Training in progress, epoch 1

README.md

@@ -35,10 +35,10 @@ This model was trained with SFT.
 ### Framework versions
 
 - TRL: 0.21.0
-- Transformers: 4.55.4
+- Transformers: 4.56.0
 - Pytorch: 2.8.0+cu126
 - Datasets: 4.0.0
-- Tokenizers: 0.21.4
+- Tokenizers: 0.22.0
 
 ## Citations
 

adapter_config.json

@@ -26,13 +26,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
     "o_proj",
     "q_proj",
+    "gate_proj",
     "down_proj",
-    "up_proj",
     "k_proj",
-    "v_proj",
-    "gate_proj"
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08fc5712ea85caf64dfc4df0824a54cdeeea795480ccb3fc7c145b22db012f45
+oid sha256:fb40ae3befec2e9207fc57f0b5e5a0e46290b18ea53c1aa75548a34e3398116c
 size 2468152240

runs/Sep05_02-11-22_4a02d2f90a3e/events.out.tfevents.1757038294.4a02d2f90a3e.977.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6967c62b76a9c19a45347fd7290020182255caad2508ee4e590eb4bf11c91588
+size 16472

runs/Sep05_02-13-45_4a02d2f90a3e/events.out.tfevents.1757038436.4a02d2f90a3e.2157.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64627e39f7fe41fb7ab668c3c5ca1c0a55a1765d488ce4e59e3aa51084faaab0
+size 7525

runs/Sep05_02-16-00_4a02d2f90a3e/events.out.tfevents.1757038582.4a02d2f90a3e.2731.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b1b58555f2ffacdb7678e723867d9e0448231263a5e0b9100c4a8e24ef60a0
+size 7538

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:969506b5abb5318c8bf2367b9effbfa965274c4c3ac424cacfe428fd6f098c00
+oid sha256:f6f2f9d36b07018159c9dcf1b4c02b6bfa3197507ec278ee261a8e7fbbf748ec
 size 6225