Training in progress, epoch 1

README.md

@@ -5,8 +5,8 @@ model_name: DirectEd-AI-LoRA
 tags:
 - generated_from_trainer
 - unsloth
-- sft
 - trl
+- sft
 licence: license
 ---
 
@@ -28,7 +28,7 @@ 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/rayymondodhiambo-direct-ed/huggingface/runs/nw48kwk6) 
+[<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/rayymondodhiambo-direct-ed/huggingface/runs/dsz5n99x) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -15,23 +15,23 @@
   "loftq_config": {},
   "lora_alpha": 16,
   "lora_bias": false,
-  "lora_dropout": 0.1,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
   "qalora_group_size": 16,
-  "r": 16,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_proj",
+    "q_proj",
     "gate_proj",
     "up_proj",
-    "o_proj",
-    "q_proj",
     "v_proj",
-    "down_proj",
-    "k_proj"
+    "o_proj",
+    "down_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:decdeef352fbb944cf9c0c89b258f475a8f3732412ae0339320a247d5b3b219a
-size 167832240
+oid sha256:fce204dbde8c95ecb379a6057e4defa0af52f05622533787da96112cd94f1fd8
+size 83945296

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0eda646b7c5f41999cd0085002feca3955366d360842a8d838f298d30e477af
+oid sha256:b6b37da950f207ec10e24ffde6e97ff9e575c996e76fd531b2eb294ac69919b0
 size 6161