Training in progress, step 120

adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "o_proj",
     "up_proj",
+    "down_proj",
     "k_proj",
+    "o_proj",
     "v_proj",
-    "down_proj",
+    "gate_proj",
     "q_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1944b7ee6e0f4f581e3dba5bf6025d9abe82ca0ef042b049988b5961919db57e
+oid sha256:c459e511bfe712da0f0b92e7e8d2db4538ed7856ece152fd75e5175dc3a6245c
 size 159967880

runs/Oct10_14-59-48_7e5dbbc0c5c7/events.out.tfevents.1728572392.7e5dbbc0c5c7.100.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93c3254a425b9845ed1fa7e8ae02f119d62f07a0aa5361663b744d336e14ddee
+size 30879

runs/Oct10_15-09-13_7e5dbbc0c5c7/events.out.tfevents.1728572966.7e5dbbc0c5c7.100.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00c482ae16f17aa0e3380c8faf923d1e39b621096a0e9ac4d100a1433032a48e
+size 30879

runs/Oct11_11-56-56_b1754e4d46cd/events.out.tfevents.1728647828.b1754e4d46cd.102.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc06e7dbffe21edc45a65475d7d0341ac3923ca32e733108b41ef50bde19213f
+size 30878

tokenizer_config.json

@@ -78,7 +78,7 @@
   "middle_token": "▁<MID>",
   "model_max_length": 16384,
   "pad_token": "<unk>",
-  "padding_side": "left",
+  "padding_side": "right",
   "prefix_token": "▁<PRE>",
   "sp_model_kwargs": {},
   "suffix_token": "▁<SUF>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01f84c66e632270eae48586c07ffbbc0d8e72d87559cba9176b8b6652dec1274
+oid sha256:8023623631dc83f56fc7edf706ce88c3b742f17183ed76704aa15bba3fda572a
 size 5432