Upload folder using huggingface_hub

adapter_config.json

@@ -12,14 +12,14 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 64,
+  "lora_alpha": 32,
   "lora_bias": false,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af620e3460c9a12310e5913dae8c6346d6cc62987891e6f33169a3d7a2ca51d8
-size 239536272
+oid sha256:6ba8e8c80803d2a11a70df9d4dacb77457eed010f3898a3e490266b2b1d0f304
+size 119801528

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7a957c9bc520a79279d849473378928e78b29011f2356d2c0e6b3407f5b6ff0
-size 479363147
+oid sha256:e175f62ebf7fe247327e70639ff1cd0a6113e616d2b57e42eb7b074ff5565e78
+size 239893323

trainer_state.json

@@ -11,198 +11,198 @@
   "log_history": [
     {
       "epoch": 0.12121212121212122,
-      "grad_norm": 2.5308644771575928,
+      "grad_norm": 1.8328726291656494,
       "learning_rate": 0.0,
       "loss": 2.5573,
       "step": 1
     },
     {
       "epoch": 0.24242424242424243,
-      "grad_norm": 2.872847557067871,
+      "grad_norm": 2.0915732383728027,
       "learning_rate": 3.3333333333333335e-05,
       "loss": 2.1189,
       "step": 2
     },
     {
       "epoch": 0.36363636363636365,
-      "grad_norm": 1.4297473430633545,
+      "grad_norm": 1.0810253620147705,
       "learning_rate": 6.666666666666667e-05,
-      "loss": 1.7812,
+      "loss": 1.7979,
       "step": 3
     },
     {
       "epoch": 0.48484848484848486,
-      "grad_norm": 1.3863275051116943,
+      "grad_norm": 1.1273187398910522,
       "learning_rate": 0.0001,
-      "loss": 2.0268,
+      "loss": 2.0746,
       "step": 4
     },
     {
       "epoch": 0.6060606060606061,
-      "grad_norm": 1.301163911819458,
+      "grad_norm": 1.1481099128723145,
       "learning_rate": 0.00013333333333333334,
-      "loss": 1.8453,
+      "loss": 1.9376,
       "step": 5
     },
     {
       "epoch": 0.7272727272727273,
-      "grad_norm": 1.2446081638336182,
+      "grad_norm": 1.120679259300232,
       "learning_rate": 0.00016666666666666666,
-      "loss": 1.8696,
+      "loss": 1.9616,
       "step": 6
     },
     {
       "epoch": 0.8484848484848485,
-      "grad_norm": 0.5551737546920776,
+      "grad_norm": 0.42956575751304626,
       "learning_rate": 0.0002,
-      "loss": 1.5345,
+      "loss": 1.5583,
       "step": 7
     },
     {
       "epoch": 0.9696969696969697,
-      "grad_norm": 0.662405252456665,
+      "grad_norm": 0.5541684031486511,
       "learning_rate": 0.00023333333333333333,
-      "loss": 1.6014,
+      "loss": 1.6371,
       "step": 8
     },
     {
       "epoch": 1.0,
-      "grad_norm": 1.045662760734558,
+      "grad_norm": 0.8354697823524475,
       "learning_rate": 0.0002666666666666667,
-      "loss": 1.9489,
+      "loss": 1.9758,
       "step": 9
     },
     {
       "epoch": 1.121212121212121,
-      "grad_norm": 2.387998342514038,
+      "grad_norm": 0.8120695352554321,
       "learning_rate": 0.0003,
-      "loss": 1.7234,
+      "loss": 1.8198,
       "step": 10
     },
     {
       "epoch": 1.2424242424242424,
-      "grad_norm": 0.8213406801223755,
+      "grad_norm": 0.595156729221344,
       "learning_rate": 0.0003333333333333333,
-      "loss": 1.5385,
+      "loss": 1.649,
       "step": 11
     },
     {
       "epoch": 1.3636363636363638,
-      "grad_norm": 0.8873594999313354,
+      "grad_norm": 0.4005779027938843,
       "learning_rate": 0.00036666666666666667,
-      "loss": 1.2518,
+      "loss": 1.3083,
       "step": 12
     },
     {
       "epoch": 1.4848484848484849,
-      "grad_norm": 7.101565361022949,
+      "grad_norm": 0.8254678845405579,
       "learning_rate": 0.0004,
-      "loss": 1.219,
+      "loss": 1.2479,
       "step": 13
     },
     {
       "epoch": 1.606060606060606,
-      "grad_norm": 2.5379955768585205,
+      "grad_norm": 0.582369863986969,
       "learning_rate": 0.00043333333333333337,
-      "loss": 1.3358,
+      "loss": 1.4063,
       "step": 14
     },
     {
       "epoch": 1.7272727272727273,
-      "grad_norm": 7.031259536743164,
+      "grad_norm": 0.7945718765258789,
       "learning_rate": 0.00046666666666666666,
-      "loss": 1.4813,
+      "loss": 1.4941,
       "step": 15
     },
     {
       "epoch": 1.8484848484848486,
-      "grad_norm": 2.496732711791992,
+      "grad_norm": 0.7387524843215942,
       "learning_rate": 0.0005,
-      "loss": 1.2563,
+      "loss": 1.3542,
       "step": 16
     },
     {
       "epoch": 1.9696969696969697,
-      "grad_norm": 1.208024263381958,
+      "grad_norm": 0.6516833305358887,
       "learning_rate": 0.0004986304738420684,
-      "loss": 1.7684,
+      "loss": 1.8561,
       "step": 17
     },
     {
       "epoch": 2.0,
-      "grad_norm": 2.3959779739379883,
+      "grad_norm": 2.1795907020568848,
       "learning_rate": 0.0004945369001834514,
-      "loss": 1.0189,
+      "loss": 1.1684,
       "step": 18
     },
     {
       "epoch": 2.121212121212121,
-      "grad_norm": 1.176888346672058,
+      "grad_norm": 2.144760847091675,
       "learning_rate": 0.0004877641290737884,
-      "loss": 1.196,
+      "loss": 1.3242,
       "step": 19
     },
     {
       "epoch": 2.242424242424242,
-      "grad_norm": 2.4621543884277344,
+      "grad_norm": 1.0639714002609253,
       "learning_rate": 0.0004783863644106502,
-      "loss": 0.9208,
+      "loss": 1.116,
       "step": 20
     },
     {
       "epoch": 2.3636363636363638,
-      "grad_norm": 2.5817689895629883,
+      "grad_norm": 2.3435370922088623,
       "learning_rate": 0.00046650635094610973,
-      "loss": 1.2624,
+      "loss": 1.4533,
       "step": 21
     },
     {
       "epoch": 2.484848484848485,
-      "grad_norm": 1.394972324371338,
+      "grad_norm": 0.9590378999710083,
       "learning_rate": 0.0004522542485937369,
-      "loss": 1.0047,
+      "loss": 1.0565,
       "step": 22
     },
     {
       "epoch": 2.606060606060606,
-      "grad_norm": 0.9446749091148376,
+      "grad_norm": 0.8274413347244263,
       "learning_rate": 0.00043578620636934855,
-      "loss": 0.8517,
+      "loss": 1.0777,
       "step": 23
     },
     {
       "epoch": 2.7272727272727275,
-      "grad_norm": 1.0814933776855469,
+      "grad_norm": 0.7866584062576294,
       "learning_rate": 0.0004172826515897146,
-      "loss": 0.8246,
+      "loss": 0.9818,
       "step": 24
     },
     {
       "epoch": 2.8484848484848486,
-      "grad_norm": 1.8725590705871582,
+      "grad_norm": 1.3257405757904053,
       "learning_rate": 0.0003969463130731183,
-      "loss": 0.9131,
+      "loss": 0.9458,
       "step": 25
     },
     {
       "epoch": 2.9696969696969697,
-      "grad_norm": 1.1195790767669678,
+      "grad_norm": 0.7941730618476868,
       "learning_rate": 0.000375,
-      "loss": 0.6881,
+      "loss": 0.8782,
       "step": 26
     },
     {
       "epoch": 3.0,
-      "grad_norm": 1.709831953048706,
+      "grad_norm": 1.2293105125427246,
       "learning_rate": 0.0003516841607689501,
-      "loss": 0.9601,
+      "loss": 0.9678,
       "step": 27
     },
     {
       "epoch": 3.121212121212121,
-      "grad_norm": 0.9859489798545837,
+      "grad_norm": 0.9322613477706909,
       "learning_rate": 0.00032725424859373687,
-      "loss": 0.425,
+      "loss": 0.5318,
       "step": 28
     }
   ],
@@ -223,7 +223,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1434067506413568.0,
+  "total_flos": 1418923874893824.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d218cb1147c6cb300dc7d91e574075fd0a3ba2cbb8375f70368500238df0d4cc
+oid sha256:6c740dd598c601f59387c76e234e8e490cd7c6f982d6844d5212ef0c066e5f45
 size 6033