Training in progress, epoch 0, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
+    "k_proj",
     "o_proj",
-    "q_proj",
     "v_proj",
+    "down_proj",
+    "q_proj",
     "up_proj",
-    "k_proj",
     "gate_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce889c1b56dadd0942b925e6de45bf71aa0a9c9ffadf129d077ad2986782a6ee
+oid sha256:37f0b12f2df5b0f3a16b7ba5390c20a6022432d02060e6a2ece844b4bb2d9204
 size 9048

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:890e339ff3b0082dccf8090baf1a7c8e81295a4f0de3d844065b1f278b04eaa3
+oid sha256:2749564122b2ed1557383859e91ce01e2a9d8a5d85d8597b9a79b78bf4318a06
 size 28134

last-checkpoint/trainer_state.json

@@ -10,17 +10,17 @@
   "log_history": [
     {
       "epoch": 0.0002666666666666667,
-      "grad_norm": 0.012360014952719212,
+      "grad_norm": 0.014745122753083706,
       "learning_rate": 0.0,
       "loss": 11.9308,
       "step": 1
     },
     {
       "epoch": 0.0002666666666666667,
-      "eval_loss": 11.933904647827148,
-      "eval_runtime": 0.0571,
-      "eval_samples_per_second": 280.314,
-      "eval_steps_per_second": 70.079,
+      "eval_loss": 11.933927536010742,
+      "eval_runtime": 0.0608,
+      "eval_samples_per_second": 263.08,
+      "eval_steps_per_second": 65.77,
       "step": 1
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ed2474dc1833860e185880c916dc528fb94a7070794e01413baaa70703a8e01
+oid sha256:5e6b8dcb9a6ffeb8b79cc321155c4fedef9714808cc00d893dbca15f2cb3911b
 size 6776