Training in progress, step 110

README.md

@@ -1,7 +1,7 @@
 ---
 base_model: unsloth/Qwen2.5-3B
 library_name: transformers
-model_name: LinalgZero-SFT-LoRA-110
+model_name: LinalgZero-SFT-LoRA
 tags:
 - generated_from_trainer
 - trl
@@ -10,7 +10,7 @@ tags:
 licence: license
 ---
 
-# Model Card for LinalgZero-SFT-LoRA-110
+# Model Card for LinalgZero-SFT-LoRA
 
 This model is a fine-tuned version of [unsloth/Qwen2.5-3B](https://huggingface.co/unsloth/Qwen2.5-3B).
 It has been trained using [TRL](https://github.com/huggingface/trl).
@@ -21,14 +21,14 @@ It has been trained using [TRL](https://github.com/huggingface/trl).
 from transformers import pipeline
 
 question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="atomwalk12/LinalgZero-SFT-LoRA-110", device="cuda")
+generator = pipeline("text-generation", model="atomwalk12/LinalgZero-SFT-LoRA", device="cuda")
 output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
 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/walks/huggingface/runs/792qyuam) 
+[<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/walks/huggingface/runs/uiedinmd) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -26,8 +26,8 @@
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": [
-    "embed_tokens",
-    "lm_head"
+    "lm_head",
+    "embed_tokens"
   ],
   "peft_type": "LORA",
   "peft_version": "0.18.0",
@@ -36,13 +36,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "q_proj",
+    "v_proj",
+    "up_proj",
     "k_proj",
     "o_proj",
     "down_proj",
-    "up_proj",
-    "v_proj"
+    "gate_proj",
+    "q_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:a3f2b372d6aeea60530f751ba48f385afd7c89ffb307eadc0d5e6762cc02bbb4
+oid sha256:f72d883a1c3a4341e417fc1b68deddb63a663d0797f2c08a6e1d94b9b50ee7a0
 size 1484196216