Upload folder using huggingface_hub

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8551ab343ef5e8756f53d7454de355fbf4b3367bec32cd436fb2109f4cb2b96
+oid sha256:22752e35bdb61ee34953f8b703375848a3db2c155e7dbaa37b2c8ab59f4feabf
 size 134235712

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0761fd66f7e9f27517b9cdc385248f873232decf6233d679c16ce939ed446c6d
+oid sha256:ecd2190146ef39a84faeb3192ab6640ab2ffd6eee4f47a114b870fcbbe44c726
 size 268514874

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a273e635a3dbe6f12de8531b896d85c09b670ee924a5c5d5c034c9f1e364651e
+oid sha256:c398e459ddc0d0eea0a5e40d93d15d770f725d809e498a814b2045f61b54f82f
 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": 2.2836,
+      "loss": 2.9084,
       "step": 2
     },
     {
-      "epoch": 0.08,
+      "epoch": 0.04,
       "learning_rate": 0.0002,
-      "loss": 2.4552,
+      "loss": 2.7567,
       "step": 4
     },
     {
-      "epoch": 0.12,
+      "epoch": 0.06,
       "learning_rate": 0.0002,
-      "loss": 2.7222,
+      "loss": 2.4718,
       "step": 6
     },
     {
-      "epoch": 0.16,
+      "epoch": 0.08,
       "learning_rate": 0.0002,
-      "loss": 2.6656,
+      "loss": 2.5822,
       "step": 8
     },
     {
-      "epoch": 0.21,
+      "epoch": 0.1,
       "learning_rate": 0.0002,
-      "loss": 2.6016,
+      "loss": 2.5266,
       "step": 10
     },
     {
-      "epoch": 0.25,
+      "epoch": 0.12,
       "learning_rate": 0.0002,
-      "loss": 3.1001,
+      "loss": 2.4351,
       "step": 12
     },
     {
-      "epoch": 0.29,
+      "epoch": 0.14,
       "learning_rate": 0.0002,
-      "loss": 2.2399,
+      "loss": 2.3991,
       "step": 14
     },
     {
-      "epoch": 0.33,
+      "epoch": 0.16,
       "learning_rate": 0.0002,
-      "loss": 2.3808,
+      "loss": 2.4939,
       "step": 16
     },
     {
-      "epoch": 0.37,
+      "epoch": 0.18,
       "learning_rate": 0.0002,
-      "loss": 2.412,
+      "loss": 2.3929,
       "step": 18
     },
     {
-      "epoch": 0.41,
+      "epoch": 0.2,
       "learning_rate": 0.0002,
-      "loss": 2.5426,
+      "loss": 2.2716,
       "step": 20
     },
     {
-      "epoch": 0.45,
+      "epoch": 0.22,
       "learning_rate": 0.0002,
-      "loss": 2.7169,
+      "loss": 2.385,
       "step": 22
     },
     {
-      "epoch": 0.49,
+      "epoch": 0.24,
       "learning_rate": 0.0002,
-      "loss": 2.9043,
+      "loss": 2.502,
       "step": 24
     },
     {
-      "epoch": 0.53,
+      "epoch": 0.26,
       "learning_rate": 0.0002,
-      "loss": 2.1974,
+      "loss": 2.22,
       "step": 26
     },
     {
-      "epoch": 0.57,
+      "epoch": 0.28,
       "learning_rate": 0.0002,
-      "loss": 2.4357,
+      "loss": 2.2473,
       "step": 28
     },
     {
-      "epoch": 0.62,
+      "epoch": 0.3,
       "learning_rate": 0.0002,
-      "loss": 2.6253,
+      "loss": 2.3497,
       "step": 30
     },
     {
-      "epoch": 0.66,
+      "epoch": 0.32,
       "learning_rate": 0.0002,
-      "loss": 2.7215,
+      "loss": 2.2763,
       "step": 32
     },
     {
-      "epoch": 0.7,
+      "epoch": 0.34,
       "learning_rate": 0.0002,
-      "loss": 2.5237,
+      "loss": 2.3384,
       "step": 34
     },
     {
-      "epoch": 0.74,
+      "epoch": 0.36,
       "learning_rate": 0.0002,
-      "loss": 3.1991,
+      "loss": 2.2627,
       "step": 36
     },
     {
-      "epoch": 0.78,
+      "epoch": 0.38,
       "learning_rate": 0.0002,
-      "loss": 2.4282,
+      "loss": 2.3317,
       "step": 38
     },
     {
-      "epoch": 0.82,
+      "epoch": 0.4,
       "learning_rate": 0.0002,
-      "loss": 2.2196,
+      "loss": 2.4054,
       "step": 40
     },
     {
-      "epoch": 0.86,
+      "epoch": 0.42,
       "learning_rate": 0.0002,
-      "loss": 2.6197,
+      "loss": 2.1966,
       "step": 42
     },
     {
-      "epoch": 0.9,
+      "epoch": 0.44,
       "learning_rate": 0.0002,
-      "loss": 2.4451,
+      "loss": 2.2012,
       "step": 44
     },
     {
-      "epoch": 0.94,
+      "epoch": 0.46,
       "learning_rate": 0.0002,
-      "loss": 2.5496,
+      "loss": 2.2417,
       "step": 46
     },
     {
-      "epoch": 0.98,
+      "epoch": 0.48,
       "learning_rate": 0.0002,
-      "loss": 2.8388,
+      "loss": 2.1286,
       "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0002,
+      "loss": 2.3857,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0002,
+      "loss": 2.4254,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0002,
+      "loss": 2.3185,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002,
+      "loss": 2.2981,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002,
+      "loss": 2.3821,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002,
+      "loss": 2.2838,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0002,
+      "loss": 2.3335,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002,
+      "loss": 2.274,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002,
+      "loss": 2.2696,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002,
+      "loss": 2.0829,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0002,
+      "loss": 2.0368,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0002,
+      "loss": 2.1695,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0002,
+      "loss": 2.116,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0002,
+      "loss": 2.1157,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0002,
+      "loss": 2.3132,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002,
+      "loss": 2.2322,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0002,
+      "loss": 2.2643,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0002,
+      "loss": 2.2758,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0002,
+      "loss": 2.2514,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0002,
+      "loss": 2.3033,
+      "step": 88
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0002,
+      "loss": 2.2307,
+      "step": 90
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0002,
+      "loss": 2.2363,
+      "step": 92
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0002,
+      "loss": 2.0307,
+      "step": 94
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0002,
+      "loss": 1.963,
+      "step": 96
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0002,
+      "loss": 2.0864,
+      "step": 98
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0002,
+      "loss": 2.1501,
+      "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": 2046020741603328.0,
+  "total_flos": 8558618648248320.0,
   "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 sha256:05d4bf44e2f3fa9eef10818d2ac256b26d0eae9c331d6b54985e765c04f7baf9
+oid sha256:61365ab9c9c37bb856874a9e6eb2b021ea0ea3c990d6e7063744ff4ba2d7b882
 size 4728