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: 1
+- num_epochs: 3
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -54,5 +54,5 @@ The following hyperparameters were used during training:
 - PEFT 0.10.1.dev0
 - Transformers 4.41.0.dev0
 - Pytorch 2.2.1+cu121
-- Datasets 2.19.0
+- Datasets 2.19.1
 - Tokenizers 0.19.1

adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "gate_proj",
-    "v_proj",
     "down_proj",
-    "up_proj",
     "k_proj",
+    "v_proj",
     "o_proj",
-    "q_proj"
+    "q_proj",
+    "up_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:d1f0736dbb2d8db18a46c977e0125d538d5be483f90a7f567dcfa79ad09d8002
+oid sha256:61b01ce3a999bdf7ccfa2243bb2c065694f330dc9988bea822b939b703dcab7a
 size 159967880

runs/May09_05-06-05_41086c82618e/events.out.tfevents.1715231174.41086c82618e.248.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6624c04af54e6e70fd644d0793b778fb4e9339c5275f051c8abb917e149e5ad3
+size 174217

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:883143816298e734338b7af64b339f3b76a8d6c98b146a91df9b9d98f59465ab
-size 4984
+oid sha256:84f53dab64744e5bc930c91d04c02e6f01e89b27cf50a2cef2f767e0c44bf6a8
+size 5112