Dietmar2020/OpenOrca-Platypus2-13B-GermanQuad_4090

README.md

@@ -35,13 +35,13 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0001
-- train_batch_size: 4
+- train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.03
-- num_epochs: 1
+- num_epochs: 3
 
 ### Training results
 

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df9b2ff404cba8fa51dca17a1d3ddb04f9f2d04530b714a13adc5cded1e6b74b
+oid sha256:8e43d294cf4669b0cf354d57f1a124c2b4343c8949c8b3c41833f0b80fff1e85
 size 209772877

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 1024,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b994affc0114d87ac9fd63600704aff77ab4a605ba704f15f7dfd89e5ecb2692
+oid sha256:30ddc8c3726f122bf57e368def2b96671e8f077d77ed6802326bac7292c7d5af
 size 3963