1633faf84a7567facd2e4b49ff25df07fa0774f88af8074f755f2
+size 288620

logs/train/plugins/profile/2022_09_09_09_08_41/ec36290bf41f.memory_profile.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51fa45e89280844873ccb2fa557fc3af3a429cc7f6d9e61f8c121a06f24f7af5
+size 52367

logs/train/plugins/profile/2022_09_09_09_08_41/ec36290bf41f.overview_page.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a323a55799327b3afd0b97bc5bf8e36597b830c97db5f42afb695755a3dff476
+size 5355

logs/train/plugins/profile/2022_09_09_09_08_41/ec36290bf41f.tensorflow_stats.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c3c5a0c2aa209fcd1ef90f8e003c8b05e290f9e45d2f557930d60f599e407f6
+size 182369

logs/train/plugins/profile/2022_09_09_09_08_41/ec36290bf41f.trace.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93ff92b242bcf6d904e7c34d7b7c1016600d0524aca2955a1563e0a2e475c878
+size 525563

logs/train/plugins/profile/2022_09_09_09_08_41/ec36290bf41f.xplane.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76726dedb4f0a70999d447295fcfc32c5b968fd3dfa38b486cc0d3af2645f84a
+size 4430492

logs/validation/events.out.tfevents.1662714791.ec36290bf41f.121.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95599bd5d5070b09b8fdb5bea5ab27d7c60b4dfe11cae6edbb9203a55f6b7832
+size 194

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 sha256:38560acd9e1cd2b754606f94af5de5e5f16f7d66339c4cbcc299df9fd248d7ea
+size 1339331396

tokenizer_config.json

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