finetuned qa dataset 4 epochs

README.md

@@ -86,9 +86,9 @@ The model was trained with the parameters:
 
 **DataLoader**:
 
-`torch.utils.data.dataloader.DataLoader` of length 773 with parameters:
+`torch.utils.data.dataloader.DataLoader` of length 2062 with parameters:
 ```
-{'batch_size': 128, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
+{'batch_size': 48, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
 ```
 
 **Loss**:
@@ -111,7 +111,7 @@ Parameters of the fit()-Method:
     },
     "scheduler": "WarmupLinear",
     "steps_per_epoch": null,
-    "warmup_steps": 309,
+    "warmup_steps": 824,
     "weight_decay": 0.01
 }
 ```

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "gapendl/gbert-base-kurier",
+  "_name_or_path": "gapendl/geronimo-base",
   "architectures": [
     "BertModel"
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19f6b1b578caf868cdbd09982fff8a844cd7ec5fdc17631b0f53b823175a5820
+oid sha256:27c9e463bd0fabd102a9f1689afecfb4d38db14b44ecb44526643ad30e0ecb22
 size 439733088

tokenizer_config.json

@@ -47,12 +47,19 @@
   "do_lower_case": false,
   "mask_token": "[MASK]",
   "max_len": 512,
+  "max_length": 512,
   "model_max_length": 512,
   "never_split": null,
+  "pad_to_multiple_of": null,
   "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "sep_token": "[SEP]",
+  "stride": 0,
   "strip_accents": false,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"
 }