End of training

README.md

@@ -35,13 +35,15 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 6
+- train_batch_size: 12
 - eval_batch_size: 48
 - seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 48
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.03
-- training_steps: 50
+- training_steps: 100
 - mixed_precision_training: Native AMP
 
 ### Training results

adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "dense_4h_to_h",
     "dense",
     "query_key_value",
-    "dense_h_to_4h"
+    "dense_h_to_4h",
+    "dense_4h_to_h"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82e8fce004b9e89d75b0b615c8d5a1127430f35bbca1cab4df0df707c093eb4e
+oid sha256:c288ff854713bcfa6217a1c218a5830891e76b64cb2a94ec63c8441f2c66903d
 size 522227376

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0b599ed3288d0990c345f1678563aee156692f6216b0605e94086af099a0313
+oid sha256:a67960fbfa9a0773a29843b8b60848e019458d5fe2a159ae7a4fc8827c8c18d2
 size 4984