Training in progress, step 50

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "o_proj",
-    "gate_proj",
+    "k_proj",
     "down_proj",
     "up_proj",
-    "k_proj",
-    "q_proj"
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80e7ea68d3523b9fafef27a84255d9eda096472412d549a512ea47cb451a3574
+oid sha256:6471d309960c925a161514960efb95840710553f244f77f0696695fc8980a3b6
 size 159968328

runs/Jan03_09-13-39_dgx-a100-12/events.out.tfevents.1735892029.dgx-a100-12.560433.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fb53bc1552015d2ecdf002e1584f9dd297c097a1016731a163f0d7dbea811f4
+size 6068

runs/Jan03_09-21-20_dgx-a100-12/events.out.tfevents.1735892491.dgx-a100-12.569257.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9aa228c50b1c09360732600a5b2fbd8284ad62d743520a6fa751626d6677804
+size 10939

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 2048,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a448c720388868dafeb2c8c865aa0df05a1cec42f1837f9f4cdc8aeb5d5de8f
+oid sha256:0dc4fdd6ee8ad7650b33f23b5676888caf478687c1da0851dfde133abb1f6151
 size 6968