Training in progress, step 700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28d15da9af301277310acc0b89ceba89e60b1da4d1490ae6c5de047dbc248f61
+oid sha256:3e9056b95b69811556bbbab4909b13b9f29315b95936bfb64bc63ae28d402fb1
 size 413085368

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7280325c4227f3f70d9aa819988c5685def3e83e3d99fe2b4ece9c86024b4a1f
+oid sha256:015601a740b4cf20fc09fef3f06463c812e19a4a15baffd2a62d379b525e5448
 size 348403672

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d153cbd5816bad7e393766d8a9ab7370767a743794723f4d66f035c55bea3201
+oid sha256:631efc3abf5a36014450900fad93b8d3f2995f952dae98fd7425b6875e114a2a
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cf6320e61cad91d817b3175aa63c2bffb4c5c8db4e7b0ae3fd9b761374e3cfc
+oid sha256:3db7f30731a016df744ba5e943c5a72e4b1cf4337482ecadb31ab0a0a177fb91
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6baa6638ee60a43a92f69e130b69f4ccd62bff32f6bafab4da7f0364252faef6
+oid sha256:f681f974a94e0a2c66c1abdd7f0ead89d21c1be7c5c0471b01ae966fdbe6e1b4
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0992e134d32ed3abd9b8e06cbc166e0100a68cdef8da84ec1b2e5e2e2413baeb
+oid sha256:abd6e1ce998d7be3d4c58694feb93e4792744bd560a2382ce56af0849f5ce5f7
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d452f5ed56546a6402f4038d92474259f8b52c0076c284980ad6fb42ea107eb4
+oid sha256:da1317e51f02727b9c9a875b269ddda1c544429c3b505d10d59cd59ee551f012
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd8be60fb86bc6e7cec48c48c53cb8dd0e2aec1e30c5cfcdb31232bc12cd246c
+oid sha256:19ba223d36a93c2c23c48d6c58884870776a88563e3a6d4158aeee1cf466ccc7
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc7bbac244760ea3c1579f834f91bb860d6b6348bcc2b73bd97b775d6e442387
+oid sha256:3cf879edc3373f3aa1fbfa5e39bed9c1d9f687cefa885aaa51983263621bfbad
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33df15a0d0c8b844eb7dfbbf49148670f816272f730064d145e3081bfa07317b
+oid sha256:c842ac876e2d9e274e43bcbfb734aef5a3ad04915985ece79c51c1dec6267db2
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6aba0f78a6ddd258c43ec093bf60cb133a45c0f2e060c6fded879ac028f3123e
+oid sha256:58326b6331289c141bb2ed088a04a076bde1df3da5eec19b81a35fe023f7a792
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.0859394073486328,
   "best_model_checkpoint": "miner_id_24/checkpoint-500",
-  "epoch": 0.4917629702483403,
+  "epoch": 0.6884681583476764,
   "eval_steps": 250,
-  "global_step": 500,
+  "global_step": 700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3531,6 +3531,1406 @@
       "eval_samples_per_second": 33.548,
       "eval_steps_per_second": 4.195,
       "step": 500
+    },
+    {
+      "epoch": 0.492746496188837,
+      "grad_norm": 1.7722065448760986,
+      "learning_rate": 9.909447523699617e-05,
+      "loss": 1.142,
+      "step": 501
+    },
+    {
+      "epoch": 0.49373002212933365,
+      "grad_norm": 1.684760332107544,
+      "learning_rate": 9.819171684992574e-05,
+      "loss": 1.1404,
+      "step": 502
+    },
+    {
+      "epoch": 0.49471354806983037,
+      "grad_norm": 1.6577117443084717,
+      "learning_rate": 9.729174958836604e-05,
+      "loss": 1.1942,
+      "step": 503
+    },
+    {
+      "epoch": 0.49569707401032703,
+      "grad_norm": 1.6315124034881592,
+      "learning_rate": 9.639459812537399e-05,
+      "loss": 1.1396,
+      "step": 504
+    },
+    {
+      "epoch": 0.4966805999508237,
+      "grad_norm": 1.611763834953308,
+      "learning_rate": 9.550028705681025e-05,
+      "loss": 1.0717,
+      "step": 505
+    },
+    {
+      "epoch": 0.49766412589132036,
+      "grad_norm": 1.792077660560608,
+      "learning_rate": 9.460884090066449e-05,
+      "loss": 1.1422,
+      "step": 506
+    },
+    {
+      "epoch": 0.4986476518318171,
+      "grad_norm": 1.6460882425308228,
+      "learning_rate": 9.37202840963834e-05,
+      "loss": 1.1549,
+      "step": 507
+    },
+    {
+      "epoch": 0.49963117777231375,
+      "grad_norm": 1.6016443967819214,
+      "learning_rate": 9.283464100420063e-05,
+      "loss": 1.1433,
+      "step": 508
+    },
+    {
+      "epoch": 0.5006147037128105,
+      "grad_norm": 1.642370581626892,
+      "learning_rate": 9.1951935904469e-05,
+      "loss": 1.0781,
+      "step": 509
+    },
+    {
+      "epoch": 0.5015982296533071,
+      "grad_norm": 1.6989452838897705,
+      "learning_rate": 9.107219299699459e-05,
+      "loss": 1.1015,
+      "step": 510
+    },
+    {
+      "epoch": 0.5025817555938038,
+      "grad_norm": 1.6444441080093384,
+      "learning_rate": 9.019543640037363e-05,
+      "loss": 1.1494,
+      "step": 511
+    },
+    {
+      "epoch": 0.5035652815343005,
+      "grad_norm": 1.650043249130249,
+      "learning_rate": 8.93216901513312e-05,
+      "loss": 1.1497,
+      "step": 512
+    },
+    {
+      "epoch": 0.5045488074747971,
+      "grad_norm": 1.5892958641052246,
+      "learning_rate": 8.845097820406199e-05,
+      "loss": 1.0955,
+      "step": 513
+    },
+    {
+      "epoch": 0.5055323334152938,
+      "grad_norm": 1.606795072555542,
+      "learning_rate": 8.758332442957394e-05,
+      "loss": 1.096,
+      "step": 514
+    },
+    {
+      "epoch": 0.5065158593557905,
+      "grad_norm": 1.6573283672332764,
+      "learning_rate": 8.671875261503348e-05,
+      "loss": 1.1306,
+      "step": 515
+    },
+    {
+      "epoch": 0.5074993852962872,
+      "grad_norm": 1.6091228723526,
+      "learning_rate": 8.585728646311369e-05,
+      "loss": 1.0845,
+      "step": 516
+    },
+    {
+      "epoch": 0.5084829112367839,
+      "grad_norm": 1.6882151365280151,
+      "learning_rate": 8.499894959134436e-05,
+      "loss": 1.1502,
+      "step": 517
+    },
+    {
+      "epoch": 0.5094664371772806,
+      "grad_norm": 1.6060574054718018,
+      "learning_rate": 8.414376553146428e-05,
+      "loss": 1.1295,
+      "step": 518
+    },
+    {
+      "epoch": 0.5104499631177772,
+      "grad_norm": 1.6418123245239258,
+      "learning_rate": 8.329175772877653e-05,
+      "loss": 1.1259,
+      "step": 519
+    },
+    {
+      "epoch": 0.5114334890582739,
+      "grad_norm": 1.6071466207504272,
+      "learning_rate": 8.24429495415054e-05,
+      "loss": 1.1085,
+      "step": 520
+    },
+    {
+      "epoch": 0.5124170149987706,
+      "grad_norm": 1.5179975032806396,
+      "learning_rate": 8.159736424015609e-05,
+      "loss": 1.0485,
+      "step": 521
+    },
+    {
+      "epoch": 0.5134005409392672,
+      "grad_norm": 1.6379435062408447,
+      "learning_rate": 8.075502500687681e-05,
+      "loss": 1.1094,
+      "step": 522
+    },
+    {
+      "epoch": 0.5143840668797639,
+      "grad_norm": 1.6749610900878906,
+      "learning_rate": 7.991595493482323e-05,
+      "loss": 1.0844,
+      "step": 523
+    },
+    {
+      "epoch": 0.5153675928202607,
+      "grad_norm": 1.696667194366455,
+      "learning_rate": 7.908017702752504e-05,
+      "loss": 1.1329,
+      "step": 524
+    },
+    {
+      "epoch": 0.5163511187607573,
+      "grad_norm": 1.619667649269104,
+      "learning_rate": 7.824771419825587e-05,
+      "loss": 1.1005,
+      "step": 525
+    },
+    {
+      "epoch": 0.517334644701254,
+      "grad_norm": 1.891265630722046,
+      "learning_rate": 7.741858926940475e-05,
+      "loss": 1.1328,
+      "step": 526
+    },
+    {
+      "epoch": 0.5183181706417507,
+      "grad_norm": 1.612331509590149,
+      "learning_rate": 7.65928249718503e-05,
+      "loss": 1.1873,
+      "step": 527
+    },
+    {
+      "epoch": 0.5193016965822473,
+      "grad_norm": 1.7046937942504883,
+      "learning_rate": 7.577044394433794e-05,
+      "loss": 1.0657,
+      "step": 528
+    },
+    {
+      "epoch": 0.520285222522744,
+      "grad_norm": 1.6257797479629517,
+      "learning_rate": 7.495146873285903e-05,
+      "loss": 1.1406,
+      "step": 529
+    },
+    {
+      "epoch": 0.5212687484632407,
+      "grad_norm": 1.6082725524902344,
+      "learning_rate": 7.413592179003255e-05,
+      "loss": 1.092,
+      "step": 530
+    },
+    {
+      "epoch": 0.5222522744037374,
+      "grad_norm": 1.638418436050415,
+      "learning_rate": 7.332382547449e-05,
+      "loss": 1.1757,
+      "step": 531
+    },
+    {
+      "epoch": 0.5232358003442341,
+      "grad_norm": 1.6094216108322144,
+      "learning_rate": 7.251520205026205e-05,
+      "loss": 1.1619,
+      "step": 532
+    },
+    {
+      "epoch": 0.5242193262847308,
+      "grad_norm": 1.666649580001831,
+      "learning_rate": 7.171007368616842e-05,
+      "loss": 1.0869,
+      "step": 533
+    },
+    {
+      "epoch": 0.5252028522252274,
+      "grad_norm": 1.6826838254928589,
+      "learning_rate": 7.090846245520986e-05,
+      "loss": 1.1334,
+      "step": 534
+    },
+    {
+      "epoch": 0.5261863781657241,
+      "grad_norm": 1.6268287897109985,
+      "learning_rate": 7.011039033396329e-05,
+      "loss": 1.1287,
+      "step": 535
+    },
+    {
+      "epoch": 0.5271699041062208,
+      "grad_norm": 1.6804072856903076,
+      "learning_rate": 6.93158792019789e-05,
+      "loss": 1.1468,
+      "step": 536
+    },
+    {
+      "epoch": 0.5281534300467174,
+      "grad_norm": 1.6158145666122437,
+      "learning_rate": 6.852495084118083e-05,
+      "loss": 1.0231,
+      "step": 537
+    },
+    {
+      "epoch": 0.5291369559872141,
+      "grad_norm": 1.7181380987167358,
+      "learning_rate": 6.773762693526965e-05,
+      "loss": 1.1221,
+      "step": 538
+    },
+    {
+      "epoch": 0.5301204819277109,
+      "grad_norm": 1.662822961807251,
+      "learning_rate": 6.695392906912786e-05,
+      "loss": 1.1764,
+      "step": 539
+    },
+    {
+      "epoch": 0.5311040078682076,
+      "grad_norm": 1.5750726461410522,
+      "learning_rate": 6.617387872822842e-05,
+      "loss": 1.0695,
+      "step": 540
+    },
+    {
+      "epoch": 0.5320875338087042,
+      "grad_norm": 1.6667808294296265,
+      "learning_rate": 6.539749729804538e-05,
+      "loss": 1.1717,
+      "step": 541
+    },
+    {
+      "epoch": 0.5330710597492009,
+      "grad_norm": 1.6217957735061646,
+      "learning_rate": 6.462480606346788e-05,
+      "loss": 1.0892,
+      "step": 542
+    },
+    {
+      "epoch": 0.5340545856896975,
+      "grad_norm": 1.5805596113204956,
+      "learning_rate": 6.385582620821644e-05,
+      "loss": 1.1495,
+      "step": 543
+    },
+    {
+      "epoch": 0.5350381116301942,
+      "grad_norm": 1.619666576385498,
+      "learning_rate": 6.309057881426226e-05,
+      "loss": 1.1372,
+      "step": 544
+    },
+    {
+      "epoch": 0.5360216375706909,
+      "grad_norm": 1.5543806552886963,
+      "learning_rate": 6.232908486124918e-05,
+      "loss": 1.0527,
+      "step": 545
+    },
+    {
+      "epoch": 0.5370051635111877,
+      "grad_norm": 1.5906850099563599,
+      "learning_rate": 6.157136522591866e-05,
+      "loss": 1.0886,
+      "step": 546
+    },
+    {
+      "epoch": 0.5379886894516843,
+      "grad_norm": 1.7546547651290894,
+      "learning_rate": 6.0817440681537144e-05,
+      "loss": 1.0984,
+      "step": 547
+    },
+    {
+      "epoch": 0.538972215392181,
+      "grad_norm": 1.7061015367507935,
+      "learning_rate": 6.0067331897326895e-05,
+      "loss": 1.0988,
+      "step": 548
+    },
+    {
+      "epoch": 0.5399557413326777,
+      "grad_norm": 1.6275510787963867,
+      "learning_rate": 5.9321059437899254e-05,
+      "loss": 1.0858,
+      "step": 549
+    },
+    {
+      "epoch": 0.5409392672731743,
+      "grad_norm": 1.6035560369491577,
+      "learning_rate": 5.857864376269051e-05,
+      "loss": 1.1456,
+      "step": 550
+    },
+    {
+      "epoch": 0.541922793213671,
+      "grad_norm": 1.6571654081344604,
+      "learning_rate": 5.784010522540151e-05,
+      "loss": 1.1019,
+      "step": 551
+    },
+    {
+      "epoch": 0.5429063191541676,
+      "grad_norm": 1.6013000011444092,
+      "learning_rate": 5.7105464073439375e-05,
+      "loss": 1.1046,
+      "step": 552
+    },
+    {
+      "epoch": 0.5438898450946644,
+      "grad_norm": 1.5961564779281616,
+      "learning_rate": 5.6374740447362264e-05,
+      "loss": 1.1063,
+      "step": 553
+    },
+    {
+      "epoch": 0.5448733710351611,
+      "grad_norm": 1.6290183067321777,
+      "learning_rate": 5.564795438032757e-05,
+      "loss": 1.1154,
+      "step": 554
+    },
+    {
+      "epoch": 0.5458568969756578,
+      "grad_norm": 1.731971263885498,
+      "learning_rate": 5.492512579754252e-05,
+      "loss": 1.1149,
+      "step": 555
+    },
+    {
+      "epoch": 0.5468404229161544,
+      "grad_norm": 1.6082978248596191,
+      "learning_rate": 5.4206274515717736e-05,
+      "loss": 1.1585,
+      "step": 556
+    },
+    {
+      "epoch": 0.5478239488566511,
+      "grad_norm": 1.618871808052063,
+      "learning_rate": 5.349142024252427e-05,
+      "loss": 1.048,
+      "step": 557
+    },
+    {
+      "epoch": 0.5488074747971478,
+      "grad_norm": 1.626085638999939,
+      "learning_rate": 5.278058257605314e-05,
+      "loss": 1.1256,
+      "step": 558
+    },
+    {
+      "epoch": 0.5497910007376444,
+      "grad_norm": 1.5993646383285522,
+      "learning_rate": 5.207378100427804e-05,
+      "loss": 1.0744,
+      "step": 559
+    },
+    {
+      "epoch": 0.5507745266781411,
+      "grad_norm": 1.6538002490997314,
+      "learning_rate": 5.1371034904521134e-05,
+      "loss": 1.103,
+      "step": 560
+    },
+    {
+      "epoch": 0.5517580526186379,
+      "grad_norm": 1.6243610382080078,
+      "learning_rate": 5.067236354292175e-05,
+      "loss": 1.0917,
+      "step": 561
+    },
+    {
+      "epoch": 0.5527415785591345,
+      "grad_norm": 1.570988416671753,
+      "learning_rate": 4.9977786073908086e-05,
+      "loss": 1.1085,
+      "step": 562
+    },
+    {
+      "epoch": 0.5537251044996312,
+      "grad_norm": 1.603846788406372,
+      "learning_rate": 4.928732153967246e-05,
+      "loss": 1.1432,
+      "step": 563
+    },
+    {
+      "epoch": 0.5547086304401279,
+      "grad_norm": 1.584790825843811,
+      "learning_rate": 4.8600988869648745e-05,
+      "loss": 1.0537,
+      "step": 564
+    },
+    {
+      "epoch": 0.5556921563806245,
+      "grad_norm": 1.5726522207260132,
+      "learning_rate": 4.7918806879993814e-05,
+      "loss": 1.0789,
+      "step": 565
+    },
+    {
+      "epoch": 0.5566756823211212,
+      "grad_norm": 1.608412504196167,
+      "learning_rate": 4.724079427307162e-05,
+      "loss": 1.1146,
+      "step": 566
+    },
+    {
+      "epoch": 0.5576592082616179,
+      "grad_norm": 1.5979876518249512,
+      "learning_rate": 4.656696963694012e-05,
+      "loss": 1.0771,
+      "step": 567
+    },
+    {
+      "epoch": 0.5586427342021146,
+      "grad_norm": 1.5700702667236328,
+      "learning_rate": 4.589735144484217e-05,
+      "loss": 1.0369,
+      "step": 568
+    },
+    {
+      "epoch": 0.5596262601426113,
+      "grad_norm": 1.6290395259857178,
+      "learning_rate": 4.5231958054698774e-05,
+      "loss": 1.1129,
+      "step": 569
+    },
+    {
+      "epoch": 0.560609786083108,
+      "grad_norm": 1.664450764656067,
+      "learning_rate": 4.4570807708605825e-05,
+      "loss": 1.0261,
+      "step": 570
+    },
+    {
+      "epoch": 0.5615933120236046,
+      "grad_norm": 1.5685371160507202,
+      "learning_rate": 4.391391853233404e-05,
+      "loss": 1.1199,
+      "step": 571
+    },
+    {
+      "epoch": 0.5625768379641013,
+      "grad_norm": 1.6812089681625366,
+      "learning_rate": 4.326130853483206e-05,
+      "loss": 1.0344,
+      "step": 572
+    },
+    {
+      "epoch": 0.563560363904598,
+      "grad_norm": 1.622582197189331,
+      "learning_rate": 4.261299560773255e-05,
+      "loss": 1.061,
+      "step": 573
+    },
+    {
+      "epoch": 0.5645438898450946,
+      "grad_norm": 1.660653829574585,
+      "learning_rate": 4.196899752486192e-05,
+      "loss": 1.1085,
+      "step": 574
+    },
+    {
+      "epoch": 0.5655274157855913,
+      "grad_norm": 1.6321308612823486,
+      "learning_rate": 4.132933194175299e-05,
+      "loss": 1.0944,
+      "step": 575
+    },
+    {
+      "epoch": 0.5665109417260881,
+      "grad_norm": 1.6691020727157593,
+      "learning_rate": 4.069401639516075e-05,
+      "loss": 1.1395,
+      "step": 576
+    },
+    {
+      "epoch": 0.5674944676665847,
+      "grad_norm": 1.5686017274856567,
+      "learning_rate": 4.0063068302581885e-05,
+      "loss": 1.0362,
+      "step": 577
+    },
+    {
+      "epoch": 0.5684779936070814,
+      "grad_norm": 1.6180577278137207,
+      "learning_rate": 3.943650496177713e-05,
+      "loss": 1.0636,
+      "step": 578
+    },
+    {
+      "epoch": 0.5694615195475781,
+      "grad_norm": 1.5809311866760254,
+      "learning_rate": 3.881434355029687e-05,
+      "loss": 1.0899,
+      "step": 579
+    },
+    {
+      "epoch": 0.5704450454880747,
+      "grad_norm": 1.5602284669876099,
+      "learning_rate": 3.819660112501053e-05,
+      "loss": 1.0964,
+      "step": 580
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 1.555755376815796,
+      "learning_rate": 3.758329462163874e-05,
+      "loss": 1.1217,
+      "step": 581
+    },
+    {
+      "epoch": 0.5724120973690681,
+      "grad_norm": 1.6677347421646118,
+      "learning_rate": 3.697444085428914e-05,
+      "loss": 1.1332,
+      "step": 582
+    },
+    {
+      "epoch": 0.5733956233095648,
+      "grad_norm": 1.6057909727096558,
+      "learning_rate": 3.637005651499528e-05,
+      "loss": 1.0566,
+      "step": 583
+    },
+    {
+      "epoch": 0.5743791492500615,
+      "grad_norm": 1.5967357158660889,
+      "learning_rate": 3.57701581732592e-05,
+      "loss": 1.1161,
+      "step": 584
+    },
+    {
+      "epoch": 0.5753626751905582,
+      "grad_norm": 1.6041682958602905,
+      "learning_rate": 3.5174762275596864e-05,
+      "loss": 1.1068,
+      "step": 585
+    },
+    {
+      "epoch": 0.5763462011310548,
+      "grad_norm": 1.5802150964736938,
+      "learning_rate": 3.4583885145087615e-05,
+      "loss": 1.0469,
+      "step": 586
+    },
+    {
+      "epoch": 0.5773297270715515,
+      "grad_norm": 1.57747483253479,
+      "learning_rate": 3.3997542980926524e-05,
+      "loss": 1.0733,
+      "step": 587
+    },
+    {
+      "epoch": 0.5783132530120482,
+      "grad_norm": 1.5697864294052124,
+      "learning_rate": 3.3415751857980115e-05,
+      "loss": 1.0767,
+      "step": 588
+    },
+    {
+      "epoch": 0.5792967789525448,
+      "grad_norm": 1.550041675567627,
+      "learning_rate": 3.2838527726345993e-05,
+      "loss": 1.063,
+      "step": 589
+    },
+    {
+      "epoch": 0.5802803048930415,
+      "grad_norm": 1.5676511526107788,
+      "learning_rate": 3.226588641091521e-05,
+      "loss": 1.0693,
+      "step": 590
+    },
+    {
+      "epoch": 0.5812638308335383,
+      "grad_norm": 1.578323245048523,
+      "learning_rate": 3.1697843610938794e-05,
+      "loss": 1.0403,
+      "step": 591
+    },
+    {
+      "epoch": 0.5822473567740349,
+      "grad_norm": 1.607877492904663,
+      "learning_rate": 3.113441489959703e-05,
+      "loss": 1.0868,
+      "step": 592
+    },
+    {
+      "epoch": 0.5832308827145316,
+      "grad_norm": 1.5824037790298462,
+      "learning_rate": 3.057561572357262e-05,
+      "loss": 1.1237,
+      "step": 593
+    },
+    {
+      "epoch": 0.5842144086550283,
+      "grad_norm": 1.5974537134170532,
+      "learning_rate": 3.002146140262725e-05,
+      "loss": 1.1145,
+      "step": 594
+    },
+    {
+      "epoch": 0.5851979345955249,
+      "grad_norm": 1.5872732400894165,
+      "learning_rate": 2.9471967129181565e-05,
+      "loss": 0.9714,
+      "step": 595
+    },
+    {
+      "epoch": 0.5861814605360216,
+      "grad_norm": 1.597594976425171,
+      "learning_rate": 2.8927147967898682e-05,
+      "loss": 1.0821,
+      "step": 596
+    },
+    {
+      "epoch": 0.5871649864765183,
+      "grad_norm": 1.6081088781356812,
+      "learning_rate": 2.8387018855271085e-05,
+      "loss": 1.0513,
+      "step": 597
+    },
+    {
+      "epoch": 0.588148512417015,
+      "grad_norm": 1.5636123418807983,
+      "learning_rate": 2.7851594599211293e-05,
+      "loss": 1.0317,
+      "step": 598
+    },
+    {
+      "epoch": 0.5891320383575117,
+      "grad_norm": 1.5617702007293701,
+      "learning_rate": 2.732088987864567e-05,
+      "loss": 1.0692,
+      "step": 599
+    },
+    {
+      "epoch": 0.5901155642980084,
+      "grad_norm": 1.6476192474365234,
+      "learning_rate": 2.679491924311226e-05,
+      "loss": 1.1095,
+      "step": 600
+    },
+    {
+      "epoch": 0.591099090238505,
+      "grad_norm": 1.5220457315444946,
+      "learning_rate": 2.6273697112361784e-05,
+      "loss": 1.083,
+      "step": 601
+    },
+    {
+      "epoch": 0.5920826161790017,
+      "grad_norm": 1.5808863639831543,
+      "learning_rate": 2.575723777596213e-05,
+      "loss": 1.1458,
+      "step": 602
+    },
+    {
+      "epoch": 0.5930661421194984,
+      "grad_norm": 1.5608521699905396,
+      "learning_rate": 2.524555539290696e-05,
+      "loss": 1.049,
+      "step": 603
+    },
+    {
+      "epoch": 0.594049668059995,
+      "grad_norm": 1.6394426822662354,
+      "learning_rate": 2.473866399122733e-05,
+      "loss": 1.0653,
+      "step": 604
+    },
+    {
+      "epoch": 0.5950331940004918,
+      "grad_norm": 1.7107138633728027,
+      "learning_rate": 2.4236577467606946e-05,
+      "loss": 1.1567,
+      "step": 605
+    },
+    {
+      "epoch": 0.5960167199409885,
+      "grad_norm": 1.5471723079681396,
+      "learning_rate": 2.3739309587001567e-05,
+      "loss": 1.0468,
+      "step": 606
+    },
+    {
+      "epoch": 0.5970002458814851,
+      "grad_norm": 1.5568169355392456,
+      "learning_rate": 2.324687398226131e-05,
+      "loss": 1.0912,
+      "step": 607
+    },
+    {
+      "epoch": 0.5979837718219818,
+      "grad_norm": 1.602166771888733,
+      "learning_rate": 2.2759284153757053e-05,
+      "loss": 1.1232,
+      "step": 608
+    },
+    {
+      "epoch": 0.5989672977624785,
+      "grad_norm": 1.6254791021347046,
+      "learning_rate": 2.2276553469010208e-05,
+      "loss": 1.0962,
+      "step": 609
+    },
+    {
+      "epoch": 0.5999508237029751,
+      "grad_norm": 1.5922654867172241,
+      "learning_rate": 2.1798695162326442e-05,
+      "loss": 1.0786,
+      "step": 610
+    },
+    {
+      "epoch": 0.6009343496434718,
+      "grad_norm": 1.5703258514404297,
+      "learning_rate": 2.1325722334432485e-05,
+      "loss": 1.0496,
+      "step": 611
+    },
+    {
+      "epoch": 0.6019178755839685,
+      "grad_norm": 1.5971964597702026,
+      "learning_rate": 2.085764795211742e-05,
+      "loss": 1.0631,
+      "step": 612
+    },
+    {
+      "epoch": 0.6029014015244653,
+      "grad_norm": 1.6196777820587158,
+      "learning_rate": 2.0394484847876892e-05,
+      "loss": 1.1323,
+      "step": 613
+    },
+    {
+      "epoch": 0.6038849274649619,
+      "grad_norm": 1.5888458490371704,
+      "learning_rate": 1.9936245719561296e-05,
+      "loss": 1.0985,
+      "step": 614
+    },
+    {
+      "epoch": 0.6048684534054586,
+      "grad_norm": 1.6777266263961792,
+      "learning_rate": 1.948294313002792e-05,
+      "loss": 1.1057,
+      "step": 615
+    },
+    {
+      "epoch": 0.6058519793459552,
+      "grad_norm": 1.5191071033477783,
+      "learning_rate": 1.903458950679613e-05,
+      "loss": 1.0123,
+      "step": 616
+    },
+    {
+      "epoch": 0.6068355052864519,
+      "grad_norm": 1.5552016496658325,
+      "learning_rate": 1.8591197141707027e-05,
+      "loss": 1.0797,
+      "step": 617
+    },
+    {
+      "epoch": 0.6078190312269486,
+      "grad_norm": 1.5961596965789795,
+      "learning_rate": 1.8152778190586296e-05,
+      "loss": 1.1184,
+      "step": 618
+    },
+    {
+      "epoch": 0.6088025571674452,
+      "grad_norm": 1.5839762687683105,
+      "learning_rate": 1.771934467291094e-05,
+      "loss": 1.1104,
+      "step": 619
+    },
+    {
+      "epoch": 0.609786083107942,
+      "grad_norm": 1.589618444442749,
+      "learning_rate": 1.7290908471479805e-05,
+      "loss": 1.1358,
+      "step": 620
+    },
+    {
+      "epoch": 0.6107696090484387,
+      "grad_norm": 1.6342886686325073,
+      "learning_rate": 1.6867481332087797e-05,
+      "loss": 1.0282,
+      "step": 621
+    },
+    {
+      "epoch": 0.6117531349889354,
+      "grad_norm": 1.5776050090789795,
+      "learning_rate": 1.6449074863203772e-05,
+      "loss": 1.0728,
+      "step": 622
+    },
+    {
+      "epoch": 0.612736660929432,
+      "grad_norm": 1.6011443138122559,
+      "learning_rate": 1.6035700535652465e-05,
+      "loss": 1.1404,
+      "step": 623
+    },
+    {
+      "epoch": 0.6137201868699287,
+      "grad_norm": 1.5918643474578857,
+      "learning_rate": 1.562736968229992e-05,
+      "loss": 1.0628,
+      "step": 624
+    },
+    {
+      "epoch": 0.6147037128104254,
+      "grad_norm": 1.5177937746047974,
+      "learning_rate": 1.5224093497742653e-05,
+      "loss": 1.0399,
+      "step": 625
+    },
+    {
+      "epoch": 0.615687238750922,
+      "grad_norm": 1.622794508934021,
+      "learning_rate": 1.4825883038001054e-05,
+      "loss": 1.1013,
+      "step": 626
+    },
+    {
+      "epoch": 0.6166707646914187,
+      "grad_norm": 1.5753284692764282,
+      "learning_rate": 1.4432749220216024e-05,
+      "loss": 1.071,
+      "step": 627
+    },
+    {
+      "epoch": 0.6176542906319155,
+      "grad_norm": 1.6217107772827148,
+      "learning_rate": 1.4044702822349731e-05,
+      "loss": 1.0002,
+      "step": 628
+    },
+    {
+      "epoch": 0.6186378165724121,
+      "grad_norm": 1.5546847581863403,
+      "learning_rate": 1.3661754482890222e-05,
+      "loss": 1.0251,
+      "step": 629
+    },
+    {
+      "epoch": 0.6196213425129088,
+      "grad_norm": 1.6065832376480103,
+      "learning_rate": 1.3283914700559675e-05,
+      "loss": 1.1277,
+      "step": 630
+    },
+    {
+      "epoch": 0.6206048684534055,
+      "grad_norm": 1.582098364830017,
+      "learning_rate": 1.2911193834026546e-05,
+      "loss": 1.0606,
+      "step": 631
+    },
+    {
+      "epoch": 0.6215883943939021,
+      "grad_norm": 1.5727086067199707,
+      "learning_rate": 1.2543602101621709e-05,
+      "loss": 1.0722,
+      "step": 632
+    },
+    {
+      "epoch": 0.6225719203343988,
+      "grad_norm": 1.5591822862625122,
+      "learning_rate": 1.2181149581058181e-05,
+      "loss": 1.0718,
+      "step": 633
+    },
+    {
+      "epoch": 0.6235554462748955,
+      "grad_norm": 1.5548235177993774,
+      "learning_rate": 1.182384620915491e-05,
+      "loss": 1.0455,
+      "step": 634
+    },
+    {
+      "epoch": 0.6245389722153922,
+      "grad_norm": 1.5538259744644165,
+      "learning_rate": 1.1471701781564314e-05,
+      "loss": 1.0569,
+      "step": 635
+    },
+    {
+      "epoch": 0.6255224981558889,
+      "grad_norm": 1.5374336242675781,
+      "learning_rate": 1.1124725952503801e-05,
+      "loss": 1.0752,
+      "step": 636
+    },
+    {
+      "epoch": 0.6265060240963856,
+      "grad_norm": 1.590369462966919,
+      "learning_rate": 1.078292823449094e-05,
+      "loss": 1.0142,
+      "step": 637
+    },
+    {
+      "epoch": 0.6274895500368822,
+      "grad_norm": 1.5979132652282715,
+      "learning_rate": 1.0446317998082888e-05,
+      "loss": 1.072,
+      "step": 638
+    },
+    {
+      "epoch": 0.6284730759773789,
+      "grad_norm": 1.5855075120925903,
+      "learning_rate": 1.0114904471619247e-05,
+      "loss": 1.0809,
+      "step": 639
+    },
+    {
+      "epoch": 0.6294566019178756,
+      "grad_norm": 1.6333812475204468,
+      "learning_rate": 9.788696740969295e-06,
+      "loss": 1.1021,
+      "step": 640
+    },
+    {
+      "epoch": 0.6304401278583722,
+      "grad_norm": 1.646070957183838,
+      "learning_rate": 9.467703749282764e-06,
+      "loss": 1.0921,
+      "step": 641
+    },
+    {
+      "epoch": 0.631423653798869,
+      "grad_norm": 1.5639617443084717,
+      "learning_rate": 9.151934296744635e-06,
+      "loss": 1.052,
+      "step": 642
+    },
+    {
+      "epoch": 0.6324071797393657,
+      "grad_norm": 1.6541653871536255,
+      "learning_rate": 8.841397040333976e-06,
+      "loss": 1.0609,
+      "step": 643
+    },
+    {
+      "epoch": 0.6333907056798623,
+      "grad_norm": 1.5831325054168701,
+      "learning_rate": 8.536100493586552e-06,
+      "loss": 1.1326,
+      "step": 644
+    },
+    {
+      "epoch": 0.634374231620359,
+      "grad_norm": 1.496453046798706,
+      "learning_rate": 8.23605302636139e-06,
+      "loss": 1.0269,
+      "step": 645
+    },
+    {
+      "epoch": 0.6353577575608557,
+      "grad_norm": 1.6001390218734741,
+      "learning_rate": 7.941262864611387e-06,
+      "loss": 1.0708,
+      "step": 646
+    },
+    {
+      "epoch": 0.6363412835013523,
+      "grad_norm": 1.6304258108139038,
+      "learning_rate": 7.651738090157733e-06,
+      "loss": 1.0645,
+      "step": 647
+    },
+    {
+      "epoch": 0.637324809441849,
+      "grad_norm": 1.5697929859161377,
+      "learning_rate": 7.36748664046838e-06,
+      "loss": 1.0812,
+      "step": 648
+    },
+    {
+      "epoch": 0.6383083353823457,
+      "grad_norm": 1.6335376501083374,
+      "learning_rate": 7.0885163084403846e-06,
+      "loss": 1.0871,
+      "step": 649
+    },
+    {
+      "epoch": 0.6392918613228424,
+      "grad_norm": 1.6851428747177124,
+      "learning_rate": 6.81483474218636e-06,
+      "loss": 1.066,
+      "step": 650
+    },
+    {
+      "epoch": 0.6402753872633391,
+      "grad_norm": 1.5803459882736206,
+      "learning_rate": 6.546449444824654e-06,
+      "loss": 1.0518,
+      "step": 651
+    },
+    {
+      "epoch": 0.6412589132038358,
+      "grad_norm": 1.6332086324691772,
+      "learning_rate": 6.283367774273785e-06,
+      "loss": 1.0243,
+      "step": 652
+    },
+    {
+      "epoch": 0.6422424391443324,
+      "grad_norm": 1.5875962972640991,
+      "learning_rate": 6.025596943050648e-06,
+      "loss": 1.0768,
+      "step": 653
+    },
+    {
+      "epoch": 0.6432259650848291,
+      "grad_norm": 1.648381233215332,
+      "learning_rate": 5.773144018072807e-06,
+      "loss": 1.1158,
+      "step": 654
+    },
+    {
+      "epoch": 0.6442094910253258,
+      "grad_norm": 1.6049330234527588,
+      "learning_rate": 5.5260159204646885e-06,
+      "loss": 1.1665,
+      "step": 655
+    },
+    {
+      "epoch": 0.6451930169658224,
+      "grad_norm": 1.5462381839752197,
+      "learning_rate": 5.2842194253679424e-06,
+      "loss": 1.0788,
+      "step": 656
+    },
+    {
+      "epoch": 0.6461765429063192,
+      "grad_norm": 1.664047122001648,
+      "learning_rate": 5.0477611617556485e-06,
+      "loss": 1.156,
+      "step": 657
+    },
+    {
+      "epoch": 0.6471600688468159,
+      "grad_norm": 1.7467290163040161,
+      "learning_rate": 4.8166476122505135e-06,
+      "loss": 1.1192,
+      "step": 658
+    },
+    {
+      "epoch": 0.6481435947873125,
+      "grad_norm": 1.7353417873382568,
+      "learning_rate": 4.590885112947274e-06,
+      "loss": 1.0867,
+      "step": 659
+    },
+    {
+      "epoch": 0.6491271207278092,
+      "grad_norm": 1.587186336517334,
+      "learning_rate": 4.370479853238863e-06,
+      "loss": 1.055,
+      "step": 660
+    },
+    {
+      "epoch": 0.6501106466683059,
+      "grad_norm": 1.553141474723816,
+      "learning_rate": 4.155437875646829e-06,
+      "loss": 1.0706,
+      "step": 661
+    },
+    {
+      "epoch": 0.6510941726088025,
+      "grad_norm": 1.5985965728759766,
+      "learning_rate": 3.945765075655649e-06,
+      "loss": 1.0794,
+      "step": 662
+    },
+    {
+      "epoch": 0.6520776985492992,
+      "grad_norm": 1.505215048789978,
+      "learning_rate": 3.7414672015509746e-06,
+      "loss": 1.0067,
+      "step": 663
+    },
+    {
+      "epoch": 0.6530612244897959,
+      "grad_norm": 1.575181484222412,
+      "learning_rate": 3.542549854262278e-06,
+      "loss": 1.0166,
+      "step": 664
+    },
+    {
+      "epoch": 0.6540447504302926,
+      "grad_norm": 1.6103475093841553,
+      "learning_rate": 3.349018487209099e-06,
+      "loss": 1.1203,
+      "step": 665
+    },
+    {
+      "epoch": 0.6550282763707893,
+      "grad_norm": 1.6004595756530762,
+      "learning_rate": 3.160878406151624e-06,
+      "loss": 1.0892,
+      "step": 666
+    },
+    {
+      "epoch": 0.656011802311286,
+      "grad_norm": 1.5086390972137451,
+      "learning_rate": 2.9781347690452266e-06,
+      "loss": 1.051,
+      "step": 667
+    },
+    {
+      "epoch": 0.6569953282517826,
+      "grad_norm": 1.570785403251648,
+      "learning_rate": 2.800792585899026e-06,
+      "loss": 0.9648,
+      "step": 668
+    },
+    {
+      "epoch": 0.6579788541922793,
+      "grad_norm": 1.54836905002594,
+      "learning_rate": 2.6288567186385505e-06,
+      "loss": 1.0549,
+      "step": 669
+    },
+    {
+      "epoch": 0.658962380132776,
+      "grad_norm": 1.660688042640686,
+      "learning_rate": 2.462331880972468e-06,
+      "loss": 1.0269,
+      "step": 670
+    },
+    {
+      "epoch": 0.6599459060732726,
+      "grad_norm": 1.5790220499038696,
+      "learning_rate": 2.3012226382632894e-06,
+      "loss": 1.0473,
+      "step": 671
+    },
+    {
+      "epoch": 0.6609294320137694,
+      "grad_norm": 1.6120561361312866,
+      "learning_rate": 2.1455334074023337e-06,
+      "loss": 1.1179,
+      "step": 672
+    },
+    {
+      "epoch": 0.6619129579542661,
+      "grad_norm": 1.5404844284057617,
+      "learning_rate": 1.9952684566884926e-06,
+      "loss": 1.0333,
+      "step": 673
+    },
+    {
+      "epoch": 0.6628964838947627,
+      "grad_norm": 1.5952411890029907,
+      "learning_rate": 1.8504319057112806e-06,
+      "loss": 1.0023,
+      "step": 674
+    },
+    {
+      "epoch": 0.6638800098352594,
+      "grad_norm": 1.549829363822937,
+      "learning_rate": 1.7110277252379236e-06,
+      "loss": 1.0127,
+      "step": 675
+    },
+    {
+      "epoch": 0.6648635357757561,
+      "grad_norm": 1.5770440101623535,
+      "learning_rate": 1.577059737104447e-06,
+      "loss": 1.0096,
+      "step": 676
+    },
+    {
+      "epoch": 0.6658470617162527,
+      "grad_norm": 1.625446081161499,
+      "learning_rate": 1.4485316141108928e-06,
+      "loss": 1.0445,
+      "step": 677
+    },
+    {
+      "epoch": 0.6668305876567494,
+      "grad_norm": 1.6090573072433472,
+      "learning_rate": 1.325446879920711e-06,
+      "loss": 1.0989,
+      "step": 678
+    },
+    {
+      "epoch": 0.6678141135972461,
+      "grad_norm": 1.5554827451705933,
+      "learning_rate": 1.2078089089640809e-06,
+      "loss": 1.022,
+      "step": 679
+    },
+    {
+      "epoch": 0.6687976395377428,
+      "grad_norm": 1.5727711915969849,
+      "learning_rate": 1.0956209263453421e-06,
+      "loss": 1.0687,
+      "step": 680
+    },
+    {
+      "epoch": 0.6697811654782395,
+      "grad_norm": 1.590895175933838,
+      "learning_rate": 9.888860077547524e-07,
+      "loss": 1.1218,
+      "step": 681
+    },
+    {
+      "epoch": 0.6707646914187362,
+      "grad_norm": 1.6273709535598755,
+      "learning_rate": 8.876070793840008e-07,
+      "loss": 1.0526,
+      "step": 682
+    },
+    {
+      "epoch": 0.6717482173592328,
+      "grad_norm": 1.5715453624725342,
+      "learning_rate": 7.917869178460934e-07,
+      "loss": 1.0828,
+      "step": 683
+    },
+    {
+      "epoch": 0.6727317432997295,
+      "grad_norm": 1.5626118183135986,
+      "learning_rate": 7.01428150099126e-07,
+      "loss": 1.1077,
+      "step": 684
+    },
+    {
+      "epoch": 0.6737152692402262,
+      "grad_norm": 1.5551321506500244,
+      "learning_rate": 6.165332533744073e-07,
+      "loss": 1.0527,
+      "step": 685
+    },
+    {
+      "epoch": 0.6746987951807228,
+      "grad_norm": 1.6907010078430176,
+      "learning_rate": 5.371045551083808e-07,
+      "loss": 1.0607,
+      "step": 686
+    },
+    {
+      "epoch": 0.6756823211212196,
+      "grad_norm": 1.5568333864212036,
+      "learning_rate": 4.631442328789426e-07,
+      "loss": 0.9964,
+      "step": 687
+    },
+    {
+      "epoch": 0.6766658470617163,
+      "grad_norm": 1.6289827823638916,
+      "learning_rate": 3.946543143456882e-07,
+      "loss": 1.0931,
+      "step": 688
+    },
+    {
+      "epoch": 0.677649373002213,
+      "grad_norm": 1.5730174779891968,
+      "learning_rate": 3.3163667719433576e-07,
+      "loss": 1.0916,
+      "step": 689
+    },
+    {
+      "epoch": 0.6786328989427096,
+      "grad_norm": 1.5842548608779907,
+      "learning_rate": 2.7409304908523336e-07,
+      "loss": 1.051,
+      "step": 690
+    },
+    {
+      "epoch": 0.6796164248832063,
+      "grad_norm": 1.617651343345642,
+      "learning_rate": 2.220250076060193e-07,
+      "loss": 1.0332,
+      "step": 691
+    },
+    {
+      "epoch": 0.680599950823703,
+      "grad_norm": 1.6278129816055298,
+      "learning_rate": 1.7543398022832336e-07,
+      "loss": 1.1475,
+      "step": 692
+    },
+    {
+      "epoch": 0.6815834767641996,
+      "grad_norm": 1.5694608688354492,
+      "learning_rate": 1.343212442687536e-07,
+      "loss": 1.0138,
+      "step": 693
+    },
+    {
+      "epoch": 0.6825670027046964,
+      "grad_norm": 1.5981290340423584,
+      "learning_rate": 9.868792685368e-08,
+      "loss": 0.9832,
+      "step": 694
+    },
+    {
+      "epoch": 0.6835505286451931,
+      "grad_norm": 1.5327750444412231,
+      "learning_rate": 6.853500488854803e-08,
+      "loss": 1.0314,
+      "step": 695
+    },
+    {
+      "epoch": 0.6845340545856897,
+      "grad_norm": 1.5427277088165283,
+      "learning_rate": 4.386330503090008e-08,
+      "loss": 1.0459,
+      "step": 696
+    },
+    {
+      "epoch": 0.6855175805261864,
+      "grad_norm": 1.5548511743545532,
+      "learning_rate": 2.4673503667882458e-08,
+      "loss": 1.0574,
+      "step": 697
+    },
+    {
+      "epoch": 0.686501106466683,
+      "grad_norm": 1.5951749086380005,
+      "learning_rate": 1.0966126897571372e-08,
+      "loss": 1.1301,
+      "step": 698
+    },
+    {
+      "epoch": 0.6874846324071797,
+      "grad_norm": 1.5737613439559937,
+      "learning_rate": 2.741550514651081e-09,
+      "loss": 1.0478,
+      "step": 699
+    },
+    {
+      "epoch": 0.6884681583476764,
+      "grad_norm": 1.5692044496536255,
+      "learning_rate": 0.0,
+      "loss": 1.0708,
+      "step": 700
     }
   ],
   "logging_steps": 1,
@@ -3554,12 +4954,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.025530644522598e+16,
+  "total_flos": 8.438718091440947e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null