Upload folder using huggingface_hub

adapter_config.json

@@ -19,10 +19,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "dense",
     "query_key_value",
     "dense_h_to_4h",
-    "dense_4h_to_h"
+    "dense_4h_to_h",
+    "dense"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bebd68776a4a61cb1f4f81939eaf7f8e14cde232d04f0af2894676460b6433c
+oid sha256:c3baf4ee4567db97a49b48158b16509bfceffa809ea7e34d84bbc203f80b5285
 size 134235712

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a928ccde6a9c2011fa546fdb58512b2cab3585ac2aac2aac229b06dfffabdec4
+oid sha256:3047c1a800fcc0d22e3a53d3e0feb2c29f781621d2aa28a88866a3f19a87eda8
 size 268514874

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2409359a63e121485fe24a344ba36e669f278d392404a09304404248de3e122
+oid sha256:983276a93b8f5b51345a0c6f7f4469d5c415c6b7581581e389dc0705b248c852
 size 14244

trainer_state.json

@@ -11,154 +11,154 @@
     {
       "epoch": 0.04,
       "learning_rate": 0.0002,
-      "loss": 2.3695,
+      "loss": 2.2923,
       "step": 2
     },
     {
       "epoch": 0.08,
       "learning_rate": 0.0002,
-      "loss": 2.3951,
+      "loss": 2.4944,
       "step": 4
     },
     {
       "epoch": 0.12,
       "learning_rate": 0.0002,
-      "loss": 2.5973,
+      "loss": 2.5643,
       "step": 6
     },
     {
       "epoch": 0.16,
       "learning_rate": 0.0002,
-      "loss": 2.5197,
+      "loss": 2.5449,
       "step": 8
     },
     {
       "epoch": 0.21,
       "learning_rate": 0.0002,
-      "loss": 2.5993,
+      "loss": 2.5427,
       "step": 10
     },
     {
       "epoch": 0.25,
       "learning_rate": 0.0002,
-      "loss": 2.7419,
+      "loss": 2.8026,
       "step": 12
     },
     {
       "epoch": 0.29,
       "learning_rate": 0.0002,
-      "loss": 2.2986,
+      "loss": 2.2733,
       "step": 14
     },
     {
       "epoch": 0.33,
       "learning_rate": 0.0002,
-      "loss": 2.3248,
+      "loss": 2.3667,
       "step": 16
     },
     {
       "epoch": 0.37,
       "learning_rate": 0.0002,
-      "loss": 2.5489,
+      "loss": 2.633,
       "step": 18
     },
     {
       "epoch": 0.41,
       "learning_rate": 0.0002,
-      "loss": 2.407,
+      "loss": 2.4816,
       "step": 20
     },
     {
       "epoch": 0.45,
       "learning_rate": 0.0002,
-      "loss": 2.59,
+      "loss": 2.6263,
       "step": 22
     },
     {
       "epoch": 0.49,
       "learning_rate": 0.0002,
-      "loss": 2.6604,
+      "loss": 2.5695,
       "step": 24
     },
     {
       "epoch": 0.53,
       "learning_rate": 0.0002,
-      "loss": 2.134,
+      "loss": 2.223,
       "step": 26
     },
     {
       "epoch": 0.57,
       "learning_rate": 0.0002,
-      "loss": 2.2908,
+      "loss": 2.261,
       "step": 28
     },
     {
       "epoch": 0.62,
       "learning_rate": 0.0002,
-      "loss": 2.4975,
+      "loss": 2.3568,
       "step": 30
     },
     {
       "epoch": 0.66,
       "learning_rate": 0.0002,
-      "loss": 2.4533,
+      "loss": 2.6185,
       "step": 32
     },
     {
       "epoch": 0.7,
       "learning_rate": 0.0002,
-      "loss": 2.4644,
+      "loss": 2.5005,
       "step": 34
     },
     {
       "epoch": 0.74,
       "learning_rate": 0.0002,
-      "loss": 2.6187,
+      "loss": 2.7505,
       "step": 36
     },
     {
       "epoch": 0.78,
       "learning_rate": 0.0002,
-      "loss": 2.137,
+      "loss": 2.1988,
       "step": 38
     },
     {
       "epoch": 0.82,
       "learning_rate": 0.0002,
-      "loss": 2.368,
+      "loss": 2.1159,
       "step": 40
     },
     {
       "epoch": 0.86,
       "learning_rate": 0.0002,
-      "loss": 2.4951,
+      "loss": 2.4971,
       "step": 42
     },
     {
       "epoch": 0.9,
       "learning_rate": 0.0002,
-      "loss": 2.4786,
+      "loss": 2.5058,
       "step": 44
     },
     {
       "epoch": 0.94,
       "learning_rate": 0.0002,
-      "loss": 2.5544,
+      "loss": 2.5139,
       "step": 46
     },
     {
       "epoch": 0.98,
       "learning_rate": 0.0002,
-      "loss": 2.6641,
+      "loss": 2.4968,
       "step": 48
     }
   ],
   "logging_steps": 2,
-  "max_steps": 48,
+  "max_steps": 144,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
+  "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 2050091535802368.0,
+  "total_flos": 2084704594255872.0,
   "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:c192e600688dd01de21da2985b51206f8f07a168a8b5675a50f80ace12a3a17f
+oid sha256:cad143bc0726c99f5ae973d329c4029448ed469f25c4a6fc7ff427bbece32cca
 size 4728