Training in progress, step 9, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "gate_proj",
-    "up_proj",
-    "q_proj",
-    "k_proj",
     "o_proj",
     "v_proj",
-    "down_proj"
+    "down_proj",
+    "q_proj",
+    "k_proj",
+    "up_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:c360edff80728fafd8cfc09751d999c00b0be881df81017d54ddde2bf224869a
+oid sha256:36cb19536a0ee12ba49afa380ccf1fe42bf2babf1ab11886688b238a01ddf2f1
 size 767856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:957cf9cc03cb6f6f33ad0d9ba529ac55ed46a849e31be8980dd4652a4513c48b
+oid sha256:b2c2e866352e6cb817611d33e434459e9b3504c82f49d59cd12a975eb6f753aa
 size 1003002

last-checkpoint/trainer_state.json

@@ -18,9 +18,9 @@
     {
       "epoch": 0.00554016620498615,
       "eval_loss": 10.876238822937012,
-      "eval_runtime": 1.1301,
-      "eval_samples_per_second": 67.253,
-      "eval_steps_per_second": 33.627,
+      "eval_runtime": 1.1366,
+      "eval_samples_per_second": 66.868,
+      "eval_steps_per_second": 33.434,
       "step": 1
     },
     {
@@ -40,67 +40,67 @@
     {
       "epoch": 0.01662049861495845,
       "eval_loss": 10.876238822937012,
-      "eval_runtime": 1.0865,
-      "eval_samples_per_second": 69.949,
-      "eval_steps_per_second": 34.975,
+      "eval_runtime": 1.1359,
+      "eval_samples_per_second": 66.907,
+      "eval_steps_per_second": 33.453,
       "step": 3
     },
     {
       "epoch": 0.0221606648199446,
-      "grad_norm": 17.566349029541016,
+      "grad_norm": 17.855396270751953,
       "learning_rate": 2e-05,
       "loss": 11.1469,
       "step": 4
     },
     {
       "epoch": 0.027700831024930747,
-      "grad_norm": 17.940860748291016,
+      "grad_norm": 17.642831802368164,
       "learning_rate": 4e-05,
       "loss": 10.8969,
       "step": 5
     },
     {
       "epoch": 0.0332409972299169,
-      "grad_norm": 20.539535522460938,
+      "grad_norm": 21.13235855102539,
       "learning_rate": 6e-05,
-      "loss": 10.8141,
+      "loss": 10.8178,
       "step": 6
     },
     {
       "epoch": 0.0332409972299169,
-      "eval_loss": 10.789344787597656,
-      "eval_runtime": 1.1219,
-      "eval_samples_per_second": 67.744,
-      "eval_steps_per_second": 33.872,
+      "eval_loss": 10.794831275939941,
+      "eval_runtime": 1.1175,
+      "eval_samples_per_second": 68.007,
+      "eval_steps_per_second": 34.004,
       "step": 6
     },
     {
       "epoch": 0.038781163434903045,
-      "grad_norm": 23.39402961730957,
+      "grad_norm": 23.375688552856445,
       "learning_rate": 8e-05,
-      "loss": 10.8841,
+      "loss": 10.8872,
       "step": 7
     },
     {
       "epoch": 0.0443213296398892,
-      "grad_norm": 17.9848690032959,
+      "grad_norm": 18.43400001525879,
       "learning_rate": 0.0001,
-      "loss": 10.4167,
+      "loss": 10.4152,
       "step": 8
     },
     {
       "epoch": 0.04986149584487535,
-      "grad_norm": 16.139219284057617,
+      "grad_norm": 16.53175163269043,
       "learning_rate": 0.00012,
-      "loss": 10.8235,
+      "loss": 10.8378,
       "step": 9
     },
     {
       "epoch": 0.04986149584487535,
-      "eval_loss": 10.459603309631348,
-      "eval_runtime": 1.1553,
-      "eval_samples_per_second": 65.786,
-      "eval_steps_per_second": 32.893,
+      "eval_loss": 10.476703643798828,
+      "eval_runtime": 1.1452,
+      "eval_samples_per_second": 66.363,
+      "eval_steps_per_second": 33.182,
       "step": 9
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9bb8d12ab7d3707b6887bbd0a3831cfac8994e15c07c849a86e5da758026626
+oid sha256:dbdcc855d0f57473d8bd7ab766a229753c5c71be0fbef544d11bf2fb79cc11ff
 size 6712