Training in progress, epoch 0

README.md

@@ -33,15 +33,15 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 2
-- eval_batch_size: 2
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 8
+- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.3
-- num_epochs: 3.0
+- training_steps: 700
 
 ### Framework versions
 

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a46f03532b11232c17467a6aefb63209734c07f337de0127d0f3000f023f4c84
+oid sha256:f21612564c2cfbe49eed1ad256b95567d4cc292abbc2f5399166991e8f203292
 size 50128536

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb314e67892030090c3943b43482eaa7ca80d2153cf01c6aa26d777dacee8a53
+oid sha256:49aec3c0a7659316c088ad7250bb3b9741cd44fba92bdc0275a4e23fca8369ad
 size 4792