Training in progress, step 1100

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate_proj",
     "q_proj",
     "v_proj",
-    "k_proj",
-    "up_proj",
+    "o_proj",
     "down_proj",
-    "gate_proj",
-    "o_proj"
+    "k_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 sha256:027c28cbacad0920c7a8ec1a4dbaf396f0658e37d9c57aa24903513cf568bf29
+oid sha256:787bc21c0f2f2b1700fe11ae2508811d7577a4d6cdbd205375ea95707cebbc4c
 size 161533160

trainer_log.jsonl

@@ -23,3 +23,5 @@
 {"current_steps": 900, "total_steps": 18120, "loss": 0.7661, "lr": 4.961368653421634e-05, "epoch": 0.1490066225165563, "percentage": 4.97, "elapsed_time": "0:44:50", "remaining_time": "14:17:55"}
 {"current_steps": 950, "total_steps": 18120, "loss": 0.736, "lr": 5.237306843267108e-05, "epoch": 0.15728476821192053, "percentage": 5.24, "elapsed_time": "0:48:01", "remaining_time": "14:27:51"}
 {"current_steps": 1000, "total_steps": 18120, "loss": 0.7213, "lr": 5.513245033112583e-05, "epoch": 0.16556291390728478, "percentage": 5.52, "elapsed_time": "0:51:22", "remaining_time": "14:39:39"}
+{"current_steps": 1050, "total_steps": 18120, "loss": 0.7335, "lr": 5.789183222958058e-05, "epoch": 0.173841059602649, "percentage": 5.79, "elapsed_time": "0:03:19", "remaining_time": "0:54:03"}
+{"current_steps": 1100, "total_steps": 18120, "loss": 0.7326, "lr": 6.065121412803533e-05, "epoch": 0.18211920529801323, "percentage": 6.07, "elapsed_time": "0:06:27", "remaining_time": "1:39:52"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dd2ef96eff028fc6db83c8627ce2e789cafe652a25ea367c040819bc392f916
+oid sha256:2543e07a37d2c3de3cd8e1d682eb10ddfc7a8cf84209a331e0b0e44870af81c3
 size 5752