Training in progress, step 1500, checkpoint

checkpoint-1500/adapter_config.json

@@ -27,11 +27,11 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "down_proj",
-    "v_proj",
-    "o_proj",
     "gate_proj",
     "q_proj",
+    "v_proj",
+    "o_proj",
+    "down_proj",
     "up_proj"
   ],
   "task_type": null,

checkpoint-1500/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:736f9428472d49ff9bb10a089262016c44e499be7a443d0bf223235834eb7f52
+oid sha256:9698ea5b1699956d3ef5f28fd15a9097f914db4fac2e26ac81e9451e8e918213
 size 400616360

checkpoint-1500/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9436e62b9451796e81f7647b2b8833e3eecd0409fd1d8f10bbc76514742a79c4
+oid sha256:10511162df0f726b38aeb6b98969b34695df0197203ebe76b60f019e22167883
 size 205100562

checkpoint-1500/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3c1e7da703c784fbc3d8152b1fc8d564276ea9ef45d6aa522d9bed4c7ac16ba
+oid sha256:46fdba27324dcfa656fab0568648f1c046ad9feeecdb7f542c62dd255167ea2a
 size 14308

checkpoint-1500/trainer_state.json

@@ -70,32 +70,32 @@
     },
     {
       "epoch": 1.167114015637764,
-      "grad_norm": 2.512282609939575,
+      "grad_norm": 2.2942659854888916,
       "learning_rate": 3.915853581228413e-05,
-      "loss": 0.614,
+      "loss": 0.7993,
       "step": 1250
     },
     {
       "epoch": 1.167114015637764,
-      "eval_loss": 0.1132238432765007,
-      "eval_runtime": 22.1933,
-      "eval_samples_per_second": 3.92,
-      "eval_steps_per_second": 3.92,
+      "eval_loss": 0.1208883598446846,
+      "eval_runtime": 21.9734,
+      "eval_samples_per_second": 3.959,
+      "eval_steps_per_second": 3.959,
       "step": 1250
     },
     {
       "epoch": 1.4005134788189988,
-      "grad_norm": 1.3006846904754639,
+      "grad_norm": 1.147830843925476,
       "learning_rate": 2.1903963223439395e-05,
-      "loss": 0.6601,
+      "loss": 0.7032,
       "step": 1500
     },
     {
       "epoch": 1.4005134788189988,
-      "eval_loss": 0.10768163949251175,
-      "eval_runtime": 22.1842,
-      "eval_samples_per_second": 3.922,
-      "eval_steps_per_second": 3.922,
+      "eval_loss": 0.10965924710035324,
+      "eval_runtime": 22.0058,
+      "eval_samples_per_second": 3.954,
+      "eval_steps_per_second": 3.954,
       "step": 1500
     }
   ],
@@ -116,7 +116,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2348081207667507e+17,
+  "total_flos": 1.228651871265792e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

checkpoint-1500/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37d85e10062490083f3df78142b22b936ee4c10ad7bb1c35d68c6a9743be03a9
+oid sha256:944c7c22023831a73ee4b0a66805723ecef65f25064cb419b24a8d84b3daee22
 size 5560