Training in progress epoch 0

README.md

@@ -0,0 +1,53 @@
+---
+license: mit
+tags:
+- generated_from_keras_callback
+model-index:
+- name: Ruth/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. -->
+
+# Ruth/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: 0.1236
+- Validation Loss: 0.0807
+- 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': 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 |
+|:----------:|:---------------:|:-----:|
+| 0.1236     | 0.0807          | 0     |
+
+
+### Framework versions
+
+- Transformers 4.18.0
+- 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": "4.18.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31102
+}

logs/train/events.out.tfevents.1651760269.bb3a84e6bfa0.11312.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d488dedb471568940bd4fd2879c9a2fe250efd984b6afbc46530f65ddbe8df83
+size 5696838

logs/train/events.out.tfevents.1651760288.bb3a84e6bfa0.profile-empty

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44f7f98d7abaa9634f275079593530f6660ad7cc5a7c684d928219f51ba77fe6
+size 40

logs/train/plugins/profile/2022_05_05_14_18_08/bb3a84e6bfa0.input_pipeline.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b20b425ea22d5a4d729ce73d2db6143bb4483ba742d0255c00e19119e6cc616
+size 3052

logs/train/plugins/profile/2022_05_05_14_18_08/bb3a84e6bfa0.kernel_stats.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:865a412e384153892db7d3f022da01dcb4ce391492e44c30f4419af3c5aa6c49
+size 319316

logs/train/plugins/profile/2022_05_05_14_18_08/bb3a84e6bfa0.memory_profile.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1b816c9e8c284697cf65a4fc59a5f6fe14df8a2257c3e2082c6d0b67ce71614
+size 52406

logs/train/plugins/profile/2022_05_05_14_18_08/bb3a84e6bfa0.overview_page.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de25b2dfacbcde16ed65bfd5a178adce965943b4558c2533a6ab7fea7e004efb
+size 5407

logs/train/plugins/profile/2022_05_05_14_18_08/bb3a84e6bfa0.tensorflow_stats.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:471a83ab4a0899e3025d56678714c64a47ffad63c712814311fdb4f3d7098b3d
+size 186597

logs/train/plugins/profile/2022_05_05_14_18_08/bb3a84e6bfa0.trace.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0edf234b339df1544dbba91c6b0170dabfa1ae481e956f07e69fe91de071812
+size 551208

logs/train/plugins/profile/2022_05_05_14_18_08/bb3a84e6bfa0.xplane.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b8b80dd0514d3bd639b9a7bb041285cb62ade634ad93e2a49f77fc0e4705123
+size 4492136

logs/validation/events.out.tfevents.1651760993.bb3a84e6bfa0.11312.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05f7d821ddb7cc6e6887b92dddac584bc5351964830236834d0705606081460a
+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:f297098f01be76ad3b98af04199d7e4a1bf7c1bf59604baa672eea11d9e87e43
+size 1339331396

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/gbert-large", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}