Training in progress, epoch 1, checkpoint

checkpoint-1469/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41e784c8c66a8a24b891f9e7cb9e5c291d1946482d489927bdba0617899678a5
+oid sha256:701d2071e676254cb7f486c1583f3b336c0ab235a36ec3a2025604309a9f014d
 size 383295784

checkpoint-1469/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:930a7b2f85ed02cbfb8792d0ca762b70ae705518d7f4c19b05ed96f62b8cdbd0
+oid sha256:eaff70510894b4e6680f626eacbecc09f01ab54ea65441557aadde172c4c0421
 size 184533306

checkpoint-1469/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b8c11102d4b341eb099e507d80d3c782f420154e1604e2d7f85defeb24e33f2
+oid sha256:e2c5e1fd5d6bb74e9a611fd5587f335900288ad79fa0962b80a02eb52bde4304
 size 14308

checkpoint-1469/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2ec84729d9ec9e310defe44d38dfd41ab0bf0bd1f9f56fc1eae0c101f6d849b
+oid sha256:d51456e725db3a4810896373a397c9561592927e76bb2a2bf3bbb17ab1a7f915
 size 1064

checkpoint-1469/trainer_state.json

@@ -10,538 +10,538 @@
   "log_history": [
     {
       "epoch": 0.013614703880190605,
-      "grad_norm": 46384.1953125,
-      "learning_rate": 1.360544217687075e-07,
-      "loss": 2.0802,
+      "grad_norm": 46436.91796875,
+      "learning_rate": 1.6304347826086958e-07,
+      "loss": 2.0803,
       "step": 20
     },
     {
       "epoch": 0.02722940776038121,
-      "grad_norm": 35930.53515625,
-      "learning_rate": 2.72108843537415e-07,
-      "loss": 2.08,
+      "grad_norm": 35970.4375,
+      "learning_rate": 3.2608695652173915e-07,
+      "loss": 2.0801,
       "step": 40
     },
     {
       "epoch": 0.04084411164057182,
-      "grad_norm": 23965.296875,
-      "learning_rate": 4.0816326530612243e-07,
-      "loss": 2.0796,
+      "grad_norm": 24038.876953125,
+      "learning_rate": 4.891304347826088e-07,
+      "loss": 2.0801,
       "step": 60
     },
     {
       "epoch": 0.05445881552076242,
-      "grad_norm": 32476.51953125,
-      "learning_rate": 5.4421768707483e-07,
-      "loss": 2.0791,
+      "grad_norm": 31534.74609375,
+      "learning_rate": 6.521739130434783e-07,
+      "loss": 2.0799,
       "step": 80
     },
     {
       "epoch": 0.06807351940095303,
-      "grad_norm": 31751.640625,
-      "learning_rate": 6.802721088435376e-07,
-      "loss": 2.0793,
+      "grad_norm": 31741.2421875,
+      "learning_rate": 8.152173913043478e-07,
+      "loss": 2.0797,
       "step": 100
     },
     {
       "epoch": 0.08168822328114364,
-      "grad_norm": 29360.6328125,
-      "learning_rate": 8.163265306122449e-07,
-      "loss": 2.0793,
+      "grad_norm": 29444.419921875,
+      "learning_rate": 9.782608695652175e-07,
+      "loss": 2.0789,
       "step": 120
     },
     {
       "epoch": 0.09530292716133425,
-      "grad_norm": 31927.123046875,
-      "learning_rate": 9.523809523809525e-07,
-      "loss": 2.0788,
+      "grad_norm": 31825.087890625,
+      "learning_rate": 1.141304347826087e-06,
+      "loss": 2.079,
       "step": 140
     },
     {
       "epoch": 0.10891763104152484,
-      "grad_norm": 31685.216796875,
-      "learning_rate": 1.08843537414966e-06,
+      "grad_norm": 31622.044921875,
+      "learning_rate": 1.3043478260869566e-06,
       "loss": 2.0783,
       "step": 160
     },
     {
       "epoch": 0.12253233492171545,
-      "grad_norm": 24569.869140625,
-      "learning_rate": 1.2244897959183673e-06,
-      "loss": 2.078,
+      "grad_norm": 24459.58203125,
+      "learning_rate": 1.4673913043478262e-06,
+      "loss": 2.0774,
       "step": 180
     },
     {
       "epoch": 0.13614703880190607,
-      "grad_norm": 29527.107421875,
-      "learning_rate": 1.3605442176870751e-06,
-      "loss": 2.0772,
+      "grad_norm": 29978.267578125,
+      "learning_rate": 1.6304347826086955e-06,
+      "loss": 2.0771,
       "step": 200
     },
     {
       "epoch": 0.14976174268209666,
-      "grad_norm": 31908.814453125,
-      "learning_rate": 1.4965986394557825e-06,
-      "loss": 2.0768,
+      "grad_norm": 31998.130859375,
+      "learning_rate": 1.7934782608695653e-06,
+      "loss": 2.0766,
       "step": 220
     },
     {
       "epoch": 0.16337644656228728,
-      "grad_norm": 34667.72265625,
-      "learning_rate": 1.6326530612244897e-06,
-      "loss": 2.0754,
+      "grad_norm": 34736.546875,
+      "learning_rate": 1.956521739130435e-06,
+      "loss": 2.075,
       "step": 240
     },
     {
       "epoch": 0.17699115044247787,
-      "grad_norm": 36386.16015625,
-      "learning_rate": 1.7687074829931975e-06,
-      "loss": 2.0742,
+      "grad_norm": 36555.73046875,
+      "learning_rate": 2.1195652173913046e-06,
+      "loss": 2.0723,
       "step": 260
     },
     {
       "epoch": 0.1906058543226685,
-      "grad_norm": 24842.310546875,
-      "learning_rate": 1.904761904761905e-06,
-      "loss": 2.0722,
+      "grad_norm": 25291.138671875,
+      "learning_rate": 2.282608695652174e-06,
+      "loss": 2.0698,
       "step": 280
     },
     {
       "epoch": 0.2042205582028591,
-      "grad_norm": 28252.93359375,
-      "learning_rate": 2.0408163265306125e-06,
-      "loss": 2.0696,
+      "grad_norm": 29135.255859375,
+      "learning_rate": 2.4456521739130433e-06,
+      "loss": 2.0654,
       "step": 300
     },
     {
       "epoch": 0.21783526208304968,
-      "grad_norm": 18715.328125,
-      "learning_rate": 2.17687074829932e-06,
-      "loss": 2.0682,
+      "grad_norm": 18903.984375,
+      "learning_rate": 2.6086956521739132e-06,
+      "loss": 2.0625,
       "step": 320
     },
     {
       "epoch": 0.2314499659632403,
-      "grad_norm": 34919.875,
-      "learning_rate": 2.3129251700680273e-06,
-      "loss": 2.0648,
+      "grad_norm": 37406.1953125,
+      "learning_rate": 2.771739130434783e-06,
+      "loss": 2.0563,
       "step": 340
     },
     {
       "epoch": 0.2450646698434309,
-      "grad_norm": 41688.1484375,
-      "learning_rate": 2.4489795918367347e-06,
-      "loss": 2.0573,
+      "grad_norm": 46206.06640625,
+      "learning_rate": 2.9347826086956523e-06,
+      "loss": 2.0437,
       "step": 360
     },
     {
       "epoch": 0.2586793737236215,
-      "grad_norm": 38931.60546875,
-      "learning_rate": 2.5850340136054425e-06,
-      "loss": 2.052,
+      "grad_norm": 43209.96484375,
+      "learning_rate": 2.994840189193063e-06,
+      "loss": 2.0383,
       "step": 380
     },
     {
       "epoch": 0.27229407760381213,
-      "grad_norm": 37335.18359375,
-      "learning_rate": 2.7210884353741503e-06,
-      "loss": 2.0462,
+      "grad_norm": 42192.875,
+      "learning_rate": 2.9862405045148345e-06,
+      "loss": 2.0308,
       "step": 400
     },
     {
       "epoch": 0.2859087814840027,
-      "grad_norm": 32101.99609375,
-      "learning_rate": 2.8571428571428573e-06,
-      "loss": 2.0439,
+      "grad_norm": 35841.48046875,
+      "learning_rate": 2.977640819836606e-06,
+      "loss": 2.0333,
       "step": 420
     },
     {
       "epoch": 0.2995234853641933,
-      "grad_norm": 44584.16796875,
-      "learning_rate": 2.993197278911565e-06,
-      "loss": 2.0354,
+      "grad_norm": 49910.5234375,
+      "learning_rate": 2.969041135158378e-06,
+      "loss": 2.0314,
       "step": 440
     },
     {
       "epoch": 0.3131381892443839,
-      "grad_norm": 45670.23046875,
-      "learning_rate": 3.1292517006802725e-06,
-      "loss": 2.0189,
+      "grad_norm": 50317.3046875,
+      "learning_rate": 2.960441450480149e-06,
+      "loss": 2.0,
       "step": 460
     },
     {
       "epoch": 0.32675289312457456,
-      "grad_norm": 35136.80859375,
-      "learning_rate": 3.2653061224489794e-06,
-      "loss": 2.0123,
+      "grad_norm": 38199.23046875,
+      "learning_rate": 2.951841765801921e-06,
+      "loss": 1.9918,
       "step": 480
     },
     {
       "epoch": 0.34036759700476515,
-      "grad_norm": 45886.94140625,
-      "learning_rate": 3.4013605442176872e-06,
-      "loss": 2.0115,
+      "grad_norm": 49415.7734375,
+      "learning_rate": 2.9432420811236923e-06,
+      "loss": 2.005,
       "step": 500
     },
     {
       "epoch": 0.34036759700476515,
       "eval_accuracy": 0.1981891348088531,
-      "eval_loss": 1.9869346618652344,
-      "eval_runtime": 306.1857,
-      "eval_samples_per_second": 9.739,
-      "eval_steps_per_second": 1.218,
+      "eval_loss": 2.0004630088806152,
+      "eval_runtime": 302.489,
+      "eval_samples_per_second": 9.858,
+      "eval_steps_per_second": 1.233,
       "step": 500
     },
     {
       "epoch": 0.35398230088495575,
-      "grad_norm": 51081.21875,
-      "learning_rate": 3.537414965986395e-06,
-      "loss": 1.9899,
+      "grad_norm": 55542.02734375,
+      "learning_rate": 2.934642396445464e-06,
+      "loss": 1.9813,
       "step": 520
     },
     {
       "epoch": 0.36759700476514634,
-      "grad_norm": 65917.5625,
-      "learning_rate": 3.6734693877551024e-06,
-      "loss": 1.9912,
+      "grad_norm": 72033.6328125,
+      "learning_rate": 2.9260427117672353e-06,
+      "loss": 1.9823,
       "step": 540
     },
     {
       "epoch": 0.381211708645337,
-      "grad_norm": 70819.2109375,
-      "learning_rate": 3.80952380952381e-06,
-      "loss": 1.9697,
+      "grad_norm": 75101.5,
+      "learning_rate": 2.9174430270890068e-06,
+      "loss": 1.9645,
       "step": 560
     },
     {
       "epoch": 0.3948264125255276,
-      "grad_norm": 34979.16015625,
-      "learning_rate": 3.945578231292517e-06,
-      "loss": 1.9669,
+      "grad_norm": 36483.359375,
+      "learning_rate": 2.9088433424107783e-06,
+      "loss": 1.9719,
       "step": 580
     },
     {
       "epoch": 0.4084411164057182,
-      "grad_norm": 86509.28125,
-      "learning_rate": 4.081632653061225e-06,
-      "loss": 1.9561,
+      "grad_norm": 85846.6328125,
+      "learning_rate": 2.9002436577325497e-06,
+      "loss": 1.9678,
       "step": 600
     },
     {
       "epoch": 0.42205582028590877,
-      "grad_norm": 80961.046875,
-      "learning_rate": 4.217687074829933e-06,
-      "loss": 1.9278,
+      "grad_norm": 77670.828125,
+      "learning_rate": 2.8916439730543216e-06,
+      "loss": 1.9434,
       "step": 620
     },
     {
       "epoch": 0.43567052416609936,
-      "grad_norm": 136664.796875,
-      "learning_rate": 4.35374149659864e-06,
-      "loss": 1.9133,
+      "grad_norm": 128272.1796875,
+      "learning_rate": 2.8830442883760927e-06,
+      "loss": 1.9346,
       "step": 640
     },
     {
       "epoch": 0.44928522804629,
-      "grad_norm": 82047.3828125,
-      "learning_rate": 4.489795918367348e-06,
-      "loss": 1.8824,
+      "grad_norm": 74940.3984375,
+      "learning_rate": 2.8744446036978646e-06,
+      "loss": 1.9191,
       "step": 660
     },
     {
       "epoch": 0.4628999319264806,
-      "grad_norm": 100084.4375,
-      "learning_rate": 4.6258503401360546e-06,
-      "loss": 1.8542,
+      "grad_norm": 96815.6015625,
+      "learning_rate": 2.865844919019636e-06,
+      "loss": 1.8909,
       "step": 680
     },
     {
       "epoch": 0.4765146358066712,
-      "grad_norm": 91592.125,
-      "learning_rate": 4.761904761904762e-06,
-      "loss": 1.8855,
+      "grad_norm": 81240.6875,
+      "learning_rate": 2.8572452343414075e-06,
+      "loss": 1.921,
       "step": 700
     },
     {
       "epoch": 0.4901293396868618,
-      "grad_norm": 107294.0546875,
-      "learning_rate": 4.897959183673469e-06,
-      "loss": 1.869,
+      "grad_norm": 91377.9765625,
+      "learning_rate": 2.848645549663179e-06,
+      "loss": 1.9241,
       "step": 720
     },
     {
       "epoch": 0.5037440435670524,
-      "grad_norm": 65171.02734375,
-      "learning_rate": 4.998208527409531e-06,
-      "loss": 1.8418,
+      "grad_norm": 58107.17578125,
+      "learning_rate": 2.8400458649849505e-06,
+      "loss": 1.907,
       "step": 740
     },
     {
       "epoch": 0.517358747447243,
-      "grad_norm": 122938.7578125,
-      "learning_rate": 4.991042637047653e-06,
-      "loss": 1.7756,
+      "grad_norm": 100952.0234375,
+      "learning_rate": 2.8314461803067224e-06,
+      "loss": 1.8606,
       "step": 760
     },
     {
       "epoch": 0.5309734513274337,
-      "grad_norm": 149156.90625,
-      "learning_rate": 4.9838767466857765e-06,
-      "loss": 1.7877,
+      "grad_norm": 113918.6796875,
+      "learning_rate": 2.8228464956284935e-06,
+      "loss": 1.8657,
       "step": 780
     },
     {
       "epoch": 0.5445881552076243,
-      "grad_norm": 114232.359375,
-      "learning_rate": 4.976710856323898e-06,
-      "loss": 1.7956,
+      "grad_norm": 83428.9375,
+      "learning_rate": 2.8142468109502654e-06,
+      "loss": 1.877,
       "step": 800
     },
     {
       "epoch": 0.5582028590878149,
-      "grad_norm": 71295.1171875,
-      "learning_rate": 4.969544965962021e-06,
-      "loss": 1.8045,
+      "grad_norm": 64413.90234375,
+      "learning_rate": 2.805647126272037e-06,
+      "loss": 1.8967,
       "step": 820
     },
     {
       "epoch": 0.5718175629680055,
-      "grad_norm": 107194.9453125,
-      "learning_rate": 4.962379075600144e-06,
-      "loss": 1.7672,
+      "grad_norm": 88485.0703125,
+      "learning_rate": 2.7970474415938083e-06,
+      "loss": 1.8517,
       "step": 840
     },
     {
       "epoch": 0.585432266848196,
-      "grad_norm": 187415.6875,
-      "learning_rate": 4.9552131852382664e-06,
-      "loss": 1.7479,
+      "grad_norm": 145627.515625,
+      "learning_rate": 2.78844775691558e-06,
+      "loss": 1.8351,
       "step": 860
     },
     {
       "epoch": 0.5990469707283866,
-      "grad_norm": 138833.421875,
-      "learning_rate": 4.948047294876388e-06,
-      "loss": 1.8075,
+      "grad_norm": 111430.3828125,
+      "learning_rate": 2.7798480722373513e-06,
+      "loss": 1.8828,
       "step": 880
     },
     {
       "epoch": 0.6126616746085772,
-      "grad_norm": 164837.234375,
-      "learning_rate": 4.940881404514512e-06,
-      "loss": 1.7473,
+      "grad_norm": 119978.2265625,
+      "learning_rate": 2.7712483875591228e-06,
+      "loss": 1.8287,
       "step": 900
     },
     {
       "epoch": 0.6262763784887678,
-      "grad_norm": 148592.34375,
-      "learning_rate": 4.933715514152634e-06,
-      "loss": 1.647,
+      "grad_norm": 109119.8046875,
+      "learning_rate": 2.7626487028808942e-06,
+      "loss": 1.7565,
       "step": 920
     },
     {
       "epoch": 0.6398910823689585,
-      "grad_norm": 219803.328125,
-      "learning_rate": 4.926549623790756e-06,
-      "loss": 1.7584,
+      "grad_norm": 168422.890625,
+      "learning_rate": 2.754049018202666e-06,
+      "loss": 1.8571,
       "step": 940
     },
     {
       "epoch": 0.6535057862491491,
-      "grad_norm": 65507.84375,
-      "learning_rate": 4.919383733428879e-06,
-      "loss": 1.7161,
+      "grad_norm": 72286.7265625,
+      "learning_rate": 2.745449333524437e-06,
+      "loss": 1.8037,
       "step": 960
     },
     {
       "epoch": 0.6671204901293397,
-      "grad_norm": 216308.921875,
-      "learning_rate": 4.912217843067002e-06,
-      "loss": 1.787,
+      "grad_norm": 165114.03125,
+      "learning_rate": 2.736849648846209e-06,
+      "loss": 1.8221,
       "step": 980
     },
     {
       "epoch": 0.6807351940095303,
-      "grad_norm": 169682.25,
-      "learning_rate": 4.905051952705124e-06,
-      "loss": 1.7747,
+      "grad_norm": 139429.90625,
+      "learning_rate": 2.7282499641679806e-06,
+      "loss": 1.8316,
       "step": 1000
     },
     {
       "epoch": 0.6807351940095303,
       "eval_accuracy": 0.1981891348088531,
-      "eval_loss": 1.6881698369979858,
-      "eval_runtime": 294.5683,
-      "eval_samples_per_second": 10.123,
-      "eval_steps_per_second": 1.266,
+      "eval_loss": 1.8303836584091187,
+      "eval_runtime": 286.8908,
+      "eval_samples_per_second": 10.394,
+      "eval_steps_per_second": 1.3,
       "step": 1000
     },
     {
       "epoch": 0.6943498978897209,
-      "grad_norm": 247486.65625,
-      "learning_rate": 4.897886062343246e-06,
-      "loss": 1.765,
+      "grad_norm": 180090.1875,
+      "learning_rate": 2.719650279489752e-06,
+      "loss": 1.8362,
       "step": 1020
     },
     {
       "epoch": 0.7079646017699115,
-      "grad_norm": 169864.59375,
-      "learning_rate": 4.890720171981369e-06,
-      "loss": 1.7452,
+      "grad_norm": 118638.21875,
+      "learning_rate": 2.7110505948115235e-06,
+      "loss": 1.8059,
       "step": 1040
     },
     {
       "epoch": 0.7215793056501021,
-      "grad_norm": 141110.296875,
-      "learning_rate": 4.883554281619492e-06,
-      "loss": 1.8073,
+      "grad_norm": 108668.46875,
+      "learning_rate": 2.7024509101332954e-06,
+      "loss": 1.8377,
       "step": 1060
     },
     {
       "epoch": 0.7351940095302927,
-      "grad_norm": 168530.28125,
-      "learning_rate": 4.876388391257614e-06,
-      "loss": 1.7331,
+      "grad_norm": 111934.5625,
+      "learning_rate": 2.6938512254550665e-06,
+      "loss": 1.7902,
       "step": 1080
     },
     {
       "epoch": 0.7488087134104833,
-      "grad_norm": 131218.578125,
-      "learning_rate": 4.869222500895736e-06,
-      "loss": 1.6542,
+      "grad_norm": 129614.65625,
+      "learning_rate": 2.6852515407768384e-06,
+      "loss": 1.7476,
       "step": 1100
     },
     {
       "epoch": 0.762423417290674,
-      "grad_norm": 151837.5,
-      "learning_rate": 4.862056610533859e-06,
-      "loss": 1.7534,
+      "grad_norm": 132005.140625,
+      "learning_rate": 2.67665185609861e-06,
+      "loss": 1.791,
       "step": 1120
     },
     {
       "epoch": 0.7760381211708646,
-      "grad_norm": 131823.84375,
-      "learning_rate": 4.854890720171982e-06,
-      "loss": 1.7498,
+      "grad_norm": 111099.4921875,
+      "learning_rate": 2.6680521714203813e-06,
+      "loss": 1.8005,
       "step": 1140
     },
     {
       "epoch": 0.7896528250510552,
-      "grad_norm": 219690.40625,
-      "learning_rate": 4.847724829810104e-06,
-      "loss": 1.643,
+      "grad_norm": 186854.171875,
+      "learning_rate": 2.659452486742153e-06,
+      "loss": 1.7101,
       "step": 1160
     },
     {
       "epoch": 0.8032675289312458,
-      "grad_norm": 121273.3125,
-      "learning_rate": 4.840558939448226e-06,
-      "loss": 1.7032,
+      "grad_norm": 116679.1328125,
+      "learning_rate": 2.6508528020639243e-06,
+      "loss": 1.7432,
       "step": 1180
     },
     {
       "epoch": 0.8168822328114363,
-      "grad_norm": 204578.28125,
-      "learning_rate": 4.83339304908635e-06,
-      "loss": 1.7133,
+      "grad_norm": 148153.296875,
+      "learning_rate": 2.642253117385696e-06,
+      "loss": 1.7575,
       "step": 1200
     },
     {
       "epoch": 0.8304969366916269,
-      "grad_norm": 87904.203125,
-      "learning_rate": 4.826227158724472e-06,
-      "loss": 1.7369,
+      "grad_norm": 78890.7578125,
+      "learning_rate": 2.6336534327074673e-06,
+      "loss": 1.7866,
       "step": 1220
     },
     {
       "epoch": 0.8441116405718175,
-      "grad_norm": 94867.0625,
-      "learning_rate": 4.819061268362594e-06,
-      "loss": 1.8071,
+      "grad_norm": 73448.65625,
+      "learning_rate": 2.625053748029239e-06,
+      "loss": 1.8399,
       "step": 1240
     },
     {
       "epoch": 0.8577263444520081,
-      "grad_norm": 231554.109375,
-      "learning_rate": 4.811895378000717e-06,
-      "loss": 1.8353,
+      "grad_norm": 214759.703125,
+      "learning_rate": 2.6164540633510106e-06,
+      "loss": 1.8554,
       "step": 1260
     },
     {
       "epoch": 0.8713410483321987,
-      "grad_norm": 178638.8125,
-      "learning_rate": 4.80472948763884e-06,
-      "loss": 1.7133,
+      "grad_norm": 132226.390625,
+      "learning_rate": 2.607854378672782e-06,
+      "loss": 1.7432,
       "step": 1280
     },
     {
       "epoch": 0.8849557522123894,
-      "grad_norm": 166282.265625,
-      "learning_rate": 4.7975635972769616e-06,
-      "loss": 1.6657,
+      "grad_norm": 139430.578125,
+      "learning_rate": 2.5992546939945536e-06,
+      "loss": 1.7099,
       "step": 1300
     },
     {
       "epoch": 0.89857045609258,
-      "grad_norm": 192489.40625,
-      "learning_rate": 4.790397706915085e-06,
-      "loss": 1.6692,
+      "grad_norm": 132929.875,
+      "learning_rate": 2.590655009316325e-06,
+      "loss": 1.7122,
       "step": 1320
     },
     {
       "epoch": 0.9121851599727706,
-      "grad_norm": 252441.734375,
-      "learning_rate": 4.783231816553207e-06,
-      "loss": 1.6666,
+      "grad_norm": 246533.125,
+      "learning_rate": 2.5820553246380966e-06,
+      "loss": 1.7024,
       "step": 1340
     },
     {
       "epoch": 0.9257998638529612,
-      "grad_norm": 134902.515625,
-      "learning_rate": 4.77606592619133e-06,
-      "loss": 1.8356,
+      "grad_norm": 140797.140625,
+      "learning_rate": 2.573455639959868e-06,
+      "loss": 1.8611,
       "step": 1360
     },
     {
       "epoch": 0.9394145677331518,
-      "grad_norm": 207219.609375,
-      "learning_rate": 4.768900035829452e-06,
-      "loss": 1.7977,
+      "grad_norm": 179730.140625,
+      "learning_rate": 2.56485595528164e-06,
+      "loss": 1.8152,
       "step": 1380
     },
     {
       "epoch": 0.9530292716133424,
-      "grad_norm": 110303.21875,
-      "learning_rate": 4.761734145467575e-06,
-      "loss": 1.6795,
+      "grad_norm": 107053.234375,
+      "learning_rate": 2.556256270603411e-06,
+      "loss": 1.7251,
       "step": 1400
     },
     {
       "epoch": 0.966643975493533,
-      "grad_norm": 155455.640625,
-      "learning_rate": 4.754568255105697e-06,
-      "loss": 1.7061,
+      "grad_norm": 148813.046875,
+      "learning_rate": 2.547656585925183e-06,
+      "loss": 1.7433,
       "step": 1420
     },
     {
       "epoch": 0.9802586793737236,
-      "grad_norm": 238588.40625,
-      "learning_rate": 4.74740236474382e-06,
-      "loss": 1.7127,
+      "grad_norm": 207710.78125,
+      "learning_rate": 2.5390569012469544e-06,
+      "loss": 1.7679,
       "step": 1440
     },
     {
       "epoch": 0.9938733832539143,
-      "grad_norm": 358719.46875,
-      "learning_rate": 4.740236474381942e-06,
-      "loss": 1.7185,
+      "grad_norm": 343417.40625,
+      "learning_rate": 2.530457216568726e-06,
+      "loss": 1.7534,
       "step": 1460
     }
   ],
   "logging_steps": 20,
-  "max_steps": 14690,
+  "max_steps": 7345,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 10,
+  "num_train_epochs": 5,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {

checkpoint-1469/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0eecac33aad667da4f4ae5a58f5c275e5b47b428ee45b4e90760cd1ea6b1c435
+oid sha256:afe2658963e005554f6f06fcd5df65a7ddb835737aa4d0ac12b591a847e9f9e9
 size 5176