Training in progress, epoch 0

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "mistralai/Mixtral-8x7B-v0.1",
+  "base_model_name_or_path": "mistralai/Mixtral-8x7B-Instruct-v0.1",
   "bias": "none",
   "fan_in_fan_out": null,
   "inference_mode": true,
@@ -19,10 +19,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "v_proj",
+    "q_proj",
     "o_proj",
-    "q_proj"
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2e92d127847669a6d0d26e91056cea2134b7f6b0c2fa5db00d4b8074b8dbe8a
+oid sha256:663a26f1f1a3b4fcfd581184eee642fd42fda734b67a37de0e0427b6782aa593
 size 27297032

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "mistralai/Mixtral-8x7B-v0.1",
+  "_name_or_path": "mistralai/Mixtral-8x7B-Instruct-v0.1",
   "architectures": [
     "MixtralForCausalLM"
   ],

runs/Feb29_16-54-10_azure-jap/events.out.tfevents.1709225652.azure-jap.95906.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df6ae3d20bfd54d4a2789ce08479c8e2166a58c811cf9ded6be641706c491bc8
+size 10584

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83ad7b64c51d461b9b4bb1de4956d35ef77a860375b5f95b565353c6148fd684
+oid sha256:4c59c6a5f88064305dd076a6acaf260003a37a4382f71c6a289edbc23a6aece0
 size 4859