Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "q_proj",
-    "o_proj",
+    "k_proj",
     "down_proj",
-    "gate_proj",
     "v_proj",
-    "up_proj"
+    "up_proj",
+    "o_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:da65eabaff7444caebfca33a37a9f8c43cd8d44d08a32899b2ea4fe748ab1eb4
+oid sha256:c5af6ceb3181bdf7e95868525dbe4d63abbe2473764de299720779b4cbec0c86
 size 35237104

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8580306d32b005c0733c680a2aa90baffc7bb3fab9f44ba259f139790c0142d8
+oid sha256:b066a8111fb29f260f02e04781565f7c6f077dac9e7e2f1f2830addf102652f8
 size 14244

last-checkpoint/trainer_state.json

@@ -18,9 +18,9 @@
     {
       "epoch": 0.0022988505747126436,
       "eval_loss": NaN,
-      "eval_runtime": 42.2453,
-      "eval_samples_per_second": 4.356,
-      "eval_steps_per_second": 2.178,
+      "eval_runtime": 55.532,
+      "eval_samples_per_second": 3.313,
+      "eval_steps_per_second": 1.657,
       "step": 1
     },
     {
@@ -40,9 +40,9 @@
     {
       "epoch": 0.006896551724137931,
       "eval_loss": NaN,
-      "eval_runtime": 55.0777,
-      "eval_samples_per_second": 3.341,
-      "eval_steps_per_second": 1.67,
+      "eval_runtime": 54.6552,
+      "eval_samples_per_second": 3.367,
+      "eval_steps_per_second": 1.683,
       "step": 3
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d591a82bd15320e6a861c112681dce84191047c1aa2c6eed1c86e87e1a090555
+oid sha256:1f6b294cad946c00780426710004bacbf6fd30dfe8b06f26312ddc12c2facb93
 size 6776