qlora-llama2-7b-question-generation-eduqg

README.md

@@ -32,14 +32,14 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 1
-- eval_batch_size: 1
+- train_batch_size: 4
+- eval_batch_size: 4
 - seed: 42
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 4
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 9
+- num_epochs: 10
 
 ### Training results
 

adapter_config.json

@@ -16,8 +16,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9026fa5734c7d8e195d928191eb11d32d5e05eb8455bc9bdc176dca77273c000
+oid sha256:913e8254c2e0e7fab8dd0cb3902e6ccc76bdcc1a7eeb407c84e312218bb603a0
 size 16822989

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 1024,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44ce4fd3212f03b378c2fd5c40f6ddeffb9fba512eb8f1a24e427ac892db9ec5
+oid sha256:20267de5e18ec40118e0e493cce3e4f294bde9ee71fb5c53154ae0351e9afdb9
 size 4155