Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

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

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dca2bcde728c1316c586604226b9a8c611a0346135c9d427617c021f1d3fda4
+oid sha256:b069ee7b70bb60b5691094986439731ee28ddd97dd404651df10a79171d23fb3
 size 78480072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5094de5ea3761e4fc7455c931e9db37abc48a3139da25aa5ee907bb55f4c3fb7
+oid sha256:f25ffa6634e51987dfee95d92295d60be14b999b7c0d78503e84a89c717f8f69
 size 40131268

last-checkpoint/trainer_state.json

@@ -18,31 +18,31 @@
     {
       "epoch": 0.0007328691828508611,
       "eval_loss": 12.304828643798828,
-      "eval_runtime": 56.9499,
-      "eval_samples_per_second": 5.057,
-      "eval_steps_per_second": 5.057,
+      "eval_runtime": 57.0786,
+      "eval_samples_per_second": 5.046,
+      "eval_steps_per_second": 5.046,
       "step": 1
     },
     {
       "epoch": 0.0014657383657017222,
-      "grad_norm": 42.04989242553711,
+      "grad_norm": 39.946189880371094,
       "learning_rate": 2e-05,
       "loss": 10.6283,
       "step": 2
     },
     {
       "epoch": 0.0021986075485525836,
-      "grad_norm": 37.467315673828125,
+      "grad_norm": 36.35205078125,
       "learning_rate": 4e-05,
       "loss": 11.3833,
       "step": 3
     },
     {
       "epoch": 0.0021986075485525836,
-      "eval_loss": 12.051217079162598,
-      "eval_runtime": 56.814,
-      "eval_samples_per_second": 5.069,
-      "eval_steps_per_second": 5.069,
+      "eval_loss": 12.076598167419434,
+      "eval_runtime": 56.5009,
+      "eval_samples_per_second": 5.097,
+      "eval_steps_per_second": 5.097,
       "step": 3
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:722f3b82bb852127c4404471dd8bb057b70f4e0cb5a02b713538b276ca5a19c9
+oid sha256:72b5ec9cd53bed712805221792024653bec1693ae9132893c54190849f7ca423
 size 6712