Upload folder using huggingface_hub

adapter_config.json

@@ -20,8 +20,8 @@
   "revision": null,
   "target_modules": [
     "gate_proj",
-    "down_proj",
-    "up_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:d27abc44b83d9536a18e48d1b5d1acec58690d543f08ec3bc180129cfacce754
+oid sha256:fa6340c6c21b5a2555d42ebd094af6dcbb30003201bf607ea3b4adc9d3ad4f77
 size 113271504

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbb43ed5cde46d7671c9cde1f0b4632f396c8671d6e8e05e02a1a10dce61b06f
+oid sha256:0fc782651d7d4e153c7b3fc44ecb67c9b5bd2d26d8f36da68c08c212696a1dd9
 size 226609018

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a152d54914a99d2f7db2490658aac5b35a045fbf5abfbd772cd982d209203b88
+oid sha256:cc28ac068ae9c17cfe666f59e9991687067bf7efa8f8c46d52a54671ec543b7e
 size 14244

trainer_state.json

@@ -11,145 +11,145 @@
     {
       "epoch": 0.04,
       "learning_rate": 2e-05,
-      "loss": 1.6156,
+      "loss": 1.6155,
       "step": 2
     },
     {
       "epoch": 0.08,
       "learning_rate": 2e-05,
-      "loss": 1.8413,
+      "loss": 1.8405,
       "step": 4
     },
     {
       "epoch": 0.12,
       "learning_rate": 2e-05,
-      "loss": 1.8148,
+      "loss": 1.8135,
       "step": 6
     },
     {
       "epoch": 0.16,
       "learning_rate": 2e-05,
-      "loss": 1.8909,
+      "loss": 1.8887,
       "step": 8
     },
     {
       "epoch": 0.21,
       "learning_rate": 2e-05,
-      "loss": 1.9389,
+      "loss": 1.9344,
       "step": 10
     },
     {
       "epoch": 0.25,
       "learning_rate": 2e-05,
-      "loss": 1.7122,
+      "loss": 1.7029,
       "step": 12
     },
     {
       "epoch": 0.29,
       "learning_rate": 2e-05,
-      "loss": 1.6582,
+      "loss": 1.6576,
       "step": 14
     },
     {
       "epoch": 0.33,
       "learning_rate": 2e-05,
-      "loss": 1.5327,
+      "loss": 1.531,
       "step": 16
     },
     {
       "epoch": 0.37,
       "learning_rate": 2e-05,
-      "loss": 1.8404,
+      "loss": 1.8376,
       "step": 18
     },
     {
       "epoch": 0.41,
       "learning_rate": 2e-05,
-      "loss": 1.6261,
+      "loss": 1.623,
       "step": 20
     },
     {
       "epoch": 0.45,
       "learning_rate": 2e-05,
-      "loss": 1.8265,
+      "loss": 1.8216,
       "step": 22
     },
     {
       "epoch": 0.49,
       "learning_rate": 2e-05,
-      "loss": 1.666,
+      "loss": 1.6551,
       "step": 24
     },
     {
       "epoch": 0.53,
       "learning_rate": 2e-05,
-      "loss": 1.5822,
+      "loss": 1.581,
       "step": 26
     },
     {
       "epoch": 0.57,
       "learning_rate": 2e-05,
-      "loss": 1.707,
+      "loss": 1.7052,
       "step": 28
     },
     {
       "epoch": 0.62,
       "learning_rate": 2e-05,
-      "loss": 1.8801,
+      "loss": 1.8765,
       "step": 30
     },
     {
       "epoch": 0.66,
       "learning_rate": 2e-05,
-      "loss": 1.6926,
+      "loss": 1.6884,
       "step": 32
     },
     {
       "epoch": 0.7,
       "learning_rate": 2e-05,
-      "loss": 1.6707,
+      "loss": 1.6657,
       "step": 34
     },
     {
       "epoch": 0.74,
       "learning_rate": 2e-05,
-      "loss": 1.7309,
+      "loss": 1.7195,
       "step": 36
     },
     {
       "epoch": 0.78,
       "learning_rate": 2e-05,
-      "loss": 1.6525,
+      "loss": 1.651,
       "step": 38
     },
     {
       "epoch": 0.82,
       "learning_rate": 2e-05,
-      "loss": 1.8128,
+      "loss": 1.8102,
       "step": 40
     },
     {
       "epoch": 0.86,
       "learning_rate": 2e-05,
-      "loss": 1.8849,
+      "loss": 1.8821,
       "step": 42
     },
     {
       "epoch": 0.9,
       "learning_rate": 2e-05,
-      "loss": 1.8942,
+      "loss": 1.8894,
       "step": 44
     },
     {
       "epoch": 0.94,
       "learning_rate": 2e-05,
-      "loss": 1.7441,
+      "loss": 1.7385,
       "step": 46
     },
     {
       "epoch": 0.98,
       "learning_rate": 2e-05,
-      "loss": 1.6244,
+      "loss": 1.6107,
       "step": 48
     }
   ],
@@ -158,7 +158,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,
-  "total_flos": 1.9274603770331136e+16,
+  "total_flos": 1.930658693426381e+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:cbf0cadb7632439b758dbdddf45638d03c8895f4124550635bac01522e2e59d3
+oid sha256:f76c7a494c5168464248de6e1be6d88051452d6dd246508974e2c5a27d3dbff3
 size 4728