Training in progress, step 500

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: GLM-4.5-Air
 tags:
 - generated_from_trainer
-- trl
 - sft
+- trl
 licence: license
 ---
 
@@ -34,11 +34,11 @@ This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.22.1
-- Transformers: 4.56.0
+- TRL: 0.23.0
+- Transformers: 4.56.2
 - Pytorch: 2.8.0
-- Datasets: 4.0.0
-- Tokenizers: 0.22.0
+- Datasets: 4.1.1
+- Tokenizers: 0.22.1
 
 ## Citations
 

adapter_config.json

@@ -25,13 +25,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "o_proj",
-    "down_proj",
-    "up_proj",
     "k_proj",
+    "up_proj",
     "gate_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "down_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e88b02c3269c973a390c911ef700718e47b72009e90a8d67f70e8bd498130c5
+oid sha256:ceb7ff4fb6f785874c37c5b8134eb278222945994102cc6004b77920a8b161bf
 size 12533238776

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d6bd8f3547406f8ad2f9d8228cc3d129e82253532bf18c563fb55b658555c34
-size 6225
+oid sha256:26b181ee871cf415d650f52c86d6d366f34610f0b0a8f1401686a14f7cc8804f
+size 6289