Training in progress, step 1000

adapter_config.json

@@ -8,18 +8,18 @@
   "init_lora_weights": true,
   "layers_pattern": null,
   "layers_to_transform": null,
-  "lora_alpha": 16,
+  "lora_alpha": 512,
   "lora_dropout": 0.05,
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 64,
+  "r": 256,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
     "o_proj",
-    "v_proj",
     "k_proj",
-    "q_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ff44dcfcc79af43e9acea89cacb9a6f0eb8baa6aae0ad4f88238d9260fe104d
-size 218138576
+oid sha256:c32ec1dd7d848dd71fb0a360af25f7634b3b9bf50913bae5e73da29921b1caf1
+size 872450448

special_tokens_map.json

@@ -18,13 +18,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "pad_token": "</s>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3b996c8b0abe691705f82a98b00f81952f66bef898fb45e3d181ab88f50c5b2
+oid sha256:19d1fc1ed356d8da00a2d95a8028eab9e7851a3c0bd08f73cbee1e1cd937cb80
 size 4664