Training in progress epoch 0

README.md

@@ -0,0 +1,53 @@
+---
+license: mit
+tags:
+- generated_from_keras_callback
+model-index:
+- name: HuggingAlex1247/distilbert-base-german-europeana-cased-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. -->
+
+# HuggingAlex1247/distilbert-base-german-europeana-cased-germeval_14
+
+This model is a fine-tuned version of [dbmdz/distilbert-base-german-europeana-cased](https://huggingface.co/dbmdz/distilbert-base-german-europeana-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 0.3609
+- Validation Loss: 0.2115
+- 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': 1e-05, 'decay_steps': 25500, '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 |
+|:----------:|:---------------:|:-----:|
+| 0.3609     | 0.2115          | 0     |
+
+
+### Framework versions
+
+- Transformers 4.17.0
+- TensorFlow 2.6.2
+- Datasets 1.18.0
+- Tokenizers 0.11.6

config.json

@@ -0,0 +1,77 @@
+{
+  "_name_or_path": "dbmdz/distilbert-base-german-europeana-cased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForTokenClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "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,
+  "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"
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": true,
+  "tie_weights_": true,
+  "transformers_version": "4.17.0",
+  "vocab_size": 32000
+}

logs/train/events.out.tfevents.1646753432.8e22313e678f.72.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97712164d2476a40fc8b5fa9e265d3a736cc9482d8fc9b23d7322eac53126fb7
+size 1625167

logs/train/events.out.tfevents.1646753440.8e22313e678f.profile-empty

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6894201e96aa87d5e0a87cd1ba8d187c6d3f679e73f32c6e8f4e87d0627219b
+size 40

logs/train/plugins/profile/2022_03_08_15_30_40/8e22313e678f.input_pipeline.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b5924ddf019cb07b3ba36da97f1926cd679d05a8a77fe99289c204586d83c01
+size 3053

logs/train/plugins/profile/2022_03_08_15_30_40/8e22313e678f.kernel_stats.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c18da93c72a0b20f88870ec77de96cc8c4770cbedba9bf2c711f6e558ff9396e
+size 315610

logs/train/plugins/profile/2022_03_08_15_30_40/8e22313e678f.memory_profile.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd71fffe4f3a877c9fd574eb626d13dab159ca31b150638b2775653926943678
+size 34606

logs/train/plugins/profile/2022_03_08_15_30_40/8e22313e678f.overview_page.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c020a1a9c10fb40e7ee7c8f43db12bc876dd73f320e8dec008fe55aaee2de4c4
+size 5435

logs/train/plugins/profile/2022_03_08_15_30_40/8e22313e678f.tensorflow_stats.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8891ccd68abc93b5ef96cb64acd197981b789824bf78e794f1c1a0e561f9bdb4
+size 188411

logs/train/plugins/profile/2022_03_08_15_30_40/8e22313e678f.trace.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84dfcb862f25e4150ea098eb4a995192e974a7c117a5fa845b41cb4a7efbc412
+size 159061

logs/train/plugins/profile/2022_03_08_15_30_40/8e22313e678f.xplane.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:758e3da1a753b8e5c7978006f294455e0811f0cd5aaff1d704ea290b22ca6d78
+size 1258846

logs/validation/events.out.tfevents.1646753560.8e22313e678f.72.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85e2155c92c02e22ca374413f92d6cf36cf3e6cf90e8bd8461737f9042c07bfe
+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 sha256:6082a62557711eea2d80322f781d23b7e852f023a12d0d63f744da07a613b3a7
+size 270195104

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": "dbmdz/distilbert-base-german-europeana-cased", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "DistilBertTokenizer"}