Model save

README.md

@@ -47,7 +47,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.03
-- num_epochs: 3
+- num_epochs: 5
 
 ### Training results
 

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "q_proj",
-    "k_proj",
     "lm_head",
+    "down_proj",
     "up_proj",
+    "k_proj",
     "gate_proj",
     "v_proj",
+    "q_proj",
     "o_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bb847e0b387b8ac2052c1d3aac738f9b163c62c5e0b7367fc7ca3f27efc9965
+oid sha256:abb79f901fa3c36beb16a11e706b8a66560da9103e99d35e62fd8a682bf5bfc5
 size 608759824

special_tokens_map.json

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

tokenizer_config.json

@@ -6178,7 +6178,7 @@
   "eos_token": "</s>",
   "legacy": false,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "</s>",
+  "pad_token": "<unk>",
   "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 sha256:6ba28abc75fdfa5fe3db8ed17f7d1f2b081ba34a74aa663f48e9138c67be2a6a
+oid sha256:5e841c2eb417e521dfa5e360ad1c3e1bf1ad22b625832299281f63df1b489de5
 size 5112