Training in progress epoch 0

README.md

@@ -0,0 +1,53 @@
+---
+license: mit
+tags:
+- generated_from_keras_callback
+model-index:
+- name: HuggingAlex1247/gelectra-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/gelectra-large-germaner
+
+This model is a fine-tuned version of [deepset/gelectra-large](https://huggingface.co/deepset/gelectra-large) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 0.1696
+- Validation Loss: 0.0800
+- 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': 3475, '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 |
+|:----------:|:---------------:|:-----:|
+| 0.1696     | 0.0800          | 0     |
+
+
+### Framework versions
+
+- Transformers 4.22.2
+- TensorFlow 2.6.2
+- Datasets 1.18.0
+- Tokenizers 0.12.1

config.json

@@ -0,0 +1,51 @@
+{
+  "_name_or_path": "deepset/gelectra-large",
+  "architectures": [
+    "ElectraForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 1024,
+  "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": "electra",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "transformers_version": "4.22.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31102
+}

logs/train/events.out.tfevents.1664991962.9791291a9c7a.105.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fcb4aa0908d1ade5dca431d054fc796289ec2af9c161bf2d0b56eaf8354eead
+size 5935892

logs/train/events.out.tfevents.1664991977.9791291a9c7a.profile-empty

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23087ade0b04a4e5c9fe71042def53edfc319cf00e5211405c512d1372558813
+size 40

logs/train/plugins/profile/2022_10_05_17_46_17/9791291a9c7a.input_pipeline.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee9867e1f5ee088f8a22912026b8c1394046cec2276a00918d06daf8080412e3
+size 3069

logs/train/plugins/profile/2022_10_05_17_46_17/9791291a9c7a.kernel_stats.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:559f2f7568e880594dedcdce24bc2a259d5acde7c52d3b45d9c86cf8cada20af
+size 287748

logs/train/plugins/profile/2022_10_05_17_46_17/9791291a9c7a.memory_profile.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2360a3b9ceef1ab51d3dbf3045a879cf228ad5becf02c86f3b03a99efca0f46d
+size 53607

logs/train/plugins/profile/2022_10_05_17_46_17/9791291a9c7a.overview_page.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58416cbb5ba3f01c796b2582f4088084ae2f983b0c59e7ceebc2b13363a74adf
+size 5944

logs/train/plugins/profile/2022_10_05_17_46_17/9791291a9c7a.tensorflow_stats.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9836da26a6d1e16cce5dd9faa3e640515535bcc21ca116494b54fb385d678dc2
+size 202649

logs/train/plugins/profile/2022_10_05_17_46_17/9791291a9c7a.trace.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cabaf51822605ea8610d3cecf7d7cfe92ed2898c8f1e8d4ade2a14f7b4013f4
+size 548968

logs/train/plugins/profile/2022_10_05_17_46_17/9791291a9c7a.xplane.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d28652add683ead626b005c0b63cabadee4fa390571570a31e009a3cd4452406
+size 4541731

logs/validation/events.out.tfevents.1664992154.9791291a9c7a.105.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9597e94c0119224d7b60352e02a9c9a9c7aed90a198f07c8f7ec5eef66056ec
+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 sha256:7210bc26ccdde2c50c6b5b1af88fefee56f1249590e143219ecffc972c45713f
+size 1339333944

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/gelectra-large",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": false,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "ElectraTokenizer",
+  "unk_token": "[UNK]"
+}