Upload folder using huggingface_hub

adapter_config.json

@@ -20,8 +20,8 @@
   "revision": null,
   "target_modules": [
     "gate_proj",
-    "up_proj",
-    "down_proj"
+    "down_proj",
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9185204c1ca65430df44f37ad7dc9a7d8607a11b8b14944579a99e1c1861986c
+oid sha256:f10ec4e175c8926be15da8555ee9990942c6796a23104d30110ee64eb5912082
 size 113271504

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d903b5e84103ffa728fdf2bc9491ed4b4ac2e5d6506c31daddd299090df94467
+oid sha256:5dd945d9e9d6260a85d9125554f7d8d87d0517f7b135b607c312f553a8c5d03f
 size 226609018

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e223434d2640d399673ae6c1909d730176bd2783c0124f8ea83ce13965cd95a8
+oid sha256:4c1b7936e437df962b46832c4b8e6fc59cbabca747ef4f7193ec40abad23a379
 size 14244

trainer_state.json

@@ -11,145 +11,145 @@
     {
       "epoch": 0.04,
       "learning_rate": 2e-05,
-      "loss": 1.7311,
+      "loss": 1.628,
       "step": 2
     },
     {
       "epoch": 0.08,
       "learning_rate": 2e-05,
-      "loss": 1.8755,
+      "loss": 1.7785,
       "step": 4
     },
     {
       "epoch": 0.12,
       "learning_rate": 2e-05,
-      "loss": 1.9054,
+      "loss": 1.7989,
       "step": 6
     },
     {
       "epoch": 0.16,
       "learning_rate": 2e-05,
-      "loss": 2.052,
+      "loss": 1.9499,
       "step": 8
     },
     {
       "epoch": 0.21,
       "learning_rate": 2e-05,
-      "loss": 2.174,
+      "loss": 2.083,
       "step": 10
     },
     {
       "epoch": 0.25,
       "learning_rate": 2e-05,
-      "loss": 2.3593,
+      "loss": 2.2934,
       "step": 12
     },
     {
       "epoch": 0.29,
       "learning_rate": 2e-05,
-      "loss": 1.6346,
+      "loss": 1.6058,
       "step": 14
     },
     {
       "epoch": 0.33,
       "learning_rate": 2e-05,
-      "loss": 1.5595,
+      "loss": 1.5273,
       "step": 16
     },
     {
       "epoch": 0.37,
       "learning_rate": 2e-05,
-      "loss": 1.851,
+      "loss": 1.8161,
       "step": 18
     },
     {
       "epoch": 0.41,
       "learning_rate": 2e-05,
-      "loss": 1.6995,
+      "loss": 1.6572,
       "step": 20
     },
     {
       "epoch": 0.45,
       "learning_rate": 2e-05,
-      "loss": 1.9828,
+      "loss": 1.9493,
       "step": 22
     },
     {
       "epoch": 0.49,
       "learning_rate": 2e-05,
-      "loss": 2.0154,
+      "loss": 2.0149,
       "step": 24
     },
     {
       "epoch": 0.53,
       "learning_rate": 2e-05,
-      "loss": 1.5442,
+      "loss": 1.5307,
       "step": 26
     },
     {
       "epoch": 0.57,
       "learning_rate": 2e-05,
-      "loss": 1.7272,
+      "loss": 1.7295,
       "step": 28
     },
     {
       "epoch": 0.62,
       "learning_rate": 2e-05,
-      "loss": 1.8829,
+      "loss": 1.8937,
       "step": 30
     },
     {
       "epoch": 0.66,
       "learning_rate": 2e-05,
-      "loss": 1.7181,
+      "loss": 1.7242,
       "step": 32
     },
     {
       "epoch": 0.7,
       "learning_rate": 2e-05,
-      "loss": 1.7273,
+      "loss": 1.7415,
       "step": 34
     },
     {
       "epoch": 0.74,
       "learning_rate": 2e-05,
-      "loss": 1.9079,
+      "loss": 2.0247,
       "step": 36
     },
     {
       "epoch": 0.78,
       "learning_rate": 2e-05,
-      "loss": 1.5964,
+      "loss": 1.6039,
       "step": 38
     },
     {
       "epoch": 0.82,
       "learning_rate": 2e-05,
-      "loss": 1.751,
+      "loss": 1.7683,
       "step": 40
     },
     {
       "epoch": 0.86,
       "learning_rate": 2e-05,
-      "loss": 1.8439,
+      "loss": 1.8772,
       "step": 42
     },
     {
       "epoch": 0.9,
       "learning_rate": 2e-05,
-      "loss": 1.8702,
+      "loss": 1.911,
       "step": 44
     },
     {
       "epoch": 0.94,
       "learning_rate": 2e-05,
-      "loss": 1.7397,
+      "loss": 1.7922,
       "step": 46
     },
     {
       "epoch": 0.98,
       "learning_rate": 2e-05,
-      "loss": 1.7357,
+      "loss": 1.908,
       "step": 48
     }
   ],
@@ -158,7 +158,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,
-  "total_flos": 1.6885823916957696e+16,
+  "total_flos": 1.6455943600201728e+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 sha256:1f7c6a339d11a6181488bf73e4550f6121f9691d255a16fbb92fea537306e476
+oid sha256:d7a1a06ce701b7de13923583a9ef790577ed56b6c9dde545519e13e3f431bf57
 size 4728