Training in progress, step 100

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "alignment-handbook/zephyr-7b-sft-full",
+  "_name_or_path": "/mnt/bn/xuruijie-llm/checkpoints/trick/DPO",
   "architectures": [
     "MistralForCausalLM"
   ],

runs/Jun30_01-55-06_n136-129-074/events.out.tfevents.1719683774.n136-129-074.944731.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2afb6f6f97f50dd0dcc95a6f3616b6bf5885b3d88f1068cd7965fb4a80ec1085
+size 7599

runs/Jun30_02-07-44_n136-129-074/events.out.tfevents.1719684758.n136-129-074.948584.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac00b6898a9604815e4482dba0470d5f2d86e4ab21ea7b067a8740f1d7d39382
+size 9627

runs/Jun30_02-30-12_n136-129-074/events.out.tfevents.1719685832.n136-129-074.957046.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e6b54898884c6f07bb6d99a3f6c4110c8aa0699fc1653d53eab74c0e175ff1a
+size 12331

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:133221776a5e6d91be244dc0d687a768a5d5e2b866c6e50e92fc4c4395294899
+oid sha256:e5a6bae99f4cbe511f3eca5c4118d9962cf521b9dd97d594d8256c4fea05a69a
 size 6264