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",
+    "up_proj",
     "v_proj",
-    "q_proj",
-    "down_proj"
+    "o_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ad611488cb2cf40055401766db250e6f4b00b225e70e0bfdb0429d123a1707c
+oid sha256:d7b00b00fdd93f76905911cc160d433986f7dd961a5046075e49e67af4a23161
 size 2772497632

runs/Aug22_13-24-40_merlin.doc.ic.ac.uk/events.out.tfevents.1724329489.merlin.doc.ic.ac.uk

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3df427857e2e9bd6afbc7c075e5dc107273c8421a0c9ab660a83c87396a016c0
+size 19460

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 sha256:8a9145fc9a6a39471f0407c5291dd47fe70f5821aed8bc541737361c92128d40
+oid sha256:daa07f3687ded2d7c93d94f9a5d875882a04095f451c34861e674f9cc82e83bf
 size 5048