zjoe99/llama3-8B-Instruct-steiner-library

README.md

@@ -37,15 +37,15 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 8
+- train_batch_size: 4
 - eval_batch_size: 8
 - seed: 3407
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 32
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 5
-- num_epochs: 3.0
+- num_epochs: 2
 
 ### Training results
 
@@ -54,7 +54,7 @@ The following hyperparameters were used during training:
 ### Framework versions
 
 - PEFT 0.11.1
-- Transformers 4.42.0.dev0
-- Pytorch 2.2.2+cu121
+- Transformers 4.41.1
+- Pytorch 2.2.0+cu121
 - Datasets 2.19.1
 - Tokenizers 0.19.1

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cfb9057da32a336f6726f50a078043a99711e7ce8efdcfd28a72ea406f6f89a
+oid sha256:5fe512bedc04eb97ada1673eee5367034b3ca7e61ca447795e4aaf588b6e6d43
 size 167832240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e65499aa34223dba129336bb32a8fd015707bfc358f4f9346747af2ecb4e1d04
+oid sha256:7a4800816280e78a2f44433fe1d38c4d51c12caef2d8c9ccceb0b98dffcf5fb4
 size 5048