Training in progress, epoch 0, checkpoint

last-checkpoint/adapter_config.json

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

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1509ef8e6237faed0830eba67f6bdc88d9d5a88c8acb12515a0a11b164c4b733
+oid sha256:389feb1cf7e09bf0d90a44d07d61d7f735f797e8865b11c13d494e098291ec81
 size 9048

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fbff8c9b3e554d5a9e30365930e0b58928598e0823ab9a2f4a301f18488f192
+oid sha256:21710edc9af4f5a7713369516124e72ee866e971f6aa4121b38175cce196a7da
 size 28134

last-checkpoint/trainer_state.json

@@ -10,17 +10,17 @@
   "log_history": [
     {
       "epoch": 0.0002666666666666667,
-      "grad_norm": 0.014081359840929508,
+      "grad_norm": 0.02084502950310707,
       "learning_rate": 0.0,
       "loss": 11.9308,
       "step": 1
     },
     {
       "epoch": 0.0002666666666666667,
-      "eval_loss": 11.933910369873047,
-      "eval_runtime": 0.0581,
-      "eval_samples_per_second": 275.442,
-      "eval_steps_per_second": 68.86,
+      "eval_loss": 11.933904647827148,
+      "eval_runtime": 0.0598,
+      "eval_samples_per_second": 267.596,
+      "eval_steps_per_second": 66.899,
       "step": 1
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25466abd5e997c477f14121d1249700b11515d3fbb0d02027f9d5d17e8c65066
+oid sha256:578047ac6d20cb709ae6ac1ae98498a9b6b689cfaadf5290cc78e5a4548ec16d
 size 6776