Training in progress, step 10

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "mistralai/Mixtral-8x7B-Instruct-v0.1",
+  "base_model_name_or_path": null,
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,9 +20,9 @@
   "revision": null,
   "target_modules": [
     "o_proj",
-    "k_proj",
     "q_proj",
     "gate",
+    "k_proj",
     "v_proj"
   ],
   "task_type": "CAUSAL_LM"

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fbaaa70e5f0dc50134c54bd96a78f7cab5d9f36ed74b5e3b20d6fc1f647d10d
-size 125905328
+oid sha256:1061eebb2bd138e748fa99483c8b334b712999dd925106f9ffeec242b750a30f
+size 125910768

runs/Dec27_06-14-13_e047f54d00ab/events.out.tfevents.1703657672.e047f54d00ab.121111.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65ada365c8819723cbb83a668642b7af1f8b9aae8d63f3ac96810bd07da177b6
+size 5108

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 sha256:592687f1f7f7206614797b90d909d922bdd07893d16531e4f7519f4ef253ff25
-size 4728
+oid sha256:65c205a12c047b8bdc9a4a73356af3a44c586879d783d6fa397f22fb28a4e4d5
+size 4792