Training in progress, step 10

README.md

@@ -1,6 +1,5 @@
 ---
 base_model: Qwen/Qwen2-0.5B-Instruct
-datasets: trl-lib/chatbot_arena_completions
 library_name: transformers
 model_name: gkd-model
 tags:
@@ -12,7 +11,7 @@ licence: license
 
 # Model Card for gkd-model
 
-This model is a fine-tuned version of [Qwen/Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct) on the [trl-lib/chatbot_arena_completions](https://huggingface.co/datasets/trl-lib/chatbot_arena_completions) dataset.
+This model is a fine-tuned version of [Qwen/Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c536eeb02c03cfb5d83c01823344a4056e25bb8d175ae29780bb3c448273610b
+oid sha256:009a53b8b2a0b9dd2aa1dd1de5d85f6e36911266bff548fc9bb358fe09d2147b
 size 1976163472

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b880aea4105d5071cca0d3bcadb9e215f625ad42b0c4542d1103d26b724aafdf
+oid sha256:63ca7f3ae5c7dbb387b8c4b4924b448bfd892d33d497dfe6a102acfe0b8142c4
 size 11418364

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:811d4c60bb019dc027ecd98a63314bbb1a6c076f04811001c31f46ce6353ecaa
+oid sha256:94830d474f63aa54d42e24e100c30ea6e3d7a6d599e88713cc02d0d50f32422d
 size 6481