Training in progress, step 31

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "down_proj",
     "up_proj",
-    "gate_proj",
     "o_proj",
+    "k_proj",
     "q_proj",
-    "v_proj"
+    "v_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 sha256:146cce1d6188e1d4b0bc36075b62e93e0091e454992eb2fc4986069115efdfde
+oid sha256:4eebc8dd067a4ac394a35e70db650418ea190f22a29a5be8b60b2a4dbbe4e651
 size 207244392

trainer_log.jsonl

@@ -1 +1,5 @@
-{"current_steps": 8, "total_steps": 8, "epoch": 0.9552238805970149, "percentage": 100.0, "elapsed_time": "0:11:51", "remaining_time": "0:00:00"}
+{"current_steps": 10, "total_steps": 31, "loss": 0.668, "lr": 8.83022221559489e-05, "epoch": 0.321285140562249, "percentage": 32.26, "elapsed_time": "0:13:04", "remaining_time": "0:27:28"}
+{"current_steps": 20, "total_steps": 31, "loss": 0.4073, "lr": 3.5659838364445505e-05, "epoch": 0.642570281124498, "percentage": 64.52, "elapsed_time": "0:26:11", "remaining_time": "0:14:24"}
+{"current_steps": 30, "total_steps": 31, "loss": 0.3531, "lr": 3.380821129028489e-07, "epoch": 0.963855421686747, "percentage": 96.77, "elapsed_time": "0:39:13", "remaining_time": "0:01:18"}
+{"current_steps": 30, "total_steps": 31, "eval_loss": 0.32887399196624756, "epoch": 0.963855421686747, "percentage": 96.77, "elapsed_time": "0:39:30", "remaining_time": "0:01:19"}
+{"current_steps": 31, "total_steps": 31, "epoch": 0.9959839357429718, "percentage": 100.0, "elapsed_time": "0:42:09", "remaining_time": "0:00:00"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:058e4ba0cdee1722cfd170be1c8ac7edeeb9bc813920d3f14ab604c7bba852cd
+oid sha256:48f0672495e21950dd6e656d1f09c349e8d7d9df9bf90e3befd54f5b08064f2b
 size 7608