Training in progress, step 50

README.md

@@ -27,7 +27,7 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/3dsmile/huggingface/runs/g6zfeh4a) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/3dsmile/huggingface/runs/jakraxed) 
 
 
 

adapter_config.json

@@ -18,7 +18,7 @@
   "loftq_config": {},
   "lora_alpha": 8,
   "lora_bias": false,
-  "lora_dropout": 0.1,
+  "lora_dropout": 0.5,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
@@ -29,9 +29,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
     "v_proj",
-    "o_proj",
-    "q_proj"
+    "o_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76845a7d11e09cf3ab7f54f8a3bbcba95c905c11d4a623fabeac430a60849cc0
+oid sha256:c2aff3304412ebf9f557e21f860d483fb4d0b5bf2a616a9b306301266fd98e96
 size 5071040

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a392a9e7f82ea8de586f47e98377e27c28ee661d8a50836c651a3874c36c1c6
+oid sha256:ab5119290ef739338f8821ed9a10f587abc0eb8c8ef9e9516369bbe2c814ea74
 size 5649