Training in progress, step 500

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: medgemma-4b-multitask-polyp2
 tags:
 - generated_from_trainer
-- trl
 - sft
+- trl
 licence: license
 ---
 
@@ -35,8 +35,8 @@ This model was trained with SFT.
 ### Framework versions
 
 - TRL: 0.19.0
-- Transformers: 4.52.4
-- Pytorch: 2.5.1
+- Transformers: 4.53.0
+- Pytorch: 2.6.0+cu124
 - Datasets: 3.6.0
 - Tokenizers: 0.21.2
 

adapter_config.json

@@ -27,16 +27,16 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "out_proj",
-    "down_proj",
     "q_proj",
-    "fc1",
-    "k_proj",
+    "v_proj",
     "o_proj",
+    "fc1",
     "up_proj",
+    "down_proj",
+    "fc2",
+    "out_proj",
     "gate_proj",
-    "v_proj",
-    "fc2"
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afa903d4fb989963a8d4317f962e61d5f9bfcb0c94d06dd0e31f37e1f9c4347b
+oid sha256:cd069221ca40006350555cb98f5a81289f6889519d883a987d08522806549106
 size 2993118096

runs/Jul07_14-13-52_main1/events.out.tfevents.1751865236.main1.1291217.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8f3a269457d897617221f675c19a8714aa3f8523c18a592306140b215419b87
+size 8257

runs/Jul07_14-53-04_main1/events.out.tfevents.1751867589.main1.1291367.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6406ee589fab1ece8f24f2df05fca47d4ded3eb04ef49f3c73dd4419962b1c22
+size 9965

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98534cd97ac348a78a621a9cf26706592a388cf02d2ccb906deb66580db303da
-size 5752
+oid sha256:86a5c75735b588f5a11bdc6868cd9627f3a8e12908cb8498406b00f2ec01c313
+size 5816