End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # sft-facebook-opt350m-with-openassistant-guanaco
 
-This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) on an unknown dataset.
+This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) on the timdettmers/openassistant-guanaco dataset.
 
 ## Model description
 
@@ -39,8 +39,8 @@ The following hyperparameters were used during training:
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 8
-- total_train_batch_size: 64
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 2

adapter_config.json

@@ -9,18 +9,18 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
-  "lora_dropout": 0.0,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 64,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f968e69207bb3e51f03d98b1015c8923cd404db013687103e634d080158f72d
-size 25179464
+oid sha256:c66041ec5a8b52098b462db6d2538321f408e44d9eee952b015bec26a558fcfb
+size 6304960

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:673b6188cc33a2f3ab86bafadb849cd6162716f1866c18f4ca4cfa745ff38430
+oid sha256:a40c87389451a1dea6ad023a4cb2eba1ab84e1235fbcb4026668893ea46224ab
 size 4347