Upload folder using huggingface_hub

adapter_config.json

@@ -1,6 +1,6 @@
 {
   "auto_mapping": null,
-  "base_model_name_or_path": "stabilityai/stablelm-base-alpha-3b-v2",
+  "base_model_name_or_path": "stabilityai/stablelm-3b-4e1t",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -14,9 +14,13 @@
   "r": 16,
   "revision": null,
   "target_modules": [
-    "qkv_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj",
     "gate_proj",
-    "out_proj"
+    "down_proj",
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c93e9e064e4836d718dd5817a31b8b922c096ac52b39320046ae8414fc3f164c
-size 84504330
+oid sha256:2d2f9e238aa5a49d602e835a5896672d7a3190bfefa9629bb3bba1569670bfe3
+size 100300298

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4e047dcb32ec0ae668d771ec35f3567a0e70b1c03c1a1963e3252fa05b9c9e3
-size 169035898
+oid sha256:90e39b978dcdf99edabb64ecd69bdf0397ca86edf1ff11e8f3608e417a9d55bb
+size 200654930

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d88943110975beabc6932e5d2c3d009f5f9a53729cb06aa62da38ef86bafb19
+oid sha256:ce0d90839c1d2b909c1e5054d9a87b1c188f1ce2eeb0eec32bf435ffe51732a6
 size 14244

trainer_state.json

@@ -11,307 +11,307 @@
     {
       "epoch": 0.06,
       "learning_rate": 3.6363636363636364e-05,
-      "loss": 1.8667,
+      "loss": 1.8122,
       "step": 2
     },
     {
       "epoch": 0.12,
       "learning_rate": 7.272727272727273e-05,
-      "loss": 1.669,
+      "loss": 1.6058,
       "step": 4
     },
     {
       "epoch": 0.18,
       "learning_rate": 0.00010909090909090909,
-      "loss": 1.607,
+      "loss": 1.5108,
       "step": 6
     },
     {
       "epoch": 0.23,
       "learning_rate": 0.00014545454545454546,
-      "loss": 2.0734,
+      "loss": 1.9854,
       "step": 8
     },
     {
       "epoch": 0.29,
       "learning_rate": 0.00018181818181818183,
-      "loss": 1.5327,
+      "loss": 1.4263,
       "step": 10
     },
     {
       "epoch": 0.35,
       "learning_rate": 0.0001978021978021978,
-      "loss": 1.7996,
+      "loss": 1.6944,
       "step": 12
     },
     {
       "epoch": 0.41,
       "learning_rate": 0.00019340659340659342,
-      "loss": 1.6866,
+      "loss": 1.5822,
       "step": 14
     },
     {
       "epoch": 0.47,
       "learning_rate": 0.00018901098901098903,
-      "loss": 1.6299,
+      "loss": 1.5416,
       "step": 16
     },
     {
       "epoch": 0.53,
       "learning_rate": 0.00018461538461538463,
-      "loss": 1.8521,
+      "loss": 1.7547,
       "step": 18
     },
     {
       "epoch": 0.58,
       "learning_rate": 0.00018021978021978024,
-      "loss": 1.7468,
+      "loss": 1.6478,
       "step": 20
     },
     {
       "epoch": 0.64,
       "learning_rate": 0.00017582417582417582,
-      "loss": 1.8712,
+      "loss": 1.7881,
       "step": 22
     },
     {
       "epoch": 0.7,
       "learning_rate": 0.00017142857142857143,
-      "loss": 1.6447,
+      "loss": 1.5457,
       "step": 24
     },
     {
       "epoch": 0.76,
       "learning_rate": 0.00016703296703296706,
-      "loss": 1.7091,
+      "loss": 1.6142,
       "step": 26
     },
     {
       "epoch": 0.82,
       "learning_rate": 0.00016263736263736264,
-      "loss": 1.5068,
+      "loss": 1.4016,
       "step": 28
     },
     {
       "epoch": 0.88,
       "learning_rate": 0.00015824175824175824,
-      "loss": 1.7822,
+      "loss": 1.6815,
       "step": 30
     },
     {
       "epoch": 0.93,
       "learning_rate": 0.00015384615384615385,
-      "loss": 1.7897,
+      "loss": 1.6923,
       "step": 32
     },
     {
       "epoch": 0.99,
       "learning_rate": 0.00014945054945054946,
-      "loss": 1.5594,
+      "loss": 1.4493,
       "step": 34
     },
     {
       "epoch": 1.05,
       "learning_rate": 0.00014505494505494506,
-      "loss": 1.5073,
+      "loss": 1.3942,
       "step": 36
     },
     {
       "epoch": 1.11,
       "learning_rate": 0.00014065934065934067,
-      "loss": 2.0299,
+      "loss": 1.9206,
       "step": 38
     },
     {
       "epoch": 1.17,
       "learning_rate": 0.00013626373626373628,
-      "loss": 1.643,
+      "loss": 1.5305,
       "step": 40
     },
     {
       "epoch": 1.23,
       "learning_rate": 0.00013186813186813188,
-      "loss": 1.5875,
+      "loss": 1.4763,
       "step": 42
     },
     {
       "epoch": 1.28,
       "learning_rate": 0.00012747252747252746,
-      "loss": 1.5646,
+      "loss": 1.452,
       "step": 44
     },
     {
       "epoch": 1.34,
       "learning_rate": 0.0001230769230769231,
-      "loss": 1.4487,
+      "loss": 1.322,
       "step": 46
     },
     {
       "epoch": 1.4,
       "learning_rate": 0.00011868131868131869,
-      "loss": 1.7054,
+      "loss": 1.5994,
       "step": 48
     },
     {
       "epoch": 1.46,
       "learning_rate": 0.00011428571428571428,
-      "loss": 1.5121,
+      "loss": 1.3866,
       "step": 50
     },
     {
       "epoch": 1.52,
       "learning_rate": 0.0001098901098901099,
-      "loss": 1.2679,
+      "loss": 1.1438,
       "step": 52
     },
     {
       "epoch": 1.58,
       "learning_rate": 0.0001054945054945055,
-      "loss": 1.2186,
+      "loss": 1.0993,
       "step": 54
     },
     {
       "epoch": 1.64,
       "learning_rate": 0.0001010989010989011,
-      "loss": 1.7126,
+      "loss": 1.6039,
       "step": 56
     },
     {
       "epoch": 1.69,
       "learning_rate": 9.670329670329671e-05,
-      "loss": 1.4419,
+      "loss": 1.3193,
       "step": 58
     },
     {
       "epoch": 1.75,
       "learning_rate": 9.230769230769232e-05,
-      "loss": 1.4208,
+      "loss": 1.3037,
       "step": 60
     },
     {
       "epoch": 1.81,
       "learning_rate": 8.791208791208791e-05,
-      "loss": 1.5867,
+      "loss": 1.4728,
       "step": 62
     },
     {
       "epoch": 1.87,
       "learning_rate": 8.351648351648353e-05,
-      "loss": 1.4981,
+      "loss": 1.3756,
       "step": 64
     },
     {
       "epoch": 1.93,
       "learning_rate": 7.912087912087912e-05,
-      "loss": 1.5029,
+      "loss": 1.3881,
       "step": 66
     },
     {
       "epoch": 1.99,
       "learning_rate": 7.472527472527473e-05,
-      "loss": 1.2939,
+      "loss": 1.1797,
       "step": 68
     },
     {
       "epoch": 2.04,
       "learning_rate": 7.032967032967034e-05,
-      "loss": 1.6456,
+      "loss": 1.5189,
       "step": 70
     },
     {
       "epoch": 2.1,
       "learning_rate": 6.593406593406594e-05,
-      "loss": 1.5256,
+      "loss": 1.4004,
       "step": 72
     },
     {
       "epoch": 2.16,
       "learning_rate": 6.153846153846155e-05,
-      "loss": 1.2921,
+      "loss": 1.1743,
       "step": 74
     },
     {
       "epoch": 2.22,
       "learning_rate": 5.714285714285714e-05,
-      "loss": 1.292,
+      "loss": 1.1663,
       "step": 76
     },
     {
       "epoch": 2.28,
       "learning_rate": 5.274725274725275e-05,
-      "loss": 1.3151,
+      "loss": 1.1875,
       "step": 78
     },
     {
       "epoch": 2.34,
       "learning_rate": 4.8351648351648355e-05,
-      "loss": 1.8621,
+      "loss": 1.7227,
       "step": 80
     },
     {
       "epoch": 2.39,
       "learning_rate": 4.3956043956043955e-05,
-      "loss": 1.3737,
+      "loss": 1.2398,
       "step": 82
     },
     {
       "epoch": 2.45,
       "learning_rate": 3.956043956043956e-05,
-      "loss": 1.4477,
+      "loss": 1.3196,
       "step": 84
     },
     {
       "epoch": 2.51,
       "learning_rate": 3.516483516483517e-05,
-      "loss": 1.4073,
+      "loss": 1.2791,
       "step": 86
     },
     {
       "epoch": 2.57,
       "learning_rate": 3.0769230769230774e-05,
-      "loss": 1.4966,
+      "loss": 1.3619,
       "step": 88
     },
     {
       "epoch": 2.63,
       "learning_rate": 2.6373626373626374e-05,
-      "loss": 1.1487,
+      "loss": 1.0073,
       "step": 90
     },
     {
       "epoch": 2.69,
       "learning_rate": 2.1978021978021977e-05,
-      "loss": 1.3299,
+      "loss": 1.1867,
       "step": 92
     },
     {
       "epoch": 2.74,
       "learning_rate": 1.7582417582417584e-05,
-      "loss": 1.7217,
+      "loss": 1.605,
       "step": 94
     },
     {
       "epoch": 2.8,
       "learning_rate": 1.3186813186813187e-05,
-      "loss": 1.2555,
+      "loss": 1.1101,
       "step": 96
     },
     {
       "epoch": 2.86,
       "learning_rate": 8.791208791208792e-06,
-      "loss": 1.3967,
+      "loss": 1.2586,
       "step": 98
     },
     {
       "epoch": 2.92,
       "learning_rate": 4.395604395604396e-06,
-      "loss": 1.5847,
+      "loss": 1.4676,
       "step": 100
     },
     {
       "epoch": 2.98,
       "learning_rate": 0.0,
-      "loss": 1.6002,
+      "loss": 1.4705,
       "step": 102
     }
   ],
@@ -319,7 +319,7 @@
   "max_steps": 102,
   "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 2.6947930854260736e+16,
+  "total_flos": 2.6989001479028736e+16,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26d1905ca3abf82ab3bf45211ffccc2ef759d09640a7293e39e0c1a0ddd98eb0
+oid sha256:e35e5509b7c25ac17c40a1eee45fbfbb580135d1a9777e8e43b88eb21c75dbea
 size 4472