Training in progress, step 500

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: outputs
 tags:
 - generated_from_trainer
-- trl
 - sft
+- trl
 licence: license
 ---
 

adapter_config.json

@@ -29,13 +29,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate_proj",
     "q_proj",
     "v_proj",
-    "gate_proj",
-    "k_proj",
-    "up_proj",
     "down_proj",
-    "o_proj"
+    "o_proj",
+    "up_proj",
+    "k_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f3ee068cb784f259468df53d65d54d399587fd9295db82fbd33a59131a9ea84
+oid sha256:d30d259a2f935336e8381484f023135300a79591a4a9a8183febc6dd68014be9
 size 174909944

runs/Jan05_01-45-59_host-192-168-100-53/events.out.tfevents.1767577568.host-192-168-100-53.421560.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe1a58d3837e7a760b84b993eda1733bce8cf53291c709a032691fda2fd3b022
+size 8938

runs/Jan05_19-43-18_moleg-gpu/events.out.tfevents.1767642209.moleg-gpu.439133.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e58dff424b8739bdd4dc777f1e045998699d75ca18457a7fb06caf27137d666
+size 10073

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:424bd218ec34be5c6b1f9676d8829c564718b789cc1b5da41bd52a280e714184
+oid sha256:c3c306419a6b2f510c8235c00693c2274416193b3dcea2ef8c499cb3646c3cf4
 size 6225