Training in progress, epoch 0

README.md

@@ -51,7 +51,7 @@ The following hyperparameters were used during training:
 ### Framework versions
 
 - PEFT 0.11.1
-- Transformers 4.40.2
+- Transformers 4.42.0.dev0
 - Pytorch 2.3.0+cu121
 - Datasets 2.19.1
 - Tokenizers 0.19.1

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b11587dac5e04afb759de4ac8d5b4ccfd9d4ca79084e7013b6ba6da999c6068
+oid sha256:32ef01045fe127f4ab89317403e24e9fae043da9c52962fe36d3db6ee300949c
 size 694431312

tokenizer_config.json

@@ -1,6 +1,7 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
+  "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bfa3d779867fa855e519dcc27f4c26714e08b73c7bd81aef46709b79f47e519
-size 5048
+oid sha256:5ecdb7a3c44b587a9440792501cb32e8850922289af65b61061789040877ee14
+size 5176