Training in progress, epoch 1

adapter_config.json

@@ -23,12 +23,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "v_proj",
     "q_proj",
+    "up_proj",
     "k_proj",
+    "gate_proj",
+    "v_proj",
     "down_proj",
-    "up_proj",
     "o_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2a6e57821d7920febf2cb6b6d699ffff1eed3d868d5cfbd74bdd9ade220b95f
+oid sha256:1091199cbd691d945250ed9d71144ae67bd83e1802393b78a585294926e0c38b
 size 2772497632

runs/Jul24_15-51-45_merlin.doc.ic.ac.uk/events.out.tfevents.1721832716.merlin.doc.ic.ac.uk

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d66a999676f3345e6083a5435ad7b0b04b283e3fadb0112cc8d5cbce03144e36
+size 15586

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 sha256:0ea41a0e9740a21a7ab23a114f4598b9d6bed49819c64de822b40451616ada14
+oid sha256:750fa4ac82f8fe17ef9c02e15e54c63f24ea8278ed2f0fad288300817df50374
 size 5048