End of training

README.md

@@ -34,10 +34,10 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0003
-- train_batch_size: 2
+- train_batch_size: 1
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 4
+- gradient_accumulation_steps: 8
 - total_train_batch_size: 8
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear

adapter_config.json

@@ -11,16 +11,16 @@
   "lora_dropout": 0.0,
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 16,
   "revision": null,
   "target_modules": [
     "down_proj",
+    "o_proj",
     "gate_proj",
     "k_proj",
-    "v_proj",
     "q_proj",
     "up_proj",
-    "o_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9ada0c0165015c8d9d417ac280537b96af25ee8bd2b1c6b7487f8e6b2c0fa3e
-size 30026872
+oid sha256:5726e7adba0ffa9bd5595d9805747c225cdbccd48b3b09dd166de2cd030c8c14
+size 60010048

runs/Feb28_21-47-26_MithilAIPC/events.out.tfevents.1709137063.MithilAIPC.21972.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afafafb319e4575efe8b3adf127667590d8d8e6a66cc2119abcd1cee2dcd12c4
+size 61640

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa16865030827f9fad3a591dca26dada37f9eaf1064fed7d73acf24a10266580
+oid sha256:b14540e54927bf4ada65bb0a09730d1638b1954faa287b90513f0b43eba12172
 size 5048