trungtienluong/test_4

README.md

@@ -42,7 +42,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.05
-- num_epochs: 7
+- num_epochs: 10
 - mixed_precision_training: Native AMP
 
 ### Training results

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
+    "up_proj",
     "o_proj",
-    "q_proj",
+    "down_proj",
     "k_proj",
     "gate_proj",
-    "v_proj",
-    "down_proj",
-    "up_proj"
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4b1331bffb184cc7eb85d081a7b414a6f126d00d74ba63c290abd0f09d77e55
+oid sha256:e686aec745766170201296dac402cc6dad9c1070a164599fbcd980416997031e
 size 159967880

runs/May16_04-21-12_902ee609b897/events.out.tfevents.1715833281.902ee609b897.3205.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78c8db4f72010892e4211ceeb8fa7e1af74e81da118c83054051b6379f01d523
+size 16059

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76ae282d19828978a486033e8c0be252981b35c060ad225a07935993e4919daa
+oid sha256:2e39e9f1f73757c32bc747d16b460a587a3f35762e3b54b1918213bf7c9648e1
 size 5112