Upload folder using huggingface_hub

adapter_config.json

@@ -20,9 +20,9 @@
   "revision": null,
   "target_modules": [
     "query_key_value",
-    "dense_4h_to_h",
     "dense",
-    "dense_h_to_4h"
+    "dense_h_to_4h",
+    "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:def4bf80bf800e02179b9887cbcfe611765a18dfd835dfc8332a02edd88f2afd
+oid sha256:80ff0e31b0499ac6ef7b0552b3c8e62b5a8345a9c8a926f944256ed92b1a2a69
 size 134235712

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c82e563048bc7c11c1b1313f30a9179de4fafc980081c6a57a63f364b3e9fa90
+oid sha256:f43f109382d61b6ac04ad329d12a7c53f182d694095e3b0b0f40a627f6087d09
 size 268514874

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2267f321ff44f0478eb689f1b92fd3a803bb3057326a871a1ce82488f0f0d08
+oid sha256:c8d2ae65683150ff2100196a957b8eaab1fc3a90f8235c3ebd2a517c1df44a47
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:824a429c5f95423b97fd2ff7dc1e1dffcd96691286babb37392f00bfcecaeb1b
+oid sha256:b371ae767212827ffe8a91587d7467c4f40f93812413ed6571b08320a4c26332
 size 1064

trainer_state.json

@@ -1,218 +1,164 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9990680335507922,
+  "epoch": 0.9846153846153847,
   "eval_steps": 500,
-  "global_step": 67,
+  "global_step": 48,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.03,
+      "epoch": 0.04,
       "learning_rate": 0.0002,
-      "loss": 2.5917,
+      "loss": 2.2671,
       "step": 2
     },
     {
-      "epoch": 0.06,
+      "epoch": 0.08,
       "learning_rate": 0.0002,
-      "loss": 1.801,
+      "loss": 2.2886,
       "step": 4
     },
     {
-      "epoch": 0.09,
+      "epoch": 0.12,
       "learning_rate": 0.0002,
-      "loss": 1.8031,
+      "loss": 2.6031,
       "step": 6
     },
     {
-      "epoch": 0.12,
+      "epoch": 0.16,
       "learning_rate": 0.0002,
-      "loss": 1.8163,
+      "loss": 2.5322,
       "step": 8
     },
     {
-      "epoch": 0.15,
+      "epoch": 0.21,
       "learning_rate": 0.0002,
-      "loss": 1.5103,
+      "loss": 2.4835,
       "step": 10
     },
     {
-      "epoch": 0.18,
+      "epoch": 0.25,
       "learning_rate": 0.0002,
-      "loss": 1.7491,
+      "loss": 2.7353,
       "step": 12
     },
     {
-      "epoch": 0.21,
+      "epoch": 0.29,
       "learning_rate": 0.0002,
-      "loss": 1.6798,
+      "loss": 2.3234,
       "step": 14
     },
     {
-      "epoch": 0.24,
+      "epoch": 0.33,
       "learning_rate": 0.0002,
-      "loss": 1.4741,
+      "loss": 2.3489,
       "step": 16
     },
     {
-      "epoch": 0.27,
+      "epoch": 0.37,
       "learning_rate": 0.0002,
-      "loss": 2.49,
+      "loss": 2.3782,
       "step": 18
     },
     {
-      "epoch": 0.3,
+      "epoch": 0.41,
       "learning_rate": 0.0002,
-      "loss": 1.8303,
+      "loss": 2.2405,
       "step": 20
     },
     {
-      "epoch": 0.33,
+      "epoch": 0.45,
       "learning_rate": 0.0002,
-      "loss": 1.6824,
+      "loss": 2.5367,
       "step": 22
     },
     {
-      "epoch": 0.36,
+      "epoch": 0.49,
       "learning_rate": 0.0002,
-      "loss": 1.5503,
+      "loss": 2.4794,
       "step": 24
     },
     {
-      "epoch": 0.39,
+      "epoch": 0.53,
       "learning_rate": 0.0002,
-      "loss": 1.3722,
+      "loss": 2.1772,
       "step": 26
     },
     {
-      "epoch": 0.42,
+      "epoch": 0.57,
       "learning_rate": 0.0002,
-      "loss": 1.5678,
+      "loss": 2.4246,
       "step": 28
     },
     {
-      "epoch": 0.45,
+      "epoch": 0.62,
       "learning_rate": 0.0002,
-      "loss": 1.6044,
+      "loss": 2.4532,
       "step": 30
     },
     {
-      "epoch": 0.48,
+      "epoch": 0.66,
       "learning_rate": 0.0002,
-      "loss": 1.4898,
+      "loss": 2.5232,
       "step": 32
     },
     {
-      "epoch": 0.51,
+      "epoch": 0.7,
       "learning_rate": 0.0002,
-      "loss": 2.3578,
+      "loss": 2.3848,
       "step": 34
     },
     {
-      "epoch": 0.54,
+      "epoch": 0.74,
       "learning_rate": 0.0002,
-      "loss": 1.681,
+      "loss": 2.4291,
       "step": 36
     },
     {
-      "epoch": 0.57,
+      "epoch": 0.78,
       "learning_rate": 0.0002,
-      "loss": 1.6899,
+      "loss": 2.1858,
       "step": 38
     },
     {
-      "epoch": 0.6,
+      "epoch": 0.82,
       "learning_rate": 0.0002,
-      "loss": 1.7208,
+      "loss": 2.2289,
       "step": 40
     },
     {
-      "epoch": 0.63,
+      "epoch": 0.86,
       "learning_rate": 0.0002,
-      "loss": 1.4426,
+      "loss": 2.5027,
       "step": 42
     },
     {
-      "epoch": 0.66,
+      "epoch": 0.9,
       "learning_rate": 0.0002,
-      "loss": 1.4401,
+      "loss": 2.4909,
       "step": 44
     },
     {
-      "epoch": 0.69,
+      "epoch": 0.94,
       "learning_rate": 0.0002,
-      "loss": 1.5496,
+      "loss": 2.5565,
       "step": 46
     },
-    {
-      "epoch": 0.72,
-      "learning_rate": 0.0002,
-      "loss": 1.3325,
-      "step": 48
-    },
-    {
-      "epoch": 0.75,
-      "learning_rate": 0.0002,
-      "loss": 2.1736,
-      "step": 50
-    },
-    {
-      "epoch": 0.78,
-      "learning_rate": 0.0002,
-      "loss": 1.7819,
-      "step": 52
-    },
-    {
-      "epoch": 0.81,
-      "learning_rate": 0.0002,
-      "loss": 1.7129,
-      "step": 54
-    },
-    {
-      "epoch": 0.84,
-      "learning_rate": 0.0002,
-      "loss": 1.6788,
-      "step": 56
-    },
-    {
-      "epoch": 0.86,
-      "learning_rate": 0.0002,
-      "loss": 1.5192,
-      "step": 58
-    },
-    {
-      "epoch": 0.89,
-      "learning_rate": 0.0002,
-      "loss": 1.2892,
-      "step": 60
-    },
-    {
-      "epoch": 0.92,
-      "learning_rate": 0.0002,
-      "loss": 1.5028,
-      "step": 62
-    },
-    {
-      "epoch": 0.95,
-      "learning_rate": 0.0002,
-      "loss": 1.1439,
-      "step": 64
-    },
     {
       "epoch": 0.98,
       "learning_rate": 0.0002,
-      "loss": 1.6148,
-      "step": 66
+      "loss": 2.4867,
+      "step": 48
     }
   ],
   "logging_steps": 2,
-  "max_steps": 67,
+  "max_steps": 48,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,
-  "total_flos": 3079120462749696.0,
+  "total_flos": 2077337587531776.0,
   "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 sha256:2297ef3d3b4b6285e02eddcb6c86542c844a3ba7ac6f2da0f6de09ae9d0a5274
+oid sha256:6087b237b5e376147880fe3c0517e7723de9dcebc78ed555271848f2ef07e143
 size 4728