Training in progress, epoch 0, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "o_proj",
+    "gate_proj",
     "q_proj",
-    "up_proj",
-    "k_proj",
-    "v_proj",
     "down_proj",
-    "gate_proj"
+    "k_proj",
+    "up_proj",
+    "v_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 sha256:768130b538ea1d5a1152be5ed27852633d520795cfc581e156f38e25a9f04356
+oid sha256:1509ef8e6237faed0830eba67f6bdc88d9d5a88c8acb12515a0a11b164c4b733
 size 9048

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d706c2370200c1786d57bb980305f5a163b0acd690ff7b30a12844072e5868f
+oid sha256:3fbff8c9b3e554d5a9e30365930e0b58928598e0823ab9a2f4a301f18488f192
 size 28134

last-checkpoint/trainer_state.json

@@ -10,17 +10,17 @@
   "log_history": [
     {
       "epoch": 0.0002666666666666667,
-      "grad_norm": 0.018520789220929146,
+      "grad_norm": 0.014081359840929508,
       "learning_rate": 0.0,
       "loss": 11.9308,
       "step": 1
     },
     {
       "epoch": 0.0002666666666666667,
-      "eval_loss": 11.933884620666504,
-      "eval_runtime": 0.0597,
-      "eval_samples_per_second": 268.023,
-      "eval_steps_per_second": 67.006,
+      "eval_loss": 11.933910369873047,
+      "eval_runtime": 0.0581,
+      "eval_samples_per_second": 275.442,
+      "eval_steps_per_second": 68.86,
       "step": 1
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8548aef348062ab97cfd36e886231d4b654c2eb3c3a782e77117273c0546ae9a
+oid sha256:25466abd5e997c477f14121d1249700b11515d3fbb0d02027f9d5d17e8c65066
 size 6776