Training in progress, epoch 0, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
     "v_proj",
+    "q_proj",
+    "down_proj",
     "o_proj",
-    "gate_proj",
-    "up_proj",
     "k_proj",
-    "down_proj"
+    "up_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91a9ea1223ba85bbea9348c544be11652f89e0e757979feed1bcb01f6c918891
+oid sha256:7b49608e88641713ee5a2f11cc0f9b4df4195c3ece8e936a8dd4dced5882d814
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:336c1293365b64ddb78543f3bc45d81537f442d08bc1806978f0ed670257d124
+oid sha256:ea761731c07c68e93df9c9f52a0c1f1bc01f318ce497dba7102ff183eda25794
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9999fe17ac6d10df0b24edf483ce019f56daddfb3edc069a21c03ccaa11df1b8
+oid sha256:a833f22f25ea3834727974efdfc06b3927711900cd9acb75c7c0258b248c9673
 size 14244

last-checkpoint/trainer_state.json

@@ -10,24 +10,24 @@
   "log_history": [
     {
       "epoch": 6.727664155005382e-05,
-      "grad_norm": 17.90272331237793,
+      "grad_norm": 16.59201431274414,
       "learning_rate": 0.0001,
       "loss": 7.986,
       "step": 1
     },
     {
       "epoch": 0.00013455328310010763,
-      "grad_norm": 3.7075886726379395,
+      "grad_norm": 3.2888948917388916,
       "learning_rate": 0.0002,
       "loss": 2.0306,
       "step": 2
     },
     {
       "epoch": 0.00013455328310010763,
-      "eval_loss": 2.1211705207824707,
-      "eval_runtime": 5.4013,
-      "eval_samples_per_second": 27.956,
-      "eval_steps_per_second": 27.956,
+      "eval_loss": 2.1215152740478516,
+      "eval_runtime": 5.4188,
+      "eval_samples_per_second": 27.866,
+      "eval_steps_per_second": 27.866,
       "step": 2
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f7cf9b3f4a9b6aee0af9bb352b3071b1f748975269b94023838baf634daee8c
+oid sha256:8b6377427e4e4bf683c90c59945e864e887a68d19ec55ff4999690a80faf10af
 size 6776