Upload folder using huggingface_hub

adapter_config.json

@@ -21,8 +21,8 @@
   "target_modules": [
     "query_key_value",
     "dense",
-    "dense_h_to_4h",
-    "dense_4h_to_h"
+    "dense_4h_to_h",
+    "dense_h_to_4h"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74d3c94430da216e49b2f1edfd4d47a96775b1caf13c23787dde2966ddb28ff6
+oid sha256:9c6fbc8839039d81518e809e09d04f26d0b62532c6bba65cc594b3d72b56418f
 size 134235712

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db0cfcb41260dc3ac3f0d2d7b951d685f8708331d34c01bad2d150ab37755fec
+oid sha256:1fcb6340b982aa0e8d5ec80efe728b52fbfcffab7aceaed128ea70997a523b77
 size 268514874

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8400da4ebd11656aee565d96885e25350dc287eec4ad76194986bfeef69bcc7
+oid sha256:6ea94740a278d2cdc43335e117d4b3125aa15fdbf70cc95cca4937d85340fc2b
 size 14244

trainer_state.json

@@ -11,145 +11,145 @@
     {
       "epoch": 0.04,
       "learning_rate": 0.0002,
-      "loss": 2.3426,
+      "loss": 2.2783,
       "step": 2
     },
     {
       "epoch": 0.08,
       "learning_rate": 0.0002,
-      "loss": 2.3786,
+      "loss": 2.5108,
       "step": 4
     },
     {
       "epoch": 0.12,
       "learning_rate": 0.0002,
-      "loss": 2.6959,
+      "loss": 2.6053,
       "step": 6
     },
     {
       "epoch": 0.16,
       "learning_rate": 0.0002,
-      "loss": 2.792,
+      "loss": 2.8587,
       "step": 8
     },
     {
       "epoch": 0.21,
       "learning_rate": 0.0002,
-      "loss": 2.8302,
+      "loss": 2.8002,
       "step": 10
     },
     {
       "epoch": 0.25,
       "learning_rate": 0.0002,
-      "loss": 3.3717,
+      "loss": 3.4071,
       "step": 12
     },
     {
       "epoch": 0.29,
       "learning_rate": 0.0002,
-      "loss": 2.2267,
+      "loss": 2.2816,
       "step": 14
     },
     {
       "epoch": 0.33,
       "learning_rate": 0.0002,
-      "loss": 2.5093,
+      "loss": 2.6214,
       "step": 16
     },
     {
       "epoch": 0.37,
       "learning_rate": 0.0002,
-      "loss": 2.7368,
+      "loss": 2.4466,
       "step": 18
     },
     {
       "epoch": 0.41,
       "learning_rate": 0.0002,
-      "loss": 2.5378,
+      "loss": 2.7186,
       "step": 20
     },
     {
       "epoch": 0.45,
       "learning_rate": 0.0002,
-      "loss": 2.6,
+      "loss": 2.6705,
       "step": 22
     },
     {
       "epoch": 0.49,
       "learning_rate": 0.0002,
-      "loss": 3.0639,
+      "loss": 3.3761,
       "step": 24
     },
     {
       "epoch": 0.53,
       "learning_rate": 0.0002,
-      "loss": 2.1673,
+      "loss": 2.2793,
       "step": 26
     },
     {
       "epoch": 0.57,
       "learning_rate": 0.0002,
-      "loss": 2.4645,
+      "loss": 2.2849,
       "step": 28
     },
     {
       "epoch": 0.62,
       "learning_rate": 0.0002,
-      "loss": 2.4987,
+      "loss": 2.3829,
       "step": 30
     },
     {
       "epoch": 0.66,
       "learning_rate": 0.0002,
-      "loss": 2.3191,
+      "loss": 2.6203,
       "step": 32
     },
     {
       "epoch": 0.7,
       "learning_rate": 0.0002,
-      "loss": 2.7003,
+      "loss": 2.5967,
       "step": 34
     },
     {
       "epoch": 0.74,
       "learning_rate": 0.0002,
-      "loss": 2.8433,
+      "loss": 2.7552,
       "step": 36
     },
     {
       "epoch": 0.78,
       "learning_rate": 0.0002,
-      "loss": 2.2216,
+      "loss": 2.1381,
       "step": 38
     },
     {
       "epoch": 0.82,
       "learning_rate": 0.0002,
-      "loss": 2.346,
+      "loss": 2.2939,
       "step": 40
     },
     {
       "epoch": 0.86,
       "learning_rate": 0.0002,
-      "loss": 2.3354,
+      "loss": 2.5408,
       "step": 42
     },
     {
       "epoch": 0.9,
       "learning_rate": 0.0002,
-      "loss": 2.4828,
+      "loss": 2.4259,
       "step": 44
     },
     {
       "epoch": 0.94,
       "learning_rate": 0.0002,
-      "loss": 2.6882,
+      "loss": 2.5202,
       "step": 46
     },
     {
       "epoch": 0.98,
       "learning_rate": 0.0002,
-      "loss": 2.7263,
+      "loss": 2.5082,
       "step": 48
     }
   ],
@@ -158,7 +158,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,
-  "total_flos": 2061789415243776.0,
+  "total_flos": 2050368575963136.0,
   "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 sha256:2d2faca9fc2994cb010b4af1851a2b88208d18c68e81e002db967e23a8aae6e1
+oid sha256:bbb5d771a6d1a018774cf9649db97eccab93bd3525027d97d1a3b3ef065d42e8
 size 4728