Training in progress, epoch 1

README.md

@@ -34,11 +34,11 @@ This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.24.0.dev0
-- Transformers: 4.56.1
+- TRL: 0.23.1
+- Transformers: 4.57.0
 - Pytorch: 2.8.0+cu126
 - Datasets: 3.3.2
-- Tokenizers: 0.22.0
+- Tokenizers: 0.22.1
 
 ## Citations
 

adapter_config.json

@@ -28,13 +28,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
+    "up_proj",
+    "down_proj",
     "q_proj",
-    "gate_proj",
-    "o_proj",
     "k_proj",
-    "down_proj",
-    "up_proj"
+    "v_proj",
+    "o_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:cc994568c6d8feab5951fe21421958371c28188b5deaba49d70008cb6ca930c4
+oid sha256:017f3bd1f1b91f5195b2e1068bb42f354eb15e45bf83bcddaba124a7c0b032d3
 size 2468152240

runs/Oct12_22-16-48_5956320889d8/events.out.tfevents.1760307480.5956320889d8.670.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3aea940a81d3dd8f7165b2c6434c34114dee81374dbcc67faa533c6322096d6
+size 7384

tokenizer_config.json

@@ -51336,7 +51336,6 @@
   "image_token": "<image_soft_token>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
-  "processor_class": "Gemma3Processor",
   "sp_model_kwargs": null,
   "spaces_between_special_tokens": false,
   "tokenizer_class": "GemmaTokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f7dbbf4836e4b83048830fd1024878085b2fb50dc40e7a4c88ff2500ba39080
-size 6225
+oid sha256:f7519bb624cc7dbdb73031e2d0720ce3166879f5749178d2f1f25ef6a4096760
+size 6289