Training in progress, epoch 0

adapter_config.json

@@ -20,14 +20,14 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
     "o_proj",
-    "v_proj",
-    "gate_proj",
-    "up_proj",
     "down_proj",
-    "k_proj",
     "lm_head",
-    "q_proj"
+    "v_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fb97858cfe2e76c9e0b320f99fc789960c725a25f78de53b90a44185d62e905
-size 864513616
+oid sha256:6829a612dba3a553822c1422f3912b9fb826c5dce3e3d136776b1b568b5af47f
+size 1194754144

runs/Apr01_10-51-23_4578cb645bfc/events.out.tfevents.1711968695.4578cb645bfc.24.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f13f42e27fd51e2121bfbc0c3a8b90d8e45be09814878dcbe3cf5ab523724c50
+size 9033

special_tokens_map.json

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

tokenizer_config.json

@@ -33,7 +33,7 @@
   "eos_token": "</s>",
   "legacy": true,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<s>",
+  "pad_token": "</s>",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0e4db45dd4a3211358d59a050bd77b8782569eafbea0b8afd002c9a8b71355b
+oid sha256:1048b9cfa1cc82219eb2f1f1d637bd7ab94df34862967709e8df2078df868e6f
 size 4728