Training in progress, step 75

README.md

@@ -1,11 +1,13 @@
 ---
 base_model: meta-llama/Meta-Llama-3-8B
+datasets:
+- HuggingFaceH4/ultrachat_200k
 library_name: peft
 license: llama3
 tags:
+- alignment-handbook
 - trl
 - sft
-- alignment-handbook
 - generated_from_trainer
 model-index:
 - name: llama3-sudo
@@ -17,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama3-sudo
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the HuggingFaceH4/ultrachat_200k dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.0709
 

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "down_proj",
-    "o_proj",
-    "q_proj",
     "v_proj",
     "gate_proj",
-    "up_proj"
+    "q_proj",
+    "up_proj",
+    "o_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 sha256:9c5d3d6ecfbbafb1f7f9d5d5266e75a74558d41cf12a70edea301f2ebb05a32f
+oid sha256:fad134c422e64503fd2453b15cbc3b5282376314193c5b72ae709ebc8d1d8cb7
 size 31516744

runs/Aug13_19-05-34_ip-172-31-10-237/events.out.tfevents.1723575945.ip-172-31-10-237.662759.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0a2e9501d49f2d39c1fe0716f1be50b5989245fe1dcc36ac2a948563b50e9f9
+size 5758

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef2cf294a0941096dc386e43b0615197a851de050108383ef1b8c57a6788d26a
+oid sha256:c99b33a61873ee90046c0f4b37c5fbe4914334128aec99b883a988415fb7ab5f
 size 6904