Upload folder using huggingface_hub

tiny-aya-base/condition-2-ur-5k-seed123/adapter_config.json

@@ -33,12 +33,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
     "q_proj",
-    "up_proj",
-    "o_proj",
     "down_proj",
+    "v_proj",
     "gate_proj",
+    "up_proj",
+    "o_proj",
     "k_proj"
   ],
   "target_parameters": null,

tiny-aya-base/condition-2-ur-5k-seed123/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e87ef8e9396c4c5be1112ee09bb23cf0830fbe7649a8c7dfce82873c16d2698e
+oid sha256:3e2313b965fea6b718ae98e0358bec285b380a275092f6aa4695ee64bf3c2b9b
 size 120981200

tiny-aya-base/condition-2-ur-5k-seed123/training_metrics.json

@@ -4,43 +4,218 @@
   "seed": 123,
   "output_name": "condition-2-ur-5k-seed123",
   "train_result": {
-    "train_runtime": 454.0773,
-    "train_samples_per_second": 1.101,
-    "train_steps_per_second": 0.07,
-    "total_flos": 8941999906357248.0,
-    "train_loss": 1.3207926899194717,
+    "train_runtime": 3230.5067,
+    "train_samples_per_second": 1.393,
+    "train_steps_per_second": 0.087,
+    "total_flos": 7.877067449512755e+16,
+    "train_loss": 1.1113017433924033,
     "epoch": 1.0
   },
   "log_history": [
     {
-      "loss": 1.4818,
-      "grad_norm": 0.2078016996383667,
-      "learning_rate": 0.00017431448254773944,
-      "epoch": 0.3125,
+      "loss": 1.561,
+      "grad_norm": 0.20376847684383392,
+      "learning_rate": 0.00012,
+      "epoch": 0.03546099290780142,
       "step": 10
     },
     {
-      "loss": 1.3182,
-      "grad_norm": 0.18385834991931915,
-      "learning_rate": 7.920883091822408e-05,
-      "epoch": 0.625,
+      "loss": 1.3216,
+      "grad_norm": 0.2216212898492813,
+      "learning_rate": 0.00019988926445681492,
+      "epoch": 0.07092198581560284,
       "step": 20
     },
     {
-      "loss": 1.2291,
-      "grad_norm": 0.14557600021362305,
-      "learning_rate": 4.8943483704846475e-06,
-      "epoch": 0.9375,
+      "loss": 1.2372,
+      "grad_norm": 0.17481839656829834,
+      "learning_rate": 0.0001986463043917528,
+      "epoch": 0.10638297872340426,
       "step": 30
     },
     {
-      "train_runtime": 454.0773,
-      "train_samples_per_second": 1.101,
-      "train_steps_per_second": 0.07,
-      "total_flos": 8941999906357248.0,
-      "train_loss": 1.3207926899194717,
+      "loss": 1.1621,
+      "grad_norm": 0.19017969071865082,
+      "learning_rate": 0.00019603921063437793,
+      "epoch": 0.14184397163120568,
+      "step": 40
+    },
+    {
+      "loss": 1.1319,
+      "grad_norm": 0.17506349086761475,
+      "learning_rate": 0.0001921040354671897,
+      "epoch": 0.1773049645390071,
+      "step": 50
+    },
+    {
+      "loss": 1.1641,
+      "grad_norm": 0.21809640526771545,
+      "learning_rate": 0.00018689519659051467,
+      "epoch": 0.2127659574468085,
+      "step": 60
+    },
+    {
+      "loss": 1.0792,
+      "grad_norm": 0.18679380416870117,
+      "learning_rate": 0.00018048472460553257,
+      "epoch": 0.24822695035460993,
+      "step": 70
+    },
+    {
+      "loss": 1.101,
+      "grad_norm": 0.16744385659694672,
+      "learning_rate": 0.00017296126693671884,
+      "epoch": 0.28368794326241137,
+      "step": 80
+    },
+    {
+      "loss": 1.0698,
+      "grad_norm": 0.19381901621818542,
+      "learning_rate": 0.00016442886196799464,
+      "epoch": 0.3191489361702128,
+      "step": 90
+    },
+    {
+      "loss": 1.089,
+      "grad_norm": 0.19763484597206116,
+      "learning_rate": 0.00015500550034448413,
+      "epoch": 0.3546099290780142,
+      "step": 100
+    },
+    {
+      "loss": 1.0707,
+      "grad_norm": 0.17650987207889557,
+      "learning_rate": 0.00014482149333496454,
+      "epoch": 0.3900709219858156,
+      "step": 110
+    },
+    {
+      "loss": 1.0932,
+      "grad_norm": 0.17287975549697876,
+      "learning_rate": 0.0001340176708181637,
+      "epoch": 0.425531914893617,
+      "step": 120
+    },
+    {
+      "loss": 1.0657,
+      "grad_norm": 0.1593146175146103,
+      "learning_rate": 0.00012274343381211066,
+      "epoch": 0.46099290780141844,
+      "step": 130
+    },
+    {
+      "loss": 1.0675,
+      "grad_norm": 0.15996894240379333,
+      "learning_rate": 0.00011115468847720245,
+      "epoch": 0.49645390070921985,
+      "step": 140
+    },
+    {
+      "loss": 1.0388,
+      "grad_norm": 0.1584158092737198,
+      "learning_rate": 9.941169016269379e-05,
+      "epoch": 0.5319148936170213,
+      "step": 150
+    },
+    {
+      "loss": 1.0679,
+      "grad_norm": 0.19191399216651917,
+      "learning_rate": 8.767682731028415e-05,
+      "epoch": 0.5673758865248227,
+      "step": 160
+    },
+    {
+      "loss": 1.057,
+      "grad_norm": 0.17048010230064392,
+      "learning_rate": 7.611237586016557e-05,
+      "epoch": 0.6028368794326241,
+      "step": 170
+    },
+    {
+      "loss": 1.0826,
+      "grad_norm": 0.14610987901687622,
+      "learning_rate": 6.487825521280109e-05,
+      "epoch": 0.6382978723404256,
+      "step": 180
+    },
+    {
+      "loss": 1.0695,
+      "grad_norm": 0.13922062516212463,
+      "learning_rate": 5.4129816778190936e-05,
+      "epoch": 0.6737588652482269,
+      "step": 190
+    },
+    {
+      "loss": 0.993,
+      "grad_norm": 0.15719996392726898,
+      "learning_rate": 4.401569569374668e-05,
+      "epoch": 0.7092198581560284,
+      "step": 200
+    },
+    {
+      "loss": 1.0792,
+      "grad_norm": 0.19373147189617157,
+      "learning_rate": 3.467575541836305e-05,
+      "epoch": 0.7446808510638298,
+      "step": 210
+    },
+    {
+      "loss": 1.0739,
+      "grad_norm": 0.12987244129180908,
+      "learning_rate": 2.6239153625937784e-05,
+      "epoch": 0.7801418439716312,
+      "step": 220
+    },
+    {
+      "loss": 1.0962,
+      "grad_norm": 0.18130353093147278,
+      "learning_rate": 1.882255614419376e-05,
+      "epoch": 0.8156028368794326,
+      "step": 230
+    },
+    {
+      "loss": 1.064,
+      "grad_norm": 0.14319118857383728,
+      "learning_rate": 1.2528523637410838e-05,
+      "epoch": 0.851063829787234,
+      "step": 240
+    },
+    {
+      "loss": 1.1012,
+      "grad_norm": 0.17808066308498383,
+      "learning_rate": 7.4440933428779e-06,
+      "epoch": 0.8865248226950354,
+      "step": 250
+    },
+    {
+      "loss": 1.0573,
+      "grad_norm": 0.18549706041812897,
+      "learning_rate": 3.6395754735699894e-06,
+      "epoch": 0.9219858156028369,
+      "step": 260
+    },
+    {
+      "loss": 1.0612,
+      "grad_norm": 0.1419883370399475,
+      "learning_rate": 1.1675809310361497e-06,
+      "epoch": 0.9574468085106383,
+      "step": 270
+    },
+    {
+      "loss": 1.0421,
+      "grad_norm": 0.1958923488855362,
+      "learning_rate": 6.229377380218005e-08,
+      "epoch": 0.9929078014184397,
+      "step": 280
+    },
+    {
+      "train_runtime": 3230.5067,
+      "train_samples_per_second": 1.393,
+      "train_steps_per_second": 0.087,
+      "total_flos": 7.877067449512755e+16,
+      "train_loss": 1.1113017433924033,
       "epoch": 1.0,
-      "step": 32
+      "step": 282
     }
   ]
 }