Training in progress, step 240

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "v_proj",
-    "gate_proj",
-    "up_proj",
     "down_proj",
+    "q_proj",
+    "gate_proj",
     "o_proj",
-    "q_proj"
+    "up_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 sha256:6a5b201474c187e2e8dddeedec78e1ca8b7e62cde52cbd25cd6fa01b80a0812f
+oid sha256:e8f96b84f3521835e4c2e7bd5f9446c2060ce1c248af900530e1e084ead567ee
 size 147770496

trainer_log.jsonl

@@ -1,20 +1,4 @@
-{"current_steps": 10, "total_steps": 851, "loss": 3.0983, "lr": 0.00027, "epoch": 0.011747430249632892, "percentage": 1.18, "elapsed_time": "0:31:47", "remaining_time": "1 day, 20:33:15"}
-{"current_steps": 20, "total_steps": 851, "loss": 2.062, "lr": 0.00029991523567092526, "epoch": 0.023494860499265784, "percentage": 2.35, "elapsed_time": "1:04:02", "remaining_time": "1 day, 20:20:46"}
-{"current_steps": 30, "total_steps": 851, "loss": 1.2074, "lr": 0.00029962234616583063, "epoch": 0.03524229074889868, "percentage": 3.53, "elapsed_time": "1:36:16", "remaining_time": "1 day, 19:54:30"}
-{"current_steps": 40, "total_steps": 851, "loss": 0.888, "lr": 0.00029912069357315393, "epoch": 0.04698972099853157, "percentage": 4.7, "elapsed_time": "2:08:27", "remaining_time": "1 day, 19:24:35"}
-{"current_steps": 50, "total_steps": 851, "loss": 0.7685, "lr": 0.0002984109778320875, "epoch": 0.05873715124816446, "percentage": 5.88, "elapsed_time": "2:40:40", "remaining_time": "1 day, 18:54:06"}
-{"current_steps": 60, "total_steps": 851, "loss": 0.7096, "lr": 0.00029749418918542057, "epoch": 0.07048458149779736, "percentage": 7.05, "elapsed_time": "3:12:51", "remaining_time": "1 day, 18:22:25"}
-{"current_steps": 70, "total_steps": 851, "loss": 0.6901, "lr": 0.0002963716067978866, "epoch": 0.08223201174743025, "percentage": 8.23, "elapsed_time": "3:45:02", "remaining_time": "1 day, 17:50:45"}
-{"current_steps": 80, "total_steps": 851, "loss": 0.6702, "lr": 0.000295044796971387, "epoch": 0.09397944199706314, "percentage": 9.4, "elapsed_time": "4:17:13", "remaining_time": "1 day, 17:18:56"}
-{"current_steps": 90, "total_steps": 851, "loss": 0.6353, "lr": 0.000293515610959582, "epoch": 0.10572687224669604, "percentage": 10.58, "elapsed_time": "4:49:24", "remaining_time": "1 day, 16:47:10"}
-{"current_steps": 100, "total_steps": 851, "loss": 0.6479, "lr": 0.0002917861823848985, "epoch": 0.11747430249632893, "percentage": 11.75, "elapsed_time": "5:21:32", "remaining_time": "1 day, 16:14:43"}
-{"current_steps": 110, "total_steps": 851, "loss": 0.6244, "lr": 0.0002898589242615568, "epoch": 0.12922173274596183, "percentage": 12.93, "elapsed_time": "5:53:44", "remaining_time": "1 day, 15:42:52"}
-{"current_steps": 120, "total_steps": 851, "loss": 0.6217, "lr": 0.0002877365256287728, "epoch": 0.14096916299559473, "percentage": 14.1, "elapsed_time": "6:25:57", "remaining_time": "1 day, 15:11:05"}
-{"current_steps": 130, "total_steps": 851, "loss": 0.6022, "lr": 0.00028542194779883047, "epoch": 0.1527165932452276, "percentage": 15.28, "elapsed_time": "6:58:09", "remaining_time": "1 day, 14:39:12"}
-{"current_steps": 140, "total_steps": 851, "loss": 0.6098, "lr": 0.00028291842022526133, "epoch": 0.1644640234948605, "percentage": 16.45, "elapsed_time": "7:30:23", "remaining_time": "1 day, 14:07:21"}
-{"current_steps": 150, "total_steps": 851, "loss": 0.5971, "lr": 0.0002802294359968954, "epoch": 0.1762114537444934, "percentage": 17.63, "elapsed_time": "8:02:40", "remaining_time": "1 day, 13:35:40"}
-{"current_steps": 160, "total_steps": 851, "loss": 0.5937, "lr": 0.0002773587469640702, "epoch": 0.18795888399412627, "percentage": 18.8, "elapsed_time": "8:34:53", "remaining_time": "1 day, 13:03:40"}
-{"current_steps": 170, "total_steps": 851, "loss": 0.6054, "lr": 0.0002743103585037989, "epoch": 0.19970631424375918, "percentage": 19.98, "elapsed_time": "9:07:06", "remaining_time": "1 day, 12:31:40"}
-{"current_steps": 180, "total_steps": 851, "loss": 0.5708, "lr": 0.0002710885239312008, "epoch": 0.21145374449339208, "percentage": 21.15, "elapsed_time": "9:39:20", "remaining_time": "1 day, 11:59:38"}
-{"current_steps": 190, "total_steps": 851, "loss": 0.5806, "lr": 0.00026769773856499167, "epoch": 0.22320117474302498, "percentage": 22.33, "elapsed_time": "10:11:34", "remaining_time": "1 day, 11:27:38"}
-{"current_steps": 200, "total_steps": 851, "loss": 0.5747, "lr": 0.0002641427334553158, "epoch": 0.23494860499265785, "percentage": 23.5, "elapsed_time": "10:43:48", "remaining_time": "1 day, 10:55:37"}
+{"current_steps": 210, "total_steps": 851, "loss": 0.5879, "lr": 0.00026042846878266795, "epoch": 0.24669603524229075, "percentage": 24.68, "elapsed_time": "0:33:05", "remaining_time": "1:41:00"}
+{"current_steps": 220, "total_steps": 851, "loss": 0.5852, "lr": 0.0002565601269371192, "epoch": 0.25844346549192365, "percentage": 25.85, "elapsed_time": "1:06:33", "remaining_time": "3:10:55"}
+{"current_steps": 230, "total_steps": 851, "loss": 0.5605, "lr": 0.0002525431052874997, "epoch": 0.2701908957415565, "percentage": 27.03, "elapsed_time": "1:39:59", "remaining_time": "4:29:59"}
+{"current_steps": 240, "total_steps": 851, "loss": 0.5738, "lr": 0.00024838300865062966, "epoch": 0.28193832599118945, "percentage": 28.2, "elapsed_time": "2:13:28", "remaining_time": "5:39:47"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c61b7597101ee42620ee3c35211c8aaa2dd701dc84ac03219baa5f43c59a2eff
-size 5688
+oid sha256:8973bbd1b103ead50852e2b114af48d9e0d924c6ae8eab7404eef91ab656cddc
+size 5752