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: 10
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1
+- training_steps: 1000
 
 ### Training results
 

adapter_config.json

@@ -9,23 +9,21 @@
   "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": [
-    "o_proj",
-    "lm_head",
-    "fc1",
+    "Wqkv",
+    "q_proj",
     "v_proj",
-    "fc2",
-    "k_proj",
-    "q_proj"
+    "o_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efd736c90b15f356780147dae56463cfbe1c0e5beef56524bacbf283c5a1790a
-size 317859784
+oid sha256:237aa290cca279c1e402541888847ab7312e76606f8f49753d343c425a3f31b6
+size 109086416

runs/Jan13_16-39-56_43d25185addb/events.out.tfevents.1705163999.43d25185addb.678.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c76c82e9b213e7ce9815e8893eaf216c64f9e2db50c2a18ad88e8ad077718bd4
+size 11410

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2495eb5076d2474723846771f9e298838160ad6f2a34c86cea4b5dbf746c1e6
+oid sha256:5c8a2de949eba61884dd1c7aabff6bc08d5006b850b0b2f9f4c48d472f128edc
 size 4728