Upload folder using huggingface_hub

adapter_config.json

@@ -20,8 +20,8 @@
   "revision": null,
   "target_modules": [
     "dense_h_to_4h",
-    "dense",
     "query_key_value",
+    "dense",
     "dense_4h_to_h"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60682c0af9f3fd541cd80ee8666eab66077d73f8107e9a7c8be7e909edffe93e
+oid sha256:8029f8b9140d349faed6db3ba280818b21196c252797faa4ace2314124e89fd1
 size 134235712

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04f1c0332a2f1bc5146fc51551ce74af78597f9b37521f92923417ff3d730291
+oid sha256:d1f11e52ccb4cad880edeba12f79ce39271c92a1e6e72fc7b9030d79eece6e51
 size 268514874

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cd0cb197f9704e08105e7ec5866b4b909e204f437e856c73b38b61e70f01ff4
+oid sha256:fe5b91ef98c5d491b8e73e5cecb1c51dfbda003263d44e8fde47c0e41979e336
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b371ae767212827ffe8a91587d7467c4f40f93812413ed6571b08320a4c26332
+oid sha256:81007ec48272bbdc4f9622c046f9c026bf8120ed11d1398fd97bb5168a6f3dda
 size 1064

trainer_state.json

@@ -1,164 +1,320 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9846153846153847,
+  "epoch": 0.9944064636420137,
   "eval_steps": 500,
-  "global_step": 48,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.04,
+      "epoch": 0.02,
       "learning_rate": 0.0002,
-      "loss": 2.1776,
+      "loss": 2.6239,
       "step": 2
     },
     {
-      "epoch": 0.08,
+      "epoch": 0.04,
       "learning_rate": 0.0002,
-      "loss": 2.4224,
+      "loss": 2.5308,
       "step": 4
     },
     {
-      "epoch": 0.12,
+      "epoch": 0.06,
       "learning_rate": 0.0002,
-      "loss": 2.5657,
+      "loss": 2.5426,
       "step": 6
     },
     {
-      "epoch": 0.16,
+      "epoch": 0.08,
       "learning_rate": 0.0002,
-      "loss": 2.5934,
+      "loss": 2.4938,
       "step": 8
     },
     {
-      "epoch": 0.21,
+      "epoch": 0.1,
       "learning_rate": 0.0002,
-      "loss": 2.6175,
+      "loss": 2.3458,
       "step": 10
     },
     {
-      "epoch": 0.25,
+      "epoch": 0.12,
       "learning_rate": 0.0002,
-      "loss": 2.8582,
+      "loss": 2.3949,
       "step": 12
     },
     {
-      "epoch": 0.29,
+      "epoch": 0.14,
       "learning_rate": 0.0002,
-      "loss": 2.2232,
+      "loss": 2.4183,
       "step": 14
     },
     {
-      "epoch": 0.33,
+      "epoch": 0.16,
       "learning_rate": 0.0002,
-      "loss": 2.2464,
+      "loss": 2.3387,
       "step": 16
     },
     {
-      "epoch": 0.37,
+      "epoch": 0.18,
       "learning_rate": 0.0002,
-      "loss": 2.5335,
+      "loss": 2.2117,
       "step": 18
     },
     {
-      "epoch": 0.41,
+      "epoch": 0.2,
       "learning_rate": 0.0002,
-      "loss": 2.6144,
+      "loss": 2.0359,
       "step": 20
     },
     {
-      "epoch": 0.45,
+      "epoch": 0.22,
       "learning_rate": 0.0002,
-      "loss": 2.395,
+      "loss": 2.1539,
       "step": 22
     },
     {
-      "epoch": 0.49,
+      "epoch": 0.24,
       "learning_rate": 0.0002,
-      "loss": 2.8326,
+      "loss": 2.3478,
       "step": 24
     },
     {
-      "epoch": 0.53,
+      "epoch": 0.26,
       "learning_rate": 0.0002,
-      "loss": 2.3137,
+      "loss": 2.1061,
       "step": 26
     },
     {
-      "epoch": 0.57,
+      "epoch": 0.28,
       "learning_rate": 0.0002,
-      "loss": 2.4326,
+      "loss": 2.2001,
       "step": 28
     },
     {
-      "epoch": 0.62,
+      "epoch": 0.3,
       "learning_rate": 0.0002,
-      "loss": 2.5481,
+      "loss": 2.2459,
       "step": 30
     },
     {
-      "epoch": 0.66,
+      "epoch": 0.32,
       "learning_rate": 0.0002,
-      "loss": 2.3901,
+      "loss": 2.2569,
       "step": 32
     },
     {
-      "epoch": 0.7,
+      "epoch": 0.34,
       "learning_rate": 0.0002,
-      "loss": 2.4413,
+      "loss": 2.1687,
       "step": 34
     },
     {
-      "epoch": 0.74,
+      "epoch": 0.36,
       "learning_rate": 0.0002,
-      "loss": 2.6465,
+      "loss": 2.2982,
       "step": 36
     },
     {
-      "epoch": 0.78,
+      "epoch": 0.38,
       "learning_rate": 0.0002,
-      "loss": 2.2408,
+      "loss": 2.3297,
       "step": 38
     },
     {
-      "epoch": 0.82,
+      "epoch": 0.4,
       "learning_rate": 0.0002,
-      "loss": 2.1161,
+      "loss": 2.2531,
       "step": 40
     },
     {
-      "epoch": 0.86,
+      "epoch": 0.42,
       "learning_rate": 0.0002,
-      "loss": 2.4779,
+      "loss": 2.1438,
       "step": 42
     },
     {
-      "epoch": 0.9,
+      "epoch": 0.44,
       "learning_rate": 0.0002,
-      "loss": 2.3948,
+      "loss": 1.8699,
       "step": 44
     },
     {
-      "epoch": 0.94,
+      "epoch": 0.46,
       "learning_rate": 0.0002,
-      "loss": 2.6741,
+      "loss": 2.175,
       "step": 46
     },
     {
-      "epoch": 0.98,
+      "epoch": 0.48,
       "learning_rate": 0.0002,
-      "loss": 2.584,
+      "loss": 2.0656,
       "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0002,
+      "loss": 2.1565,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0002,
+      "loss": 2.2622,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0002,
+      "loss": 2.1934,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002,
+      "loss": 2.3718,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002,
+      "loss": 2.2122,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002,
+      "loss": 2.25,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0002,
+      "loss": 2.2118,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002,
+      "loss": 2.2553,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002,
+      "loss": 2.2255,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002,
+      "loss": 2.1555,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0002,
+      "loss": 1.9828,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0002,
+      "loss": 2.2447,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0002,
+      "loss": 2.0942,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0002,
+      "loss": 2.1352,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0002,
+      "loss": 2.1952,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002,
+      "loss": 2.3201,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0002,
+      "loss": 2.2092,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0002,
+      "loss": 2.2096,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0002,
+      "loss": 2.3016,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0002,
+      "loss": 2.2513,
+      "step": 88
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0002,
+      "loss": 2.0121,
+      "step": 90
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0002,
+      "loss": 2.068,
+      "step": 92
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0002,
+      "loss": 2.0854,
+      "step": 94
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0002,
+      "loss": 1.94,
+      "step": 96
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0002,
+      "loss": 2.1028,
+      "step": 98
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0002,
+      "loss": 1.9648,
+      "step": 100
     }
   ],
   "logging_steps": 2,
-  "max_steps": 48,
+  "max_steps": 100,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,
-  "total_flos": 2045076543504384.0,
+  "total_flos": 8582958605230080.0,
   "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 sha256:9b7c2e8ee1ce9a7a2b3f3bf215f3cac1050303b7acc970ceff11e5960a5a1cce
+oid sha256:c2755afb37343cbed03386874282af112ef741ab9d4e0bd17598360969d9d35f
 size 4728