Model save

README.md

@@ -33,16 +33,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0002
+- learning_rate: 2e-05
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: constant
-- lr_scheduler_warmup_ratio: 0.03
-- num_epochs: 20
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1
+- training_steps: 600
 
 ### Training results
 

adapter_config.json

@@ -9,23 +9,19 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
-  "lora_dropout": 0.1,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "fc1",
-    "lm_head",
     "fc2",
-    "k_proj",
-    "q_proj",
-    "v_proj",
-    "o_proj"
+    "Wqkv"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6138b3893e6e44c9fe18b3f0aebcb7b4c4214d1d5beaae8ec322c75312525af0
-size 347895224
+oid sha256:938c81d80c5697ea34ffc97fb6746f15711094a749088acbe9dd2ce4a023ecb6
+size 104873776

runs/Jan13_15-57-48_de4d1e082919/events.out.tfevents.1705161472.de4d1e082919.5358.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bff8b9d48bf185027819bb073c700f163b172e8f2ef2e1639222be1e43abb17e
+size 9142

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b7c8bb8d4339fa7bfee37f1783b0e8244d19d07328a7beb9d45a5fe4df442b6
+oid sha256:0a9fcd3d4e1cc8d0546ad802bd848a8839faa8d48f2d990b59761f90abe82ca9
 size 4728