Training in progress, step 1320

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
     "q_proj",
     "v_proj",
+    "o_proj",
+    "up_proj",
     "k_proj",
     "down_proj",
-    "gate_proj",
-    "o_proj"
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26a041833c14429144d72883b3abe978039d7f7c9c002d1434d48284d51b6ef9
+oid sha256:4d0b060fabbf9b746f9929798f9d64794800599b65c5c8c428ffd57ce736e62f
 size 147770496

trainer_log.jsonl

@@ -1,20 +1,4 @@
-{"current_steps": 1090, "total_steps": 2553, "loss": 0.5212, "lr": 0.00018533655414523808, "epoch": 1.280763582966226, "percentage": 42.69, "elapsed_time": "0:30:20", "remaining_time": "0:40:43"}
-{"current_steps": 1100, "total_steps": 2553, "loss": 0.5124, "lr": 0.00018353297465909717, "epoch": 1.292511013215859, "percentage": 43.09, "elapsed_time": "1:00:44", "remaining_time": "1:20:14"}
-{"current_steps": 1110, "total_steps": 2553, "loss": 0.5177, "lr": 0.00018172427748758713, "epoch": 1.3042584434654918, "percentage": 43.48, "elapsed_time": "1:31:07", "remaining_time": "1:58:27"}
-{"current_steps": 1120, "total_steps": 2553, "loss": 0.4969, "lr": 0.0001799107386677475, "epoch": 1.3160058737151248, "percentage": 43.87, "elapsed_time": "2:01:30", "remaining_time": "2:35:27"}
-{"current_steps": 1130, "total_steps": 2553, "loss": 0.516, "lr": 0.0001780926349755332, "epoch": 1.3277533039647578, "percentage": 44.26, "elapsed_time": "2:31:57", "remaining_time": "3:11:21"}
-{"current_steps": 1140, "total_steps": 2553, "loss": 0.5035, "lr": 0.00017627024388357416, "epoch": 1.3395007342143905, "percentage": 44.65, "elapsed_time": "3:02:16", "remaining_time": "3:45:55"}
-{"current_steps": 1150, "total_steps": 2553, "loss": 0.5121, "lr": 0.00017444384351882817, "epoch": 1.3512481644640235, "percentage": 45.05, "elapsed_time": "3:32:38", "remaining_time": "4:19:25"}
-{"current_steps": 1160, "total_steps": 2553, "loss": 0.5289, "lr": 0.0001726137126201342, "epoch": 1.3629955947136563, "percentage": 45.44, "elapsed_time": "4:02:58", "remaining_time": "4:51:46"}
-{"current_steps": 1170, "total_steps": 2553, "loss": 0.5054, "lr": 0.0001707801304956723, "epoch": 1.3747430249632893, "percentage": 45.83, "elapsed_time": "4:33:23", "remaining_time": "5:23:10"}
-{"current_steps": 1180, "total_steps": 2553, "loss": 0.5067, "lr": 0.00016894337698033663, "epoch": 1.3864904552129222, "percentage": 46.22, "elapsed_time": "5:03:45", "remaining_time": "5:53:26"}
-{"current_steps": 1190, "total_steps": 2553, "loss": 0.5191, "lr": 0.00016710373239302772, "epoch": 1.398237885462555, "percentage": 46.61, "elapsed_time": "5:34:06", "remaining_time": "6:22:41"}
-{"current_steps": 1200, "total_steps": 2553, "loss": 0.5073, "lr": 0.00016526147749387155, "epoch": 1.409985315712188, "percentage": 47.0, "elapsed_time": "6:04:28", "remaining_time": "6:50:57"}
-{"current_steps": 1210, "total_steps": 2553, "loss": 0.5254, "lr": 0.00016341689344137088, "epoch": 1.4217327459618208, "percentage": 47.4, "elapsed_time": "6:34:56", "remaining_time": "7:18:20"}
-{"current_steps": 1220, "total_steps": 2553, "loss": 0.5116, "lr": 0.00016157026174949538, "epoch": 1.4334801762114537, "percentage": 47.79, "elapsed_time": "7:05:20", "remaining_time": "7:44:44"}
-{"current_steps": 1230, "total_steps": 2553, "loss": 0.5011, "lr": 0.00015972186424471855, "epoch": 1.4452276064610867, "percentage": 48.18, "elapsed_time": "7:35:43", "remaining_time": "8:10:11"}
-{"current_steps": 1240, "total_steps": 2553, "loss": 0.5116, "lr": 0.0001578719830230061, "epoch": 1.4569750367107195, "percentage": 48.57, "elapsed_time": "8:06:05", "remaining_time": "8:34:42"}
-{"current_steps": 1250, "total_steps": 2553, "loss": 0.4964, "lr": 0.00015602090040676324, "epoch": 1.4687224669603525, "percentage": 48.96, "elapsed_time": "8:36:31", "remaining_time": "8:58:25"}
-{"current_steps": 1260, "total_steps": 2553, "loss": 0.505, "lr": 0.00015416889890174792, "epoch": 1.4804698972099852, "percentage": 49.35, "elapsed_time": "9:06:54", "remaining_time": "9:21:13"}
-{"current_steps": 1270, "total_steps": 2553, "loss": 0.5065, "lr": 0.0001523162611539557, "epoch": 1.4922173274596182, "percentage": 49.75, "elapsed_time": "9:37:16", "remaining_time": "9:43:11"}
-{"current_steps": 1280, "total_steps": 2553, "loss": 0.5221, "lr": 0.0001504632699064833, "epoch": 1.5039647577092512, "percentage": 50.14, "elapsed_time": "10:07:36", "remaining_time": "10:04:17"}
+{"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"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a49238321d2ae273ae832df037aebeb48e69631a79ee654ea4afd0f8a123704
+oid sha256:58badb079f5cefd969162b37291c1530e842c46f5dd5c96ba22cc97d496fc630
 size 5752