Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "v_proj",
     "gate_proj",
+    "o_proj",
     "k_proj",
-    "up_proj",
+    "down_proj",
     "q_proj",
-    "down_proj"
+    "v_proj",
+    "up_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:d8d8922cf3433da19d55bab922e4a9bed346e220554ece8c65741d65f42eda69
+oid sha256:01960c5e1f5b72a78a1dd316f7fba2dfb311c68a86d2fd73de1685758c366af5
 size 31064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d3f6d2587de2c8b58c83a431b60d54c714d9f8fc73af60714df6d0b94140e20
+oid sha256:f9981dc4e68fd59b5254f8a770c06502def6e142f2073751cfe7e5a6e752855c
 size 71718

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd5570560c2d5878b2576c09a6170f9a8f99ca083bdaa5f34d36575a3cd13599
+oid sha256:6e7b432d4c1390a80984e093813a079e02823704a7187bbae0ecafb3a9eb8384
 size 14244

last-checkpoint/trainer_state.json

@@ -11,9 +11,9 @@
     {
       "epoch": 7.697192449054207e-05,
       "eval_loss": 10.37826156616211,
-      "eval_runtime": 83.245,
-      "eval_samples_per_second": 65.722,
-      "eval_steps_per_second": 32.867,
+      "eval_runtime": 23.951,
+      "eval_samples_per_second": 228.425,
+      "eval_steps_per_second": 114.233,
       "step": 1
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c50167299a7ac562bf6b762b6e79596a72bd3b103dec7d8d05007b09b987414
+oid sha256:52d79810d23038375259e98ee1deb701984e2d15994ef059a65eb865be018715
 size 6776