Training in progress, step 1750, checkpoint

checkpoint-1750/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-1750/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1c8109fc65b0d8615d46fbe71b71141f41de6cec6a0502bca2610787d9246f8
+oid sha256:295a3701e85f024dd17479cad12f5298eb6c1e9a6927ffb58ed5462836a7b846
 size 400616360

checkpoint-1750/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f60ee02a42f7991f5208e8baa2d32c3951fb94d54acbab2c010606d9ba6f3dde
+oid sha256:aa5962e9c44f6bdb64830af5766bc1f7edda27e4d64356d877f5059a8c1c29f6
 size 205100562

checkpoint-1750/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3240fd44f8548b12441af7b5c9c267d29c3ea86e935e03bb0c123a56e39f3a2
+oid sha256:1f9c5082699d30c0f1953a76da5ea5d539e6209fc8f0085fd232a2d2abbfebed
 size 14308

checkpoint-1750/trainer_state.json

@@ -70,47 +70,47 @@
     },
     {
       "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
     },
     {
       "epoch": 1.6339129420002334,
-      "grad_norm": 1.7093279361724854,
+      "grad_norm": 2.2439823150634766,
       "learning_rate": 8.619209196560924e-06,
-      "loss": 0.6404,
+      "loss": 0.6596,
       "step": 1750
     },
     {
       "epoch": 1.6339129420002334,
-      "eval_loss": 0.10490020364522934,
-      "eval_runtime": 22.1702,
-      "eval_samples_per_second": 3.924,
-      "eval_steps_per_second": 3.924,
+      "eval_loss": 0.10602504760026932,
+      "eval_runtime": 22.0084,
+      "eval_samples_per_second": 3.953,
+      "eval_steps_per_second": 3.953,
       "step": 1750
     }
   ],
@@ -131,7 +131,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4253324554464051e+17,
+  "total_flos": 1.415876128180654e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

checkpoint-1750/training_args.bin

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