Training in progress, epoch 1

README.md

@@ -2,7 +2,10 @@
 license: apache-2.0
 base_model: alignment-handbook/zephyr-7b-sft-full
 tags:
+- alignment-handbook
 - generated_from_trainer
+datasets:
+- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: zephyr-7b-dpo-lora
   results: []
@@ -13,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-dpo-lora
 
-This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the None dataset.
+This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the HuggingFaceH4/ultrafeedback_binarized dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.5650
 - Rewards/chosen: 0.0816

adapter_config.json

@@ -16,8 +16,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "v_proj",
+    "o_proj",
     "q_proj",
     "k_proj"
   ],

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30289b286308940696068f0ad4375260c6bfb714350a71c97ef8a9e9582042fb
+oid sha256:74aeaa41361cf19130082481873abd9dee881a558133a02119bf73f216ba81dc
 size 109086672

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "HuggingFaceH4/mistral-7b-sft-beta",
+  "_name_or_path": "alignment-handbook/zephyr-7b-sft-full",
   "architectures": [
     "MistralForCausalLM"
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea442d361aad58962e30eb6b5e88eb41a119a6bd1f02593c97d61b2fe3be8197
+oid sha256:178ca2e9659218d5d6a040bc9b839def7f1e2d04d37ea8a694c883bf79442126
 size 5688