Training in progress, epoch 1

adapter_config.json

@@ -21,9 +21,9 @@
   "revision": null,
   "target_modules": [
     "qkv_proj",
+    "down_proj",
     "gate_up_proj",
-    "o_proj",
-    "down_proj"
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f7305a9bf120db9dcb9b2a878c98af97d2a2b4f21be45389ef03dda5375c380
+oid sha256:a612df7165db3f3b1c8b993ba5f31783c5e4cc81995d83f685aea33cf2797e6d
 size 201361312

runs/Apr27_16-24-23_expcompute/events.out.tfevents.1714235066.expcompute.21890.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f489eb4a77f26efa59e196d40c0a69c5d803078f01d3b2fcd40a79fd16e85519
+size 5527

special_tokens_map.json

@@ -13,7 +13,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|endoftext|>",
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a462e6e88b6ac2b0232e88ffc00fe3436245dcbe188638a9e88b7a6b7e94b44
+oid sha256:a283581c37689db9292b2cd988746f2eded0b7a3d37c82b4169c8ab67380c1b7
 size 5048