Training in progress, step 1400

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj",
-    "o_proj",
-    "up_proj",
     "k_proj",
     "down_proj",
-    "gate_proj"
+    "v_proj",
+    "up_proj",
+    "o_proj",
+    "gate_proj",
+    "q_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:a903e293d9130992fc0cf87b99a1cdeb8d31fca7a018d5f7518b387884f58806
+oid sha256:1615841c13c049e702c516acde8d23f94d7116112383ee44425bbf84b72e56d7
 size 147770496

trainer_log.jsonl

@@ -1,8 +1,4 @@
-{"current_steps": 1290, "total_steps": 2553, "loss": 0.5057, "lr": 0.00014861020795637716, "epoch": 1.515712187958884, "percentage": 50.53, "elapsed_time": "0:34:36", "remaining_time": "0:33:53"}
-{"current_steps": 1300, "total_steps": 2553, "loss": 0.5054, "lr": 0.00014675735811147444, "epoch": 1.5274596182085167, "percentage": 50.92, "elapsed_time": "1:09:46", "remaining_time": "1:07:14"}
-{"current_steps": 1310, "total_steps": 2553, "loss": 0.5083, "lr": 0.00014490500314724117, "epoch": 1.5392070484581497, "percentage": 51.31, "elapsed_time": "1:44:55", "remaining_time": "1:39:33"}
-{"current_steps": 1320, "total_steps": 2553, "loss": 0.5157, "lr": 0.0001430534257636167, "epoch": 1.5509544787077827, "percentage": 51.7, "elapsed_time": "2:20:05", "remaining_time": "2:10:51"}
-{"current_steps": 1330, "total_steps": 2553, "loss": 0.5151, "lr": 0.00014120290854186863, "epoch": 1.5627019089574157, "percentage": 52.1, "elapsed_time": "2:55:11", "remaining_time": "2:41:05"}
-{"current_steps": 1340, "total_steps": 2553, "loss": 0.507, "lr": 0.00013935373390146634, "epoch": 1.5744493392070484, "percentage": 52.49, "elapsed_time": "3:30:20", "remaining_time": "3:10:24"}
-{"current_steps": 1350, "total_steps": 2553, "loss": 0.4973, "lr": 0.00013750618405697912, "epoch": 1.5861967694566812, "percentage": 52.88, "elapsed_time": "4:05:30", "remaining_time": "3:38:46"}
-{"current_steps": 1360, "total_steps": 2553, "loss": 0.5033, "lr": 0.0001356605409750058, "epoch": 1.5979441997063142, "percentage": 53.27, "elapsed_time": "4:40:38", "remaining_time": "4:06:11"}
+{"current_steps": 1370, "total_steps": 2553, "loss": 0.5259, "lr": 0.0001340013252947644, "epoch": 1.6096916299559472, "percentage": 53.66, "elapsed_time": "0:34:02", "remaining_time": "0:29:23"}
+{"current_steps": 1380, "total_steps": 2553, "loss": 0.5164, "lr": 0.00013216008080267535, "epoch": 1.6214390602055802, "percentage": 54.05, "elapsed_time": "1:08:10", "remaining_time": "0:57:57"}
+{"current_steps": 1390, "total_steps": 2553, "loss": 0.5011, "lr": 0.0001303215589766901, "epoch": 1.633186490455213, "percentage": 54.45, "elapsed_time": "1:42:17", "remaining_time": "1:25:35"}
+{"current_steps": 1400, "total_steps": 2553, "loss": 0.5096, "lr": 0.00012848604040558272, "epoch": 1.6449339207048457, "percentage": 54.84, "elapsed_time": "2:16:30", "remaining_time": "1:52:25"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58badb079f5cefd969162b37291c1530e842c46f5dd5c96ba22cc97d496fc630
+oid sha256:4096d841cf7ca75806307b6c6b7d6fa53491e67ad1132e299019b216142f58b9
 size 5752