Training in progress, epoch 1

README.md

@@ -35,7 +35,7 @@ This model was trained with SFT.
 ### Framework versions
 
 - TRL: 0.24.0
-- Transformers: 4.57.0
+- Transformers: 4.57.1
 - Pytorch: 2.8.0+cu126
 - Datasets: 4.0.0
 - Tokenizers: 0.22.1

adapter_config.json

@@ -13,7 +13,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 32,
   "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
@@ -21,7 +21,7 @@
   "modules_to_save": null,
   "peft_type": "LORA",
   "qalora_group_size": 16,
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f1cc66f5e03771bde2596204f516d99a80a73f4f5a77a1dfd7c1e068e889d68
-size 13648432
+oid sha256:9c7f5f7fe1c127c675e02a5714bf670702d7313f6484a940fbcffb2a0412dc84
+size 27280152

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1bf30a0f9f38e49e129cd3ff4b069b717f1799c054568469bd9a48ca5b46dd9
+oid sha256:bc315b47e765dd917994b2eb10116d803be45a1972129363729f177ecfc62ac5
 size 6225