fkjsdahfjkasf/sft-Llama-3-8B

adapter_config.json

@@ -15,21 +15,21 @@
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": [
-    "embed_tokens",
-    "lm_head"
+    "lm_head",
+    "embed_tokens"
   ],
   "peft_type": "LORA",
   "r": 16,
   "rank_pattern": {},
   "revision": "unsloth",
   "target_modules": [
+    "q_proj",
     "k_proj",
+    "down_proj",
     "gate_proj",
     "up_proj",
-    "q_proj",
-    "o_proj",
-    "down_proj",
-    "v_proj"
+    "v_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

runs/Jun10_00-44-06_150-136-147-171/events.out.tfevents.1717980250.150-136-147-171.16227.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c520a46f378e743a2533c57929b7b8088bfdfd3bb069f6c5606827622e6ab1a8
+size 5723

trainer_state.json

@@ -14,8 +14,8 @@
       "step": 1,
       "total_flos": 6348239762620416.0,
       "train_loss": 2.5150043964385986,
-      "train_runtime": 45.5008,
-      "train_samples_per_second": 0.352,
+      "train_runtime": 45.5311,
+      "train_samples_per_second": 0.351,
       "train_steps_per_second": 0.022
     }
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e3ad79e0fa9bae84cea9f2ff76b21e0fd174a4b7ab94d8ed5bbcaff2563d4ee
+oid sha256:68234b6943b94c1487c8251f3f9a6e3ede15155d223d03798197eaf89641b76c
 size 5112