Upload folder using huggingface_hub

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3ba49f73a389971e386b4f6a21d7d4552dbea70aed7d8edffa40c1e9dc9fa7d
+oid sha256:249bf4be205dd2652c9d937e1a83f98e812c06fb681cd4b41b07c4dc3deeb8cf
 size 121915776

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:699481cdb4057dad1811072a3784c5c230ed68cc7b5dd2db650491588235f3f7
+oid sha256:3a03758fe15563c285b5fa37f0d42fae16f0830f42ab8c4338a12440593139e8
 size 243883194

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:242671a394d6ab31de2cba9a24ffa0e05edcd8ff2eccd478f7b1d3b9cfdac40f
+oid sha256:1e19a7c720ea8fd4e0186a55d33f9b6127ae50d335e0963842995e747c4de6e2
 size 14244

trainer_state.json

@@ -11,601 +11,601 @@
     {
       "epoch": 0.03,
       "learning_rate": 5.7142857142857145e-06,
-      "loss": 2.5851,
+      "loss": 2.5972,
       "step": 2
     },
     {
       "epoch": 0.06,
       "learning_rate": 1.1428571428571429e-05,
-      "loss": 1.606,
+      "loss": 1.6213,
       "step": 4
     },
     {
       "epoch": 0.09,
       "learning_rate": 1.7142857142857142e-05,
-      "loss": 1.6376,
+      "loss": 1.6595,
       "step": 6
     },
     {
       "epoch": 0.12,
       "learning_rate": 1.9998688836656322e-05,
-      "loss": 1.5397,
+      "loss": 1.5668,
       "step": 8
     },
     {
       "epoch": 0.15,
       "learning_rate": 1.998820159279591e-05,
-      "loss": 1.2479,
+      "loss": 1.2901,
       "step": 10
     },
     {
       "epoch": 0.18,
       "learning_rate": 1.9967238104745695e-05,
-      "loss": 1.5462,
+      "loss": 1.6238,
       "step": 12
     },
     {
       "epoch": 0.21,
       "learning_rate": 1.993582036030978e-05,
-      "loss": 1.9254,
+      "loss": 2.0448,
       "step": 14
     },
     {
       "epoch": 0.24,
       "learning_rate": 1.9893981312363563e-05,
-      "loss": 2.377,
+      "loss": 2.5822,
       "step": 16
     },
     {
       "epoch": 0.27,
       "learning_rate": 1.9841764844290744e-05,
-      "loss": 2.0347,
+      "loss": 2.0548,
       "step": 18
     },
     {
       "epoch": 0.3,
       "learning_rate": 1.977922572395571e-05,
-      "loss": 1.5208,
+      "loss": 1.5504,
       "step": 20
     },
     {
       "epoch": 0.33,
       "learning_rate": 1.9706429546259592e-05,
-      "loss": 1.4954,
+      "loss": 1.534,
       "step": 22
     },
     {
       "epoch": 0.36,
       "learning_rate": 1.9623452664340305e-05,
-      "loss": 1.4711,
+      "loss": 1.4985,
       "step": 24
     },
     {
       "epoch": 0.39,
       "learning_rate": 1.953038210948861e-05,
-      "loss": 1.4482,
+      "loss": 1.4896,
       "step": 26
     },
     {
       "epoch": 0.42,
       "learning_rate": 1.9427315499864345e-05,
-      "loss": 1.6474,
+      "loss": 1.7378,
       "step": 28
     },
     {
       "epoch": 0.45,
       "learning_rate": 1.9314360938108427e-05,
-      "loss": 1.9729,
+      "loss": 2.0865,
       "step": 30
     },
     {
       "epoch": 0.48,
       "learning_rate": 1.9191636897958123e-05,
-      "loss": 2.0591,
+      "loss": 2.2693,
       "step": 32
     },
     {
       "epoch": 0.51,
       "learning_rate": 1.905927209998447e-05,
-      "loss": 2.4572,
+      "loss": 2.4775,
       "step": 34
     },
     {
       "epoch": 0.54,
       "learning_rate": 1.8917405376582144e-05,
-      "loss": 1.8854,
+      "loss": 1.907,
       "step": 36
     },
     {
       "epoch": 0.57,
       "learning_rate": 1.876618552635348e-05,
-      "loss": 1.5307,
+      "loss": 1.5578,
       "step": 38
     },
     {
       "epoch": 0.6,
       "learning_rate": 1.8605771158039253e-05,
-      "loss": 1.4091,
+      "loss": 1.4374,
       "step": 40
     },
     {
       "epoch": 0.63,
       "learning_rate": 1.8436330524160048e-05,
-      "loss": 1.2489,
+      "loss": 1.2885,
       "step": 42
     },
     {
       "epoch": 0.66,
       "learning_rate": 1.8258041344542567e-05,
-      "loss": 1.4895,
+      "loss": 1.5687,
       "step": 44
     },
     {
       "epoch": 0.69,
       "learning_rate": 1.8071090619916095e-05,
-      "loss": 1.7542,
+      "loss": 1.819,
       "step": 46
     },
     {
       "epoch": 0.72,
       "learning_rate": 1.7875674435774546e-05,
-      "loss": 1.6872,
+      "loss": 1.9352,
       "step": 48
     },
     {
       "epoch": 0.75,
       "learning_rate": 1.767199775670986e-05,
-      "loss": 2.7505,
+      "loss": 2.7611,
       "step": 50
     },
     {
       "epoch": 0.78,
       "learning_rate": 1.7460274211432463e-05,
-      "loss": 1.5695,
+      "loss": 1.5858,
       "step": 52
     },
     {
       "epoch": 0.81,
       "learning_rate": 1.7240725868704218e-05,
-      "loss": 1.3149,
+      "loss": 1.3336,
       "step": 54
     },
     {
       "epoch": 0.84,
       "learning_rate": 1.7013583004418994e-05,
-      "loss": 1.5899,
+      "loss": 1.5745,
       "step": 56
     },
     {
       "epoch": 0.86,
       "learning_rate": 1.6779083860075032e-05,
-      "loss": 1.39,
+      "loss": 1.4328,
       "step": 58
     },
     {
       "epoch": 0.89,
       "learning_rate": 1.6537474392892527e-05,
-      "loss": 1.2605,
+      "loss": 1.2795,
       "step": 60
     },
     {
       "epoch": 0.92,
       "learning_rate": 1.6289008017838447e-05,
-      "loss": 1.4089,
+      "loss": 1.4316,
       "step": 62
     },
     {
       "epoch": 0.95,
       "learning_rate": 1.603394534182925e-05,
-      "loss": 1.7018,
+      "loss": 1.7587,
       "step": 64
     },
     {
       "epoch": 0.98,
       "learning_rate": 1.5772553890390196e-05,
-      "loss": 1.3784,
+      "loss": 1.3836,
       "step": 66
     },
     {
       "epoch": 1.01,
       "learning_rate": 1.5505107827058038e-05,
-      "loss": 2.1283,
+      "loss": 2.1514,
       "step": 68
     },
     {
       "epoch": 1.04,
       "learning_rate": 1.52318876658213e-05,
-      "loss": 1.7516,
+      "loss": 1.7494,
       "step": 70
     },
     {
       "epoch": 1.07,
       "learning_rate": 1.4953179976899878e-05,
-      "loss": 1.3695,
+      "loss": 1.3705,
       "step": 72
     },
     {
       "epoch": 1.1,
       "learning_rate": 1.4669277086172406e-05,
-      "loss": 1.5351,
+      "loss": 1.5337,
       "step": 74
     },
     {
       "epoch": 1.13,
       "learning_rate": 1.4380476768566825e-05,
-      "loss": 1.212,
+      "loss": 1.206,
       "step": 76
     },
     {
       "epoch": 1.16,
       "learning_rate": 1.4087081935735565e-05,
-      "loss": 1.2777,
+      "loss": 1.2772,
       "step": 78
     },
     {
       "epoch": 1.19,
       "learning_rate": 1.378940031834307e-05,
-      "loss": 1.4289,
+      "loss": 1.4074,
       "step": 80
     },
     {
       "epoch": 1.22,
       "learning_rate": 1.3487744143298822e-05,
-      "loss": 1.6633,
+      "loss": 1.6871,
       "step": 82
     },
     {
       "epoch": 1.25,
       "learning_rate": 1.3182429806274442e-05,
-      "loss": 1.9543,
+      "loss": 2.1145,
       "step": 84
     },
     {
       "epoch": 1.28,
       "learning_rate": 1.2873777539848284e-05,
-      "loss": 1.7349,
+      "loss": 1.6078,
       "step": 86
     },
     {
       "epoch": 1.31,
       "learning_rate": 1.2562111077625723e-05,
-      "loss": 1.5843,
+      "loss": 1.5886,
       "step": 88
     },
     {
       "epoch": 1.34,
       "learning_rate": 1.2247757314687296e-05,
-      "loss": 1.469,
+      "loss": 1.4686,
       "step": 90
     },
     {
       "epoch": 1.37,
       "learning_rate": 1.1931045964720882e-05,
-      "loss": 1.3608,
+      "loss": 1.3602,
       "step": 92
     },
     {
       "epoch": 1.4,
       "learning_rate": 1.1612309214197599e-05,
-      "loss": 1.1707,
+      "loss": 1.2071,
       "step": 94
     },
     {
       "epoch": 1.43,
       "learning_rate": 1.1291881373954066e-05,
-      "loss": 1.4295,
+      "loss": 1.3785,
       "step": 96
     },
     {
       "epoch": 1.46,
       "learning_rate": 1.0970098528546482e-05,
-      "loss": 1.5818,
+      "loss": 1.5731,
       "step": 98
     },
     {
       "epoch": 1.49,
       "learning_rate": 1.0647298183744359e-05,
-      "loss": 1.6487,
+      "loss": 1.6729,
       "step": 100
     },
     {
       "epoch": 1.52,
       "learning_rate": 1.0323818912533561e-05,
-      "loss": 2.4078,
+      "loss": 2.407,
       "step": 102
     },
     {
       "epoch": 1.55,
       "learning_rate": 1e-05,
-      "loss": 1.4366,
+      "loss": 1.4189,
       "step": 104
     },
     {
       "epoch": 1.58,
       "learning_rate": 9.676181087466444e-06,
-      "loss": 1.3339,
+      "loss": 1.3595,
       "step": 106
     },
     {
       "epoch": 1.61,
       "learning_rate": 9.352701816255643e-06,
-      "loss": 1.2585,
+      "loss": 1.2607,
       "step": 108
     },
     {
       "epoch": 1.64,
       "learning_rate": 9.02990147145352e-06,
-      "loss": 1.1135,
+      "loss": 1.1152,
       "step": 110
     },
     {
       "epoch": 1.67,
       "learning_rate": 8.708118626045939e-06,
-      "loss": 1.4447,
+      "loss": 1.4698,
       "step": 112
     },
     {
       "epoch": 1.7,
       "learning_rate": 8.387690785802403e-06,
-      "loss": 1.747,
+      "loss": 1.7058,
       "step": 114
     },
     {
       "epoch": 1.73,
       "learning_rate": 8.068954035279121e-06,
-      "loss": 2.0869,
+      "loss": 2.082,
       "step": 116
     },
     {
       "epoch": 1.76,
       "learning_rate": 7.752242685312709e-06,
-      "loss": 2.0168,
+      "loss": 2.0173,
       "step": 118
     },
     {
       "epoch": 1.79,
       "learning_rate": 7.4378889223742766e-06,
-      "loss": 1.5621,
+      "loss": 1.566,
       "step": 120
     },
     {
       "epoch": 1.82,
       "learning_rate": 7.126222460151719e-06,
-      "loss": 1.3901,
+      "loss": 1.392,
       "step": 122
     },
     {
       "epoch": 1.85,
       "learning_rate": 6.8175701937255645e-06,
-      "loss": 1.2683,
+      "loss": 1.271,
       "step": 124
     },
     {
       "epoch": 1.88,
       "learning_rate": 6.5122558567011775e-06,
-      "loss": 1.1724,
+      "loss": 1.1742,
       "step": 126
     },
     {
       "epoch": 1.91,
       "learning_rate": 6.210599681656933e-06,
-      "loss": 1.5036,
+      "loss": 1.4929,
       "step": 128
     },
     {
       "epoch": 1.94,
       "learning_rate": 5.912918064264441e-06,
-      "loss": 1.7858,
+      "loss": 1.7692,
       "step": 130
     },
     {
       "epoch": 1.97,
       "learning_rate": 5.619523231433177e-06,
-      "loss": 1.2173,
+      "loss": 1.2306,
       "step": 132
     },
     {
       "epoch": 2.0,
       "learning_rate": 5.330722913827594e-06,
-      "loss": 1.4985,
+      "loss": 1.4964,
       "step": 134
     },
     {
       "epoch": 2.03,
       "learning_rate": 5.046820023100129e-06,
-      "loss": 2.1682,
+      "loss": 2.1739,
       "step": 136
     },
     {
       "epoch": 2.06,
       "learning_rate": 4.7681123341787e-06,
-      "loss": 1.5148,
+      "loss": 1.5173,
       "step": 138
     },
     {
       "epoch": 2.09,
       "learning_rate": 4.494892172941965e-06,
-      "loss": 1.3437,
+      "loss": 1.3477,
       "step": 140
     },
     {
       "epoch": 2.12,
       "learning_rate": 4.2274461096098085e-06,
-      "loss": 1.4119,
+      "loss": 1.4137,
       "step": 142
     },
     {
       "epoch": 2.15,
       "learning_rate": 3.966054658170754e-06,
-      "loss": 1.1752,
+      "loss": 1.1751,
       "step": 144
     },
     {
       "epoch": 2.18,
       "learning_rate": 3.7109919821615546e-06,
-      "loss": 1.4334,
+      "loss": 1.4773,
       "step": 146
     },
     {
       "epoch": 2.21,
       "learning_rate": 3.4625256071074776e-06,
-      "loss": 1.4999,
+      "loss": 1.447,
       "step": 148
     },
     {
       "epoch": 2.24,
       "learning_rate": 3.2209161399249677e-06,
-      "loss": 1.4172,
+      "loss": 1.4195,
       "step": 150
     },
     {
       "epoch": 2.27,
       "learning_rate": 2.9864169955810085e-06,
-      "loss": 2.4804,
+      "loss": 2.4854,
       "step": 152
     },
     {
       "epoch": 2.3,
       "learning_rate": 2.759274131295787e-06,
-      "loss": 1.9752,
+      "loss": 1.9709,
       "step": 154
     },
     {
       "epoch": 2.33,
       "learning_rate": 2.5397257885675396e-06,
-      "loss": 1.4638,
+      "loss": 1.4681,
       "step": 156
     },
     {
       "epoch": 2.36,
       "learning_rate": 2.328002243290138e-06,
-      "loss": 1.4279,
+      "loss": 1.4283,
       "step": 158
     },
     {
       "epoch": 2.39,
       "learning_rate": 2.124325564225458e-06,
-      "loss": 1.1614,
+      "loss": 1.1628,
       "step": 160
     },
     {
       "epoch": 2.42,
       "learning_rate": 1.9289093800839067e-06,
-      "loss": 1.3463,
+      "loss": 1.3378,
       "step": 162
     },
     {
       "epoch": 2.45,
       "learning_rate": 1.7419586554574364e-06,
-      "loss": 1.4851,
+      "loss": 1.4992,
       "step": 164
     },
     {
       "epoch": 2.48,
       "learning_rate": 1.5636694758399563e-06,
-      "loss": 1.5392,
+      "loss": 1.5194,
       "step": 166
     },
     {
       "epoch": 2.51,
       "learning_rate": 1.3942288419607476e-06,
-      "loss": 2.1037,
+      "loss": 2.1038,
       "step": 168
     },
     {
       "epoch": 2.53,
       "learning_rate": 1.233814473646524e-06,
-      "loss": 1.573,
+      "loss": 1.5741,
       "step": 170
     },
     {
       "epoch": 2.56,
       "learning_rate": 1.0825946234178575e-06,
-      "loss": 1.4296,
+      "loss": 1.4266,
       "step": 172
     },
     {
       "epoch": 2.59,
       "learning_rate": 9.407279000155311e-07,
-      "loss": 1.5531,
+      "loss": 1.5593,
       "step": 174
     },
     {
       "epoch": 2.62,
       "learning_rate": 8.083631020418792e-07,
-      "loss": 1.1438,
+      "loss": 1.1452,
       "step": 176
     },
     {
       "epoch": 2.65,
       "learning_rate": 6.856390618915775e-07,
-      "loss": 1.1934,
+      "loss": 1.1922,
       "step": 178
     },
     {
       "epoch": 2.68,
       "learning_rate": 5.726845001356573e-07,
-      "loss": 1.5436,
+      "loss": 1.5303,
       "step": 180
     },
     {
       "epoch": 2.71,
       "learning_rate": 4.696178905113913e-07,
-      "loss": 1.5864,
+      "loss": 1.5796,
       "step": 182
     },
     {
       "epoch": 2.74,
       "learning_rate": 3.7654733565969826e-07,
-      "loss": 2.6632,
+      "loss": 2.6667,
       "step": 184
     },
     {
       "epoch": 2.77,
       "learning_rate": 2.935704537404083e-07,
-      "loss": 1.4566,
+      "loss": 1.4578,
       "step": 186
     },
     {
       "epoch": 2.8,
       "learning_rate": 2.2077427604429435e-07,
-      "loss": 1.3796,
+      "loss": 1.3813,
       "step": 188
     },
     {
       "epoch": 2.83,
       "learning_rate": 1.5823515570925763e-07,
-      "loss": 1.385,
+      "loss": 1.3865,
       "step": 190
     },
     {
       "epoch": 2.86,
       "learning_rate": 1.0601868763643997e-07,
-      "loss": 0.9717,
+      "loss": 0.9682,
       "step": 192
     },
     {
       "epoch": 2.89,
       "learning_rate": 6.417963969022389e-08,
-      "loss": 1.4063,
+      "loss": 1.4016,
       "step": 194
     },
     {
       "epoch": 2.92,
       "learning_rate": 3.2761895254306285e-08,
-      "loss": 1.6286,
+      "loss": 1.6069,
       "step": 196
     },
     {
       "epoch": 2.95,
       "learning_rate": 1.179840720409331e-08,
-      "loss": 1.5127,
+      "loss": 1.5111,
       "step": 198
     },
     {
       "epoch": 2.98,
       "learning_rate": 1.3111633436779792e-09,
-      "loss": 1.1829,
+      "loss": 1.188,
       "step": 200
     }
   ],
@@ -614,7 +614,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 1.4168234860720128e+16,
+  "total_flos": 1.4213537149710336e+16,
   "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 sha256:3f64cf07e44bd49988614f1c5896457855e086b870fd8cb30fb62dd90dfe3010
+oid sha256:ce271b16491de873616884437f0a6baabfe3fe612247046ef5bf66fb65ae12ef
 size 4728