Training in progress, epoch 0, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
+    "gate_proj",
     "k_proj",
-    "o_proj",
+    "v_proj",
     "down_proj",
     "q_proj",
-    "gate_proj",
-    "v_proj"
+    "o_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:f25359b683e22b03b52ac4093c485073114aedd358f879a11e84cf90e49a4a93
+oid sha256:5e91ecc3215812954a830f1f723d3eedc0c15dbb2e729c236a25ebebff95a5ea
 size 9048

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ded90c3181b31ec9bbc4afc53a003b8495f6c9234eeca06d2be815e87a774daf
+oid sha256:8a3417c1810d1006c9fdc86a246e24fb6fb6a16f833a1c9b9fddfd514117cd35
 size 28134

last-checkpoint/trainer_state.json

@@ -10,17 +10,17 @@
   "log_history": [
     {
       "epoch": 0.0002666666666666667,
-      "grad_norm": 0.018526403233408928,
+      "grad_norm": 0.02039993554353714,
       "learning_rate": 0.0,
       "loss": 11.9308,
       "step": 1
     },
     {
       "epoch": 0.0002666666666666667,
-      "eval_loss": 11.933902740478516,
-      "eval_runtime": 0.0582,
-      "eval_samples_per_second": 275.089,
-      "eval_steps_per_second": 68.772,
+      "eval_loss": 11.933893203735352,
+      "eval_runtime": 0.0595,
+      "eval_samples_per_second": 269.009,
+      "eval_steps_per_second": 67.252,
       "step": 1
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbe6e9ba442b0bc5f9aa6ba82a0cda937bd3591b0b1cf9d2912657df85f80600
+oid sha256:4262191338f57e0cb296b0162fc58ae0cec82361790f58f1dc600363293ba4aa
 size 6776