Training in progress, step 2560

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
+    "gate_proj",
+    "down_proj",
     "up_proj",
     "v_proj",
-    "k_proj",
     "o_proj",
-    "q_proj",
-    "down_proj",
-    "gate_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:c2863fab9f406d2423827a29fb4911c4a5eb67f96ba7c0890fb3308a4360f9b8
+oid sha256:101b530fa255b128b00b1b8f5241ccacfcd8da47b9e0be5d960596d0f29b9b81
 size 147770496

trainer_log.jsonl

@@ -1,4 +1 @@
-{"current_steps": 2530, "total_steps": 2553, "loss": 0.4732, "lr": 7.153420977766278e-08, "epoch": 2.9726872246696034, "percentage": 99.1, "elapsed_time": "0:31:46", "remaining_time": "0:00:17"}
-{"current_steps": 2540, "total_steps": 2553, "loss": 0.4826, "lr": 2.5753625660224208e-08, "epoch": 2.9844346549192364, "percentage": 99.49, "elapsed_time": "1:03:22", "remaining_time": "0:00:19"}
-{"current_steps": 2550, "total_steps": 2553, "loss": 0.4913, "lr": 2.8615867500414447e-09, "epoch": 2.9961820851688694, "percentage": 99.88, "elapsed_time": "1:34:54", "remaining_time": "0:00:06"}
-{"current_steps": 2553, "total_steps": 2553, "epoch": 2.999706314243759, "percentage": 100.0, "elapsed_time": "1:44:23", "remaining_time": "0:00:00"}
+{"current_steps": 2560, "total_steps": 5106, "loss": 0.5113, "lr": 0.00015, "epoch": 3.008225616921269, "percentage": 50.14, "elapsed_time": "0:20:27", "remaining_time": "0:20:20"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcdc753965d8ff82bf636220b660b6606d164e4abf268fe254d867087721e8a7
+oid sha256:bc83588d1e0d411a76deaf141db7902e3202185b9cc735f0b37ac7fed1ba9382
 size 5752