Training in progress, step 12600

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d7f04d35541d77dbff70445b4364fcae91e44972bf3ab7e69103b284501ed21
+oid sha256:366c6b6fac1cdd0e18cf44acfca9bdaee8477bb25d98740a7f9f89e4f4ba07d2
 size 161533160

trainer_log.jsonl

@@ -1,11 +1,2 @@
-{"current_steps": 12050, "total_steps": 18120, "loss": 0.3633, "lr": 3.0470536893814385e-05, "epoch": 1.9950331125827816, "percentage": 66.5, "elapsed_time": "0:03:10", "remaining_time": "0:01:36"}
-{"current_steps": 12080, "total_steps": 18120, "eval_loss": 0.38875386118888855, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:36:36", "remaining_time": "0:18:18"}
-{"current_steps": 12100, "total_steps": 18120, "loss": 0.3221, "lr": 3.0028102791373535e-05, "epoch": 2.0033112582781456, "percentage": 66.78, "elapsed_time": "0:37:49", "remaining_time": "0:18:48"}
-{"current_steps": 12150, "total_steps": 18120, "loss": 0.281, "lr": 2.9587521598880573e-05, "epoch": 2.01158940397351, "percentage": 67.05, "elapsed_time": "0:41:00", "remaining_time": "0:20:08"}
-{"current_steps": 12200, "total_steps": 18120, "loss": 0.2824, "lr": 2.914883419163475e-05, "epoch": 2.019867549668874, "percentage": 67.33, "elapsed_time": "0:44:12", "remaining_time": "0:21:27"}
-{"current_steps": 12250, "total_steps": 18120, "loss": 0.2986, "lr": 2.871208126923771e-05, "epoch": 2.0281456953642385, "percentage": 67.6, "elapsed_time": "0:47:14", "remaining_time": "0:22:38"}
-{"current_steps": 12300, "total_steps": 18120, "loss": 0.2852, "lr": 2.827730335181765e-05, "epoch": 2.0364238410596025, "percentage": 67.88, "elapsed_time": "0:50:32", "remaining_time": "0:23:54"}
-{"current_steps": 12350, "total_steps": 18120, "loss": 0.2905, "lr": 2.7844540776269924e-05, "epoch": 2.044701986754967, "percentage": 68.16, "elapsed_time": "0:53:57", "remaining_time": "0:25:12"}
-{"current_steps": 12400, "total_steps": 18120, "loss": 0.2791, "lr": 2.7413833692514844e-05, "epoch": 2.052980132450331, "percentage": 68.43, "elapsed_time": "0:57:06", "remaining_time": "0:26:20"}
-{"current_steps": 12450, "total_steps": 18120, "loss": 0.2887, "lr": 2.698522205977273e-05, "epoch": 2.0612582781456954, "percentage": 68.71, "elapsed_time": "1:00:18", "remaining_time": "0:27:27"}
-{"current_steps": 12500, "total_steps": 18120, "loss": 0.2845, "lr": 2.655874564285656e-05, "epoch": 2.0695364238410594, "percentage": 68.98, "elapsed_time": "1:03:33", "remaining_time": "0:28:34"}
+{"current_steps": 12550, "total_steps": 18120, "loss": 0.284, "lr": 2.613444400848287e-05, "epoch": 2.077814569536424, "percentage": 69.26, "elapsed_time": "0:03:10", "remaining_time": "0:01:24"}
+{"current_steps": 12600, "total_steps": 18120, "loss": 0.2852, "lr": 2.571235652160091e-05, "epoch": 2.0860927152317883, "percentage": 69.54, "elapsed_time": "0:06:12", "remaining_time": "0:02:43"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d239bd5c15d3a2ea118383dc904ef4e598d66c2b3b3c72f570384f15cfc1fc71
+oid sha256:03460364198bac94559385f580ca233415d6d940ccd70edd3903925ee0255ba2
 size 5752