gemma2B-It-Coding-Finetuned-2epochs

README.md

@@ -43,7 +43,7 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2
+- training_steps: 451
 
 ### Training results
 

adapter_config.json

@@ -19,13 +19,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
     "up_proj",
-    "down_proj",
     "v_proj",
     "gate_proj",
-    "k_proj",
+    "down_proj",
     "o_proj",
-    "q_proj"
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3df46d8c03b83f70c4a2c7c8c2f8a92d2d5455ef5d473b3a00a169642a7ef101
+oid sha256:202b274d7cfce48f427a869a1e87765162165b48aed0adca4a609f5a9eb0648d
 size 156926880

runs/Apr26_04-36-09_4f9e32ec1dfa/events.out.tfevents.1714106175.4f9e32ec1dfa.188.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70387f632c1de41a6bb7861bd4de85b2cdd371f6a16b1e23ef2c60c0fcd80bb4
+size 14795

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0a5a7a9aa6c3ec5965de8f7081e98ec2cb46130a757de74ceac1b0f0c9f733f
+oid sha256:2db54742bc5a356f3fee65900dcf4a5691003e96737e433f3a8b2fbe148e3246
 size 4856