Training in progress, epoch 1

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
     "gate_proj",
+    "o_proj",
+    "k_proj",
     "v_proj",
     "q_proj",
-    "up_proj",
-    "o_proj",
-    "down_proj",
-    "k_proj"
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b23b8af8c66594a38f4e257d921c3ad3b49a7024be6f0398a8fc09ce4b55fe3
+oid sha256:f96ab8ffc9e97ae37c7865a08afa9ed242d11511c397df096fe59de363d753db
 size 2772497632

runs/Aug22_10-24-53_merlin.doc.ic.ac.uk/events.out.tfevents.1724318702.merlin.doc.ic.ac.uk

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bfd4ae262cd7561d1b69ec658810260968b047a61852dabbcf3b2a1f9a36dd5
+size 32118

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 2048,
-    "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:b8b348bf86835aaeb791ac042b1011c6b191ff97edaf2ee0167ca0e258c72928
+oid sha256:8a9145fc9a6a39471f0407c5291dd47fe70f5821aed8bc541737361c92128d40
 size 5048