Babu/llava-1.5-7b-hf-ft-mix-vsft

README.md

@@ -55,7 +55,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 10
 - mixed_precision_training: Native AMP
 
 ### Training results

adapter_config.json

@@ -17,15 +17,15 @@
   "r": 64,
   "revision": null,
   "target_modules": [
-    "linear_1",
     "gate_proj",
+    "linear_2",
     "up_proj",
-    "k_proj",
-    "v_proj",
     "o_proj",
+    "linear_1",
+    "k_proj",
     "down_proj",
-    "linear_2",
-    "q_proj"
+    "q_proj",
+    "v_proj"
   ],
   "task_type": null
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:064b4c86e07a8a78da8c9b2f621141f309d68b3bec3e87bfc15dc74d6db7602e
+oid sha256:c1f7055bfc5bd426cadf386e9095fd84b1031c170ff79fa50351bb496b63b6aa
 size 680879440

runs/Jul24_14-43-57_e2e-101-73/events.out.tfevents.1721832278.e2e-101-73.6375.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f36d0396395eb592a3b27992eaad0cf34bf21be3e6a93a6787c47c6a237d181d
+size 6971

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4501ef6a612ed7baffccacf62e4012c655590f492a76ec18a511a08d97e88879
+oid sha256:ed30224af0208cac2e049e584e2cc266d206ba4aa1d7b277d2da41d2bf5c1e46
 size 4475