Upload folder using huggingface_hub

model-00001-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4f25daa81041e3089f0c5611ff9eada4e29812eaaaf1414d46b011017465321
+oid sha256:5df36714cc848620821d0d91f29a48c3a6f4c9ab4d2d763da91f52ee38d095b0
 size 4997184968

model-00002-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a54bcbe6f8fa2d01f059ad775d1ce2ca0a8748e56ac0a5c4e857a65e0d59401e
+oid sha256:a0bd5ea3e409ef2a29204a175a006612ba38d4412f2ed3ebbc7b131c14e6abd8
 size 4997741608

model-00003-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c745de27ec6798ffc207fcdcfee069d4922f5c0426019b24cb4405992776c6c
+oid sha256:cd608c6295f46b573e8c297602744cc75b76a3d849e18b27d91e484a7bb1cce6
 size 4997742208

model-00004-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d68af5e887e6239c081bc847696c5cd741d44defe7d2188bf72f0eea7b0563c
+oid sha256:e3d907c21a0413e1f00c6af17ced2f28c0349825a2a5b12b8efee0a9424c9b16
 size 4997743184

model-00005-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58395c4c944248528d4a1b62309f5944a36249ea1c409e20f90ff21c17bbf49a
+oid sha256:022b29e7203e217c7924aff13191a54b63d34ee294169278b73bd2d848a407c5
 size 4997743184

model-00006-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9fcc33a21010650e8b266ea1537e594763e26c9b1eba1c28e21ec6313947cfe
+oid sha256:2064f4048082e45f9d9cf0b13c5568e4b6372a1d082ada7e74e783b2da3e6652
 size 4997743184

model-00007-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:630cc4683dc57615ce50a6b897f0bf964965e8b06446b57bf3327882e48a4383
+oid sha256:4f0bcde9b7579243d87ed6d32fd05d3ddf9c32de46e31219d7bb0cd8e985735c
 size 4997743184

model-00008-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e94df70d8dae12edaa6398c6810eaceeca28443fe9da4abc064f7543a38eb4f9
+oid sha256:74c6c4f801192a95525b02477d048b3847845b0bd9fcba3f0b50f452455574ac
 size 4997743184

model-00009-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d871090f232f36371b5605657993f4dc24d1a2f045d023216e9e3e6b80131360
+oid sha256:94263b2f50b2592bcafab6fe4f2b88bfc0eb38bffcb2d16f1d0b264d6632f52f
 size 4997743184

model-00010-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ff5549d63d7c0b6bf6f57f105aeddc96a8c0f71b687912cfdaace928a1486d7
+oid sha256:d687b57c114a8662ca806ac0bf1e5e7850a1009b76d424f00d9f6fca6d93246d
 size 4997743184

model-00011-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd42b9fbdc0159ffa146576fbe01ca567c0109ffc719ab06aa351d652ecccf3a
+oid sha256:54bc9d286c8125ab6c3f09ac65c5c2ce2aceaae60d7d0d6d5fadc374eda62950
 size 4997743184

model-00012-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb2ac1fcb28d411a4224268d44f7711ee81d6417a536f8c9d016688e8e0f4578
+oid sha256:fa15ca24ce99fa4f7b590f502aaf6a92f6e3f30e05bc7bcf6ab42c6a6bda58b6
 size 4997743184

model-00013-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4301251d9ddd9244ed412a9126d9fbb549dea24a022adddcc65f536cc934219
+oid sha256:a04c45b32da70dfcaa029d2f24ec84ada5bb225dc551eb271b4b38f154a79596
 size 1094220288

trainer_state.json

@@ -11,401 +11,401 @@
   "log_history": [
     {
       "epoch": 0.017543859649122806,
-      "grad_norm": 1.8317057887019643,
+      "grad_norm": 2.410881066137832,
       "learning_rate": 0.0,
       "loss": 0.8483,
       "step": 1
     },
     {
       "epoch": 0.03508771929824561,
-      "grad_norm": 1.7353440418305668,
+      "grad_norm": 2.665228254124179,
       "learning_rate": 3.3333333333333333e-06,
       "loss": 0.8763,
       "step": 2
     },
     {
       "epoch": 0.05263157894736842,
-      "grad_norm": 1.9110385217084043,
+      "grad_norm": 2.3728587057049992,
       "learning_rate": 6.666666666666667e-06,
-      "loss": 1.0195,
+      "loss": 1.019,
       "step": 3
     },
     {
       "epoch": 0.07017543859649122,
-      "grad_norm": 1.650455460756132,
+      "grad_norm": 1.9987528382054482,
       "learning_rate": 1e-05,
-      "loss": 1.049,
+      "loss": 1.0451,
       "step": 4
     },
     {
       "epoch": 0.08771929824561403,
-      "grad_norm": 0.9846115915202341,
+      "grad_norm": 1.2387448314677751,
       "learning_rate": 1.3333333333333333e-05,
-      "loss": 0.8378,
+      "loss": 0.8298,
       "step": 5
     },
     {
       "epoch": 0.10526315789473684,
-      "grad_norm": 1.2896673412488742,
+      "grad_norm": 1.4006709843865188,
       "learning_rate": 1.6666666666666667e-05,
-      "loss": 0.9736,
+      "loss": 0.9668,
       "step": 6
     },
     {
       "epoch": 0.12280701754385964,
-      "grad_norm": 2.011543412600694,
+      "grad_norm": 2.1941304727738995,
       "learning_rate": 2e-05,
-      "loss": 0.9678,
+      "loss": 0.9639,
       "step": 7
     },
     {
       "epoch": 0.14035087719298245,
-      "grad_norm": 1.6250329547144573,
+      "grad_norm": 2.0965952504080145,
       "learning_rate": 2.3333333333333336e-05,
-      "loss": 0.9089,
+      "loss": 0.906,
       "step": 8
     },
     {
       "epoch": 0.15789473684210525,
-      "grad_norm": 1.6751272065587126,
+      "grad_norm": 2.0779003780741325,
       "learning_rate": 2.6666666666666667e-05,
-      "loss": 0.9359,
+      "loss": 0.9331,
       "step": 9
     },
     {
       "epoch": 0.17543859649122806,
-      "grad_norm": 1.4234656524715992,
+      "grad_norm": 1.914852860029578,
       "learning_rate": 3e-05,
-      "loss": 0.9585,
+      "loss": 0.9615,
       "step": 10
     },
     {
       "epoch": 0.19298245614035087,
-      "grad_norm": 1.4638280218342359,
+      "grad_norm": 1.5453059456697873,
       "learning_rate": 3.3333333333333335e-05,
-      "loss": 1.0041,
+      "loss": 0.9976,
       "step": 11
     },
     {
       "epoch": 0.21052631578947367,
-      "grad_norm": 1.0419301809036907,
+      "grad_norm": 1.2149278389301041,
       "learning_rate": 3.6666666666666666e-05,
-      "loss": 0.8763,
+      "loss": 0.8731,
       "step": 12
     },
     {
       "epoch": 0.22807017543859648,
-      "grad_norm": 1.198346639614849,
+      "grad_norm": 9.574453131193065,
       "learning_rate": 4e-05,
-      "loss": 0.9129,
+      "loss": 0.9048,
       "step": 13
     },
     {
       "epoch": 0.24561403508771928,
-      "grad_norm": 1.0034373969603534,
+      "grad_norm": 1.7542365583306754,
       "learning_rate": 4.3333333333333334e-05,
-      "loss": 0.8965,
+      "loss": 0.9045,
       "step": 14
     },
     {
       "epoch": 0.2631578947368421,
-      "grad_norm": 1.0380657919294447,
+      "grad_norm": 1.5687648722942888,
       "learning_rate": 4.666666666666667e-05,
-      "loss": 0.957,
+      "loss": 0.9642,
       "step": 15
     },
     {
       "epoch": 0.2807017543859649,
-      "grad_norm": 0.9533939175115029,
+      "grad_norm": 1.1629052446813282,
       "learning_rate": 5e-05,
-      "loss": 0.91,
+      "loss": 0.9157,
       "step": 16
     },
     {
       "epoch": 0.2982456140350877,
-      "grad_norm": 1.2098882485474858,
+      "grad_norm": 1.0662859779498828,
       "learning_rate": 4.999830770009406e-05,
-      "loss": 1.0061,
+      "loss": 1.0076,
       "step": 17
     },
     {
       "epoch": 0.3157894736842105,
-      "grad_norm": 0.9892702554456709,
+      "grad_norm": 1.1540729762939772,
       "learning_rate": 4.9993231029486544e-05,
-      "loss": 0.8912,
+      "loss": 0.8898,
       "step": 18
     },
     {
       "epoch": 0.3333333333333333,
-      "grad_norm": 0.715562209343003,
+      "grad_norm": 2.284686909029557,
       "learning_rate": 4.99847706754774e-05,
-      "loss": 0.9125,
+      "loss": 0.9111,
       "step": 19
     },
     {
       "epoch": 0.3508771929824561,
-      "grad_norm": 0.8839740963896582,
+      "grad_norm": 0.9299877447474001,
       "learning_rate": 4.997292778346312e-05,
-      "loss": 0.9544,
+      "loss": 0.9567,
       "step": 20
     },
     {
       "epoch": 0.3684210526315789,
-      "grad_norm": 0.8672090781221823,
+      "grad_norm": 0.7891834706045853,
       "learning_rate": 4.995770395678171e-05,
-      "loss": 0.8931,
+      "loss": 0.8907,
       "step": 21
     },
     {
       "epoch": 0.38596491228070173,
-      "grad_norm": 0.5657183889732781,
+      "grad_norm": 0.7738739475483105,
       "learning_rate": 4.993910125649561e-05,
-      "loss": 0.7591,
+      "loss": 0.7582,
       "step": 22
     },
     {
       "epoch": 0.40350877192982454,
-      "grad_norm": 0.8395194599838961,
+      "grad_norm": 0.7564543923604894,
       "learning_rate": 4.9917122201112656e-05,
-      "loss": 0.8958,
+      "loss": 0.893,
       "step": 23
     },
     {
       "epoch": 0.42105263157894735,
-      "grad_norm": 0.7949156783532444,
+      "grad_norm": 0.7725302637179225,
       "learning_rate": 4.989176976624511e-05,
-      "loss": 0.7957,
+      "loss": 0.794,
       "step": 24
     },
     {
       "epoch": 0.43859649122807015,
-      "grad_norm": 0.6233078811754251,
+      "grad_norm": 0.7154589746662706,
       "learning_rate": 4.9863047384206835e-05,
-      "loss": 0.9287,
+      "loss": 0.927,
       "step": 25
     },
     {
       "epoch": 0.45614035087719296,
-      "grad_norm": 0.6592512357205284,
+      "grad_norm": 0.748200539385192,
       "learning_rate": 4.983095894354858e-05,
-      "loss": 0.8961,
+      "loss": 0.8946,
       "step": 26
     },
     {
       "epoch": 0.47368421052631576,
-      "grad_norm": 0.7540428801849153,
+      "grad_norm": 0.6877177188589038,
       "learning_rate": 4.979550878853154e-05,
-      "loss": 0.8113,
+      "loss": 0.8108,
       "step": 27
     },
     {
       "epoch": 0.49122807017543857,
-      "grad_norm": 0.6894407810210612,
+      "grad_norm": 0.6905557124467382,
       "learning_rate": 4.975670171853926e-05,
-      "loss": 0.8837,
+      "loss": 0.8808,
       "step": 28
     },
     {
       "epoch": 0.5087719298245614,
-      "grad_norm": 0.5962438335142802,
+      "grad_norm": 0.6261501879052016,
       "learning_rate": 4.971454298742779e-05,
-      "loss": 0.9039,
+      "loss": 0.902,
       "step": 29
     },
     {
       "epoch": 0.5263157894736842,
-      "grad_norm": 0.6159211013371156,
+      "grad_norm": 0.6935833833701227,
       "learning_rate": 4.966903830281449e-05,
-      "loss": 0.7894,
+      "loss": 0.7902,
       "step": 30
     },
     {
       "epoch": 0.543859649122807,
-      "grad_norm": 0.7929356664184409,
+      "grad_norm": 0.7380295796572786,
       "learning_rate": 4.962019382530521e-05,
-      "loss": 0.8463,
+      "loss": 0.8427,
       "step": 31
     },
     {
       "epoch": 0.5614035087719298,
-      "grad_norm": 0.5952896775612254,
+      "grad_norm": 0.6686373976763716,
       "learning_rate": 4.9568016167660334e-05,
-      "loss": 0.7816,
+      "loss": 0.7824,
       "step": 32
     },
     {
       "epoch": 0.5789473684210527,
-      "grad_norm": 0.6758915434113398,
+      "grad_norm": 0.7284830674570405,
       "learning_rate": 4.951251239389948e-05,
-      "loss": 0.8776,
+      "loss": 0.8758,
       "step": 33
     },
     {
       "epoch": 0.5964912280701754,
-      "grad_norm": 0.6318291971598253,
+      "grad_norm": 0.7667345279664498,
       "learning_rate": 4.9453690018345144e-05,
-      "loss": 0.9796,
+      "loss": 0.9769,
       "step": 34
     },
     {
       "epoch": 0.6140350877192983,
-      "grad_norm": 0.7115801773839961,
+      "grad_norm": 0.7186885267427574,
       "learning_rate": 4.939155700460536e-05,
-      "loss": 0.8228,
+      "loss": 0.8222,
       "step": 35
     },
     {
       "epoch": 0.631578947368421,
-      "grad_norm": 0.5864293536264706,
+      "grad_norm": 0.7129526253734785,
       "learning_rate": 4.9326121764495596e-05,
-      "loss": 0.839,
+      "loss": 0.8398,
       "step": 36
     },
     {
       "epoch": 0.6491228070175439,
-      "grad_norm": 0.6287778513114669,
+      "grad_norm": 0.6763307332151739,
       "learning_rate": 4.925739315689991e-05,
-      "loss": 0.8778,
+      "loss": 0.881,
       "step": 37
     },
     {
       "epoch": 0.6666666666666666,
-      "grad_norm": 0.6735952098345708,
+      "grad_norm": 0.7596612492978558,
       "learning_rate": 4.9185380486571595e-05,
-      "loss": 0.885,
+      "loss": 0.8883,
       "step": 38
     },
     {
       "epoch": 0.6842105263157895,
-      "grad_norm": 0.6067535888888641,
+      "grad_norm": 0.574360173449421,
       "learning_rate": 4.9110093502873476e-05,
-      "loss": 0.9082,
+      "loss": 0.9078,
       "step": 39
     },
     {
       "epoch": 0.7017543859649122,
-      "grad_norm": 0.5247508841910119,
+      "grad_norm": 0.5045882171460956,
       "learning_rate": 4.9031542398457974e-05,
-      "loss": 0.8739,
+      "loss": 0.8722,
       "step": 40
     },
     {
       "epoch": 0.7192982456140351,
-      "grad_norm": 0.5918453184670143,
+      "grad_norm": 0.6267476132219085,
       "learning_rate": 4.894973780788722e-05,
-      "loss": 0.8829,
+      "loss": 0.883,
       "step": 41
     },
     {
       "epoch": 0.7368421052631579,
-      "grad_norm": 0.6372269077212606,
+      "grad_norm": 0.6021189923969766,
       "learning_rate": 4.88646908061933e-05,
-      "loss": 0.8152,
+      "loss": 0.8144,
       "step": 42
     },
     {
       "epoch": 0.7543859649122807,
-      "grad_norm": 0.5430663295315261,
+      "grad_norm": 0.6014066609170303,
       "learning_rate": 4.877641290737884e-05,
-      "loss": 0.8514,
+      "loss": 0.8496,
       "step": 43
     },
     {
       "epoch": 0.7719298245614035,
-      "grad_norm": 0.511597332007924,
+      "grad_norm": 0.6014121657776419,
       "learning_rate": 4.868491606285823e-05,
-      "loss": 0.7675,
+      "loss": 0.768,
       "step": 44
     },
     {
       "epoch": 0.7894736842105263,
-      "grad_norm": 0.48967659833861754,
+      "grad_norm": 0.5324268865416073,
       "learning_rate": 4.859021265983959e-05,
-      "loss": 0.8826,
+      "loss": 0.8825,
       "step": 45
     },
     {
       "epoch": 0.8070175438596491,
-      "grad_norm": 0.5856811530030098,
+      "grad_norm": 0.6348338184686191,
       "learning_rate": 4.849231551964771e-05,
-      "loss": 0.8585,
+      "loss": 0.8587,
       "step": 46
     },
     {
       "epoch": 0.8245614035087719,
-      "grad_norm": 0.5845644414839125,
+      "grad_norm": 0.6361465840640576,
       "learning_rate": 4.839123789598829e-05,
-      "loss": 0.8677,
+      "loss": 0.868,
       "step": 47
     },
     {
       "epoch": 0.8421052631578947,
-      "grad_norm": 0.4974332648938187,
+      "grad_norm": 0.5806423652725062,
       "learning_rate": 4.828699347315356e-05,
-      "loss": 0.845,
+      "loss": 0.8445,
       "step": 48
     },
     {
       "epoch": 0.8596491228070176,
-      "grad_norm": 0.5566174918152419,
+      "grad_norm": 0.6650303211642944,
       "learning_rate": 4.817959636416969e-05,
-      "loss": 0.9432,
+      "loss": 0.9439,
       "step": 49
     },
     {
       "epoch": 0.8771929824561403,
-      "grad_norm": 0.4921351014911049,
+      "grad_norm": 0.49618932027271617,
       "learning_rate": 4.806906110888606e-05,
-      "loss": 0.6756,
+      "loss": 0.676,
       "step": 50
     },
     {
       "epoch": 0.8947368421052632,
-      "grad_norm": 0.6352002986003276,
+      "grad_norm": 0.7201128419875511,
       "learning_rate": 4.7955402672006854e-05,
-      "loss": 0.9077,
+      "loss": 0.9129,
       "step": 51
     },
     {
       "epoch": 0.9122807017543859,
-      "grad_norm": 0.5228777570085404,
+      "grad_norm": 0.7979009332190922,
       "learning_rate": 4.783863644106502e-05,
-      "loss": 0.8815,
+      "loss": 0.8844,
       "step": 52
     },
     {
       "epoch": 0.9298245614035088,
-      "grad_norm": 0.5753314530576694,
+      "grad_norm": 0.5780879587849941,
       "learning_rate": 4.771877822433911e-05,
-      "loss": 0.8342,
+      "loss": 0.835,
       "step": 53
     },
     {
       "epoch": 0.9473684210526315,
-      "grad_norm": 0.5127814989448164,
+      "grad_norm": 0.5125413888902927,
       "learning_rate": 4.759584424871302e-05,
-      "loss": 0.7837,
+      "loss": 0.7854,
       "step": 54
     },
     {
       "epoch": 0.9649122807017544,
-      "grad_norm": 0.545931046230859,
+      "grad_norm": 0.6493310136858548,
       "learning_rate": 4.7469851157479177e-05,
-      "loss": 0.8229,
+      "loss": 0.8246,
       "step": 55
     },
     {
       "epoch": 0.9824561403508771,
-      "grad_norm": 0.4669374807712089,
+      "grad_norm": 0.5420670379906682,
       "learning_rate": 4.734081600808531e-05,
-      "loss": 0.8341,
+      "loss": 0.8357,
       "step": 56
     },
     {
       "epoch": 1.0,
-      "grad_norm": 0.5386650743226552,
+      "grad_norm": 0.8014271486806656,
       "learning_rate": 4.7208756269825104e-05,
-      "loss": 0.7062,
+      "loss": 0.7012,
       "step": 57
     }
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14ce14cb5b4d1f6b7378f3a0d59f90353c316de79d943a6fb969a0b7df2b441c
+oid sha256:3b09193bae298a0a841c37ce61432d61767b4d633b9680c59539c690bef78161
 size 8081