Training in progress epoch 0

README.md

@@ -0,0 +1,53 @@
+---
+license: mit
+tags:
+- generated_from_keras_callback
+model-index:
+- name: Ruth/gelectra-large-germeval_14
+  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. -->
+
+# Ruth/gelectra-large-germeval_14
+
+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: 0.1998
+- Validation Loss: 0.0986
+- 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': 2e-05, 'decay_steps': 12750, '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 |
+|:----------:|:---------------:|:-----:|
+| 0.1998     | 0.0986          | 0     |
+
+
+### Framework versions
+
+- Transformers 4.18.0
+- TensorFlow 2.6.2
+- Datasets 1.18.0
+- Tokenizers 0.12.1

config.json

@@ -0,0 +1,83 @@
+{
+  "_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": "O",
+    "1": "B-LOC",
+    "10": "I-ORGderiv",
+    "11": "B-ORGpart",
+    "12": "I-ORGpart",
+    "13": "B-OTH",
+    "14": "I-OTH",
+    "15": "B-OTHderiv",
+    "16": "I-OTHderiv",
+    "17": "B-OTHpart",
+    "18": "I-OTHpart",
+    "19": "B-PER",
+    "2": "I-LOC",
+    "20": "I-PER",
+    "21": "B-PERderiv",
+    "22": "I-PERderiv",
+    "23": "B-PERpart",
+    "24": "I-PERpart",
+    "3": "B-LOCderiv",
+    "4": "I-LOCderiv",
+    "5": "B-LOCpart",
+    "6": "I-LOCpart",
+    "7": "B-ORG",
+    "8": "I-ORG",
+    "9": "B-ORGderiv"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-LOC": "1",
+    "B-LOCderiv": "3",
+    "B-LOCpart": "5",
+    "B-ORG": "7",
+    "B-ORGderiv": "9",
+    "B-ORGpart": "11",
+    "B-OTH": "13",
+    "B-OTHderiv": "15",
+    "B-OTHpart": "17",
+    "B-PER": "19",
+    "B-PERderiv": "21",
+    "B-PERpart": "23",
+    "I-LOC": "2",
+    "I-LOCderiv": "4",
+    "I-LOCpart": "6",
+    "I-ORG": "8",
+    "I-ORGderiv": "10",
+    "I-ORGpart": "12",
+    "I-OTH": "14",
+    "I-OTHderiv": "16",
+    "I-OTHpart": "18",
+    "I-PER": "20",
+    "I-PERderiv": "22",
+    "I-PERpart": "24",
+    "O": "0"
+  },
+  "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": "4.18.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31102
+}

logs/train/events.out.tfevents.1651755288.bb3a84e6bfa0.600.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50033703211b78bcbcb9360304e79471e1b323e07a5882b3ec1836efb208aab8
+size 5929636

logs/train/events.out.tfevents.1651755309.bb3a84e6bfa0.profile-empty

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:636351bad79ef39abb765cecc1b4d4b9eddb74deadb9644fe6b4b121a218b866
+size 40

logs/train/plugins/profile/2022_05_05_12_55_09/bb3a84e6bfa0.input_pipeline.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:475859e514fe1aae7840519430949f3223aadbc12efd1e14031271a67b478747
+size 3052

logs/train/plugins/profile/2022_05_05_12_55_09/bb3a84e6bfa0.kernel_stats.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f24f8069b5deef04f185f5f629ce74968acbd414316d010ba85c5240bcdc1155
+size 317283

logs/train/plugins/profile/2022_05_05_12_55_09/bb3a84e6bfa0.memory_profile.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea2eabafe9e161358a7b1cabc84a6c2e071f5a4b1600a3bbf40224a6e3e016c6
+size 52462

logs/train/plugins/profile/2022_05_05_12_55_09/bb3a84e6bfa0.overview_page.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d6d99e937aee22fae161432cc66d64cd5ba932bb5836627a072c0068830e661
+size 5407

logs/train/plugins/profile/2022_05_05_12_55_09/bb3a84e6bfa0.tensorflow_stats.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ba0902ebdd093d5dedbe04cf321d00d09f7acbae1eca5aa02ee236de5b1d04d
+size 197959

logs/train/plugins/profile/2022_05_05_12_55_09/bb3a84e6bfa0.trace.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76cc8ef7a8c2b7cfb2b75aad6a93df01f5e3bce170807b05899edb3c68aac38a
+size 556049

logs/train/plugins/profile/2022_05_05_12_55_09/bb3a84e6bfa0.xplane.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9dbbf057319ff3598772c6bd255cfd4ed80fd4609d9d05393006a6d2de07da6
+size 4562720

logs/validation/events.out.tfevents.1651755959.bb3a84e6bfa0.600.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f690e6edeba1bd10fa4ec5e55d1d373bfe6a5c07b8307371025a8fdb581b64f
+size 194

special_tokens_map.json

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

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abe806f44adfd27b42d32e6dd170df247f73f21cc9054b44cd641760fc27d426
+size 1339399480

tokenizer_config.json

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