Training in progress, step 96

README.md

@@ -1,5 +1,6 @@
 ---
 base_model: meta-llama/Llama-3.2-1B-Instruct
+datasets: shoubing35/ones_digit_sft_dataset
 library_name: transformers
 model_name: llama-1B-sft
 tags:
@@ -11,7 +12,7 @@ licence: license
 
 # Model Card for llama-1B-sft
 
-This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct).
+This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) on the [shoubing35/ones_digit_sft_dataset](https://huggingface.co/datasets/shoubing35/ones_digit_sft_dataset) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

adapter_config.json

@@ -25,13 +25,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
+    "q_proj",
+    "o_proj",
     "gate_proj",
     "down_proj",
-    "v_proj",
-    "q_proj",
     "up_proj",
-    "o_proj"
+    "v_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad5e0be0bf861ae1ea915e650ed3bb716183a321b6351d19cfac595d7763ff90
+oid sha256:e90b7de9cf798cd9aad14f56ca6acb17039673580d56050f860e8915562c73bd
 size 1095792688

runs/Apr18_02-07-45_ed4ef8575fbd/events.out.tfevents.1744942081.ed4ef8575fbd.3850.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e77ffd0b63a2f8929c6758ae250dccd2a6f2da76270cfc766da9f8aec9d1050
+size 17331

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72822d278e5c197834640a0b7cab79e3ff0e57f55fc11eed4e505a440e532bf8
+oid sha256:59e83b8eb8734725929f6a51ccc9a7f035ab2c05e6ea36559e2b9d0a6cbfa604
 size 5688