Model save

README.md

@@ -38,9 +38,9 @@ The following hyperparameters were used during training:
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
+- lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 1
-- training_steps: 1000
+- training_steps: 450
 
 ### Training results
 

adapter_config.json

@@ -9,21 +9,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 64,
+  "lora_alpha": 128,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "Wqkv",
+    "fc2",
     "q_proj",
+    "Wqkv",
+    "k_proj",
+    "fc1",
     "v_proj",
-    "o_proj",
-    "k_proj"
+    "lm_head"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:237aa290cca279c1e402541888847ab7312e76606f8f49753d343c425a3f31b6
-size 109086416
+oid sha256:ecbb44d3c58cb17f5f4e3bdeb0553c16f615e449488d3227588014ff6e1aaadc
+size 417785576

runs/Jan14_13-44-39_60866f00c1af/events.out.tfevents.1705239882.60866f00c1af.3226.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:791341e61db248dbfbb16feec659c8b67bbc9d510511c87f88812c366ab8bc8b
+size 6552

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c8a2de949eba61884dd1c7aabff6bc08d5006b850b0b2f9f4c48d472f128edc
+oid sha256:eef709b4d90610876357531cbdc5fc518e1bc1fac2c0610ea66ee80d24a94904
 size 4728