Upload folder using huggingface_hub

adapter_config.json

@@ -19,9 +19,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
     "gate_proj",
-    "down_proj",
-    "up_proj"
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58d114eb040f54e2692a420917bec596c0695c0cd31485a0288b5e726b0ef589
+oid sha256:c11e80c2626b7e725c36b5d59e4313d238413de8eebfdb5b1d6b6e28ab8c714b
 size 113271504

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b645afabb74c2cf7ba011308647c11b78c30d0838c0a9c13339b1243b7030104
+oid sha256:87d135c01136a11bcef2ed383e09bc32d52fff97352f14798fe440aa0238e742
 size 226609018

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a8a82e80daa12ff099e617cf99473e3bb80028e142245ed1e3d1d876dcb1535
+oid sha256:b3698f87a076ace386d58713681a24c766465261225a60a74e4631003e3b501c
 size 14244

trainer_state.json

@@ -11,145 +11,145 @@
     {
       "epoch": 0.04,
       "learning_rate": 2e-05,
-      "loss": 1.6262,
+      "loss": 1.6235,
       "step": 2
     },
     {
       "epoch": 0.08,
       "learning_rate": 2e-05,
-      "loss": 1.8704,
+      "loss": 1.878,
       "step": 4
     },
     {
       "epoch": 0.12,
       "learning_rate": 2e-05,
-      "loss": 1.8716,
+      "loss": 1.8871,
       "step": 6
     },
     {
       "epoch": 0.16,
       "learning_rate": 2e-05,
-      "loss": 1.977,
+      "loss": 1.9954,
       "step": 8
     },
     {
       "epoch": 0.21,
       "learning_rate": 2e-05,
-      "loss": 2.0637,
+      "loss": 2.0806,
       "step": 10
     },
     {
       "epoch": 0.25,
       "learning_rate": 2e-05,
-      "loss": 2.0112,
+      "loss": 2.0435,
       "step": 12
     },
     {
       "epoch": 0.29,
       "learning_rate": 2e-05,
-      "loss": 1.6794,
+      "loss": 1.6826,
       "step": 14
     },
     {
       "epoch": 0.33,
       "learning_rate": 2e-05,
-      "loss": 1.5713,
+      "loss": 1.5779,
       "step": 16
     },
     {
       "epoch": 0.37,
       "learning_rate": 2e-05,
-      "loss": 1.8947,
+      "loss": 1.9058,
       "step": 18
     },
     {
       "epoch": 0.41,
       "learning_rate": 2e-05,
-      "loss": 1.6961,
+      "loss": 1.6972,
       "step": 20
     },
     {
       "epoch": 0.45,
       "learning_rate": 2e-05,
-      "loss": 1.9329,
+      "loss": 1.9398,
       "step": 22
     },
     {
       "epoch": 0.49,
       "learning_rate": 2e-05,
-      "loss": 1.9001,
+      "loss": 1.9236,
       "step": 24
     },
     {
       "epoch": 0.53,
       "learning_rate": 2e-05,
-      "loss": 1.6055,
+      "loss": 1.6062,
       "step": 26
     },
     {
       "epoch": 0.57,
       "learning_rate": 2e-05,
-      "loss": 1.7543,
+      "loss": 1.7559,
       "step": 28
     },
     {
       "epoch": 0.62,
       "learning_rate": 2e-05,
-      "loss": 1.9416,
+      "loss": 1.9474,
       "step": 30
     },
     {
       "epoch": 0.66,
       "learning_rate": 2e-05,
-      "loss": 1.7657,
+      "loss": 1.7649,
       "step": 32
     },
     {
       "epoch": 0.7,
       "learning_rate": 2e-05,
-      "loss": 1.7753,
+      "loss": 1.7762,
       "step": 34
     },
     {
       "epoch": 0.74,
       "learning_rate": 2e-05,
-      "loss": 1.9847,
+      "loss": 2.011,
       "step": 36
     },
     {
       "epoch": 0.78,
       "learning_rate": 2e-05,
-      "loss": 1.6714,
+      "loss": 1.6693,
       "step": 38
     },
     {
       "epoch": 0.82,
       "learning_rate": 2e-05,
-      "loss": 1.853,
+      "loss": 1.8561,
       "step": 40
     },
     {
       "epoch": 0.86,
       "learning_rate": 2e-05,
-      "loss": 1.9394,
+      "loss": 1.9452,
       "step": 42
     },
     {
       "epoch": 0.9,
       "learning_rate": 2e-05,
-      "loss": 1.9669,
+      "loss": 1.9725,
       "step": 44
     },
     {
       "epoch": 0.94,
       "learning_rate": 2e-05,
-      "loss": 1.8408,
+      "loss": 1.8454,
       "step": 46
     },
     {
       "epoch": 0.98,
       "learning_rate": 2e-05,
-      "loss": 1.8702,
+      "loss": 1.8836,
       "step": 48
     }
   ],
@@ -158,7 +158,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 1.931399969882112e+16,
+  "total_flos": 1.901574003725107e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09cc70b30444e968e7edb0b6e89583eb33e514fc6a008179a6727031b56aed62
+oid sha256:1142229c66bf3f832461258a15f379deffb2b5691470e753d093d27a4adb154c
 size 4728