End of training

README.md

@@ -42,7 +42,11 @@ The following hyperparameters were used during training:
 - optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 50
-- num_epochs: 1
+- num_epochs: 2
+
+### Training results
+
+
 
 ### Framework versions
 

adapter_config.json

@@ -27,11 +27,11 @@
   "revision": null,
   "target_modules": [
     "gate_proj",
-    "q_proj",
-    "up_proj",
+    "o_proj",
     "down_proj",
     "k_proj",
-    "o_proj",
+    "q_proj",
+    "up_proj",
     "v_proj"
   ],
   "task_type": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adc844e54620ab5e1daa75a845b9a575c90311e7aea9fde1a139a323049fab50
+oid sha256:2a2e53d3bee1c0d1caf2758304b9c914f73625ef752ec5e2426548a8006e5140
 size 42220792

runs/May25_14-39-53_0cf47b0eb397/events.out.tfevents.1748183994.0cf47b0eb397.117.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42390da8a68bd66d29bb42a5ce9951e96417217afee9beba516eeb7a0769d284
+size 8928

runs/May25_15-37-47_0cf47b0eb397/events.out.tfevents.1748187469.0cf47b0eb397.200.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92fa646bebc110b555a47d5bdf2047ee0f00715c55fa7684a97a30c9d87fb5f6
+size 9483

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06c75812d2a2dd36dec4877f8f200fcb145852b3d271d6268cdd1b5e75abf81b
+oid sha256:1d3d2b7e2de2c844e85a3cca6a7441b8062c79e6f749c032c706a53162d0a1eb
 size 5368