Training in progress, step 200

README.md

@@ -36,8 +36,8 @@ This model was trained with SFT.
 ### Framework versions
 
 - TRL: 0.21.0
-- Transformers: 4.55.0
-- Pytorch: 2.7.1
+- Transformers: 4.55.2
+- Pytorch: 2.8.0+cu126
 - Datasets: 3.6.0
 - Tokenizers: 0.21.4
 

adapter_config.json

@@ -25,15 +25,15 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
     "embed_tokens",
     "k_proj",
-    "q_proj",
-    "down_proj",
     "lm_head",
+    "down_proj",
+    "o_proj",
     "up_proj",
-    "v_proj",
-    "gate_proj",
-    "o_proj"
+    "q_proj",
+    "gate_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e560d9a036582e45eea6e1ef405d72306e3ab8e91a76eb732c6df09287a018a3
+oid sha256:0cf6080fb196f46574937f2d723d6618389af79a80189f6ade815c7d50ef0a8d
 size 3706540688

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df9919b1d4865de6c032dd72539ecc4cfe9d56edca507c7f33651635cdd1c974
+oid sha256:efb3e57a570373a659483d7b496e401d020999f5b294d535c8f3b0a5606bcb0b
 size 6225