Training in progress, step 3600, checkpoint

last-checkpoint/optimizer_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b16e67baf5cfceecccbeaca8b58da303eaf73b17a51a7a27d2eeb645c7b1f9e4
+oid sha256:20341a5db0928170548e9d4eb5993cb2e15527b53cbd9d37ae4eefd083dd738f
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df6d15578ce7461a65e3d4573631629600f16341c2e151f5618c1a8e05be12e7
+oid sha256:37d0655a5c6ff373dfb712f627106345ec6d39275d8f6710e47b1e421e5fc12f
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c8d953afc881ab0dd7c35d8bed0bf96b70919c9bc96a27c7970d3d8561f492e
+oid sha256:9bb5d4ff1981eedbfa382a52daaf94f5e4d327c2791ddbba8ce42947f1faed80
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9952a55ee296a52f4b41a79416235ca4e467bfb2d38e406014037f6296cb8bd3
+oid sha256:9948d5b8cf09dcdbdfb9a349a8d0b29905c49a16863a96357c9d2a167d4594b6
 size 13990904

last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f116d69ef453f4a4e9e385b98d7cc4c1269cb0a068b07c53b34efc9aa8a3e06c
+oid sha256:773f63cfbbca499e57a6b1c26f07d1ff64a12064f8efc5697a5c6ec4acc3f9af
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54743e3ec92e6bba23e12a00c6fc7a862a8c703ccec27d001cceac7b972ba11f
+oid sha256:d848ac36c96e3361918d5881a58962bbc9487ac40028bf8166aa8cf052ba2224
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a74fffaefc1e6daba654c4aae129ffa7a374f17ee3470a05b2d2cfc5fb713335
+oid sha256:996552dc812062afe63350faae11d499e4888d07ecd9389eb16dbdd953080b05
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:627d9fd686c5312231b69470a8c938f0b89f58eb7b46a5397cd0de6ae9cfc6db
+oid sha256:e35b965f00c20776496b1a86953ce335b1405f30773e8ad65847507becdffb40
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2959b7d0cc6a73dd7a982a0ebc0dcad24dc8fe4cf1adb63e6422a7b207cbcd36
+oid sha256:8e5808effcdebd7a3be2031acb94a582a6b2acd7fdded70ad918c0e244b5af31
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015d45f86fc1a9d22364b86b52fa480ca21a653f465a66b7d9e373571a4d3052
+oid sha256:6b659774061b4a9fe1771f5b849cb61766eb1e83dff28b336947fdd50ba2c425
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d0b2147472e5ebbb5ec01a3bf49c458cdba6b0342e907e3d15b25d8f1cdf015
+oid sha256:3073e049caa29de490cb95f0c4ff8156a42990acb73fc31545188bb0c56a241c
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eba81b72522c20179f6a9e5bd4eb0fea662f295dd50c509d5cca3ea3ab4da5d
+oid sha256:03a1c9f69774d333fb89fa1471ffc1f35ad85f1122c910027cf7e50924e37c9c
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79d9433244954a0989e91ba334032147c20bc4a07ead6f002c05049b1192b520
+oid sha256:9597d79022068ceebb9509c33370c3e389771e5b77adc2a3470d46a567aa4406
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5164146071560309,
+  "epoch": 0.5311693102176319,
   "eval_steps": 20,
-  "global_step": 3500,
+  "global_step": 3600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -26619,6 +26619,766 @@
       "eval_samples_per_second": 5.902,
       "eval_steps_per_second": 0.203,
       "step": 3500
+    },
+    {
+      "epoch": 0.516562154186647,
+      "grad_norm": 2.469064712524414,
+      "learning_rate": 1.1164055630258155e-05,
+      "loss": 0.1101,
+      "step": 3501
+    },
+    {
+      "epoch": 0.516709701217263,
+      "grad_norm": 1.4656027555465698,
+      "learning_rate": 1.1158939497425881e-05,
+      "loss": 0.037,
+      "step": 3502
+    },
+    {
+      "epoch": 0.516857248247879,
+      "grad_norm": 3.337543249130249,
+      "learning_rate": 1.1153823057094941e-05,
+      "loss": 0.0785,
+      "step": 3503
+    },
+    {
+      "epoch": 0.517004795278495,
+      "grad_norm": 2.9996700286865234,
+      "learning_rate": 1.1148706310622872e-05,
+      "loss": 0.0834,
+      "step": 3504
+    },
+    {
+      "epoch": 0.517152342309111,
+      "grad_norm": 1.8667278289794922,
+      "learning_rate": 1.1143589259367287e-05,
+      "loss": 0.0438,
+      "step": 3505
+    },
+    {
+      "epoch": 0.517299889339727,
+      "grad_norm": 3.0531399250030518,
+      "learning_rate": 1.1138471904685875e-05,
+      "loss": 0.0689,
+      "step": 3506
+    },
+    {
+      "epoch": 0.5174474363703431,
+      "grad_norm": 2.248572587966919,
+      "learning_rate": 1.1133354247936423e-05,
+      "loss": 0.0348,
+      "step": 3507
+    },
+    {
+      "epoch": 0.5175949834009591,
+      "grad_norm": 2.1095054149627686,
+      "learning_rate": 1.1128236290476778e-05,
+      "loss": 0.0305,
+      "step": 3508
+    },
+    {
+      "epoch": 0.517742530431575,
+      "grad_norm": 4.427886009216309,
+      "learning_rate": 1.1123118033664877e-05,
+      "loss": 0.0373,
+      "step": 3509
+    },
+    {
+      "epoch": 0.5178900774621911,
+      "grad_norm": 1.3057057857513428,
+      "learning_rate": 1.1117999478858737e-05,
+      "loss": 0.0132,
+      "step": 3510
+    },
+    {
+      "epoch": 0.5180376244928071,
+      "grad_norm": 3.117243766784668,
+      "learning_rate": 1.1112880627416449e-05,
+      "loss": 0.0896,
+      "step": 3511
+    },
+    {
+      "epoch": 0.5181851715234231,
+      "grad_norm": 1.9899787902832031,
+      "learning_rate": 1.110776148069619e-05,
+      "loss": 0.0578,
+      "step": 3512
+    },
+    {
+      "epoch": 0.5183327185540391,
+      "grad_norm": 8.810548782348633,
+      "learning_rate": 1.1102642040056206e-05,
+      "loss": 0.1897,
+      "step": 3513
+    },
+    {
+      "epoch": 0.5184802655846551,
+      "grad_norm": 1.2062597274780273,
+      "learning_rate": 1.1097522306854831e-05,
+      "loss": 0.0264,
+      "step": 3514
+    },
+    {
+      "epoch": 0.5186278126152711,
+      "grad_norm": 1.4792219400405884,
+      "learning_rate": 1.1092402282450468e-05,
+      "loss": 0.0592,
+      "step": 3515
+    },
+    {
+      "epoch": 0.5187753596458872,
+      "grad_norm": 2.792485475540161,
+      "learning_rate": 1.1087281968201603e-05,
+      "loss": 0.06,
+      "step": 3516
+    },
+    {
+      "epoch": 0.5189229066765031,
+      "grad_norm": 2.4529595375061035,
+      "learning_rate": 1.1082161365466797e-05,
+      "loss": 0.0824,
+      "step": 3517
+    },
+    {
+      "epoch": 0.5190704537071191,
+      "grad_norm": 3.275951623916626,
+      "learning_rate": 1.1077040475604684e-05,
+      "loss": 0.0914,
+      "step": 3518
+    },
+    {
+      "epoch": 0.5192180007377352,
+      "grad_norm": 1.783270001411438,
+      "learning_rate": 1.107191929997398e-05,
+      "loss": 0.0651,
+      "step": 3519
+    },
+    {
+      "epoch": 0.5193655477683512,
+      "grad_norm": 2.4270193576812744,
+      "learning_rate": 1.1066797839933473e-05,
+      "loss": 0.1079,
+      "step": 3520
+    },
+    {
+      "epoch": 0.5193655477683512,
+      "eval_accuracy": 0.975397973950796,
+      "eval_f1": 0.9580246913580247,
+      "eval_loss": 0.05977718532085419,
+      "eval_precision": 0.9748743718592965,
+      "eval_recall": 0.941747572815534,
+      "eval_runtime": 50.4104,
+      "eval_samples_per_second": 5.773,
+      "eval_steps_per_second": 0.198,
+      "step": 3520
+    },
+    {
+      "epoch": 0.5195130947989671,
+      "grad_norm": 3.448223829269409,
+      "learning_rate": 1.1061676096842033e-05,
+      "loss": 0.067,
+      "step": 3521
+    },
+    {
+      "epoch": 0.5196606418295832,
+      "grad_norm": 3.3494110107421875,
+      "learning_rate": 1.1056554072058596e-05,
+      "loss": 0.0937,
+      "step": 3522
+    },
+    {
+      "epoch": 0.5198081888601992,
+      "grad_norm": 2.503899097442627,
+      "learning_rate": 1.1051431766942176e-05,
+      "loss": 0.0774,
+      "step": 3523
+    },
+    {
+      "epoch": 0.5199557358908152,
+      "grad_norm": 5.1114821434021,
+      "learning_rate": 1.1046309182851863e-05,
+      "loss": 0.0394,
+      "step": 3524
+    },
+    {
+      "epoch": 0.5201032829214312,
+      "grad_norm": 1.1896251440048218,
+      "learning_rate": 1.1041186321146818e-05,
+      "loss": 0.0321,
+      "step": 3525
+    },
+    {
+      "epoch": 0.5202508299520472,
+      "grad_norm": 1.3631348609924316,
+      "learning_rate": 1.103606318318628e-05,
+      "loss": 0.048,
+      "step": 3526
+    },
+    {
+      "epoch": 0.5203983769826632,
+      "grad_norm": 1.6505790948867798,
+      "learning_rate": 1.1030939770329557e-05,
+      "loss": 0.0526,
+      "step": 3527
+    },
+    {
+      "epoch": 0.5205459240132793,
+      "grad_norm": 1.5522688627243042,
+      "learning_rate": 1.1025816083936036e-05,
+      "loss": 0.0587,
+      "step": 3528
+    },
+    {
+      "epoch": 0.5206934710438953,
+      "grad_norm": 3.606168270111084,
+      "learning_rate": 1.1020692125365171e-05,
+      "loss": 0.1196,
+      "step": 3529
+    },
+    {
+      "epoch": 0.5208410180745112,
+      "grad_norm": 2.4806244373321533,
+      "learning_rate": 1.1015567895976486e-05,
+      "loss": 0.0705,
+      "step": 3530
+    },
+    {
+      "epoch": 0.5209885651051273,
+      "grad_norm": 1.4611976146697998,
+      "learning_rate": 1.1010443397129584e-05,
+      "loss": 0.0367,
+      "step": 3531
+    },
+    {
+      "epoch": 0.5211361121357433,
+      "grad_norm": 2.171333074569702,
+      "learning_rate": 1.100531863018414e-05,
+      "loss": 0.0199,
+      "step": 3532
+    },
+    {
+      "epoch": 0.5212836591663593,
+      "grad_norm": 1.693715214729309,
+      "learning_rate": 1.1000193596499886e-05,
+      "loss": 0.0364,
+      "step": 3533
+    },
+    {
+      "epoch": 0.5214312061969752,
+      "grad_norm": 2.185756206512451,
+      "learning_rate": 1.0995068297436643e-05,
+      "loss": 0.0883,
+      "step": 3534
+    },
+    {
+      "epoch": 0.5215787532275913,
+      "grad_norm": 5.272037982940674,
+      "learning_rate": 1.098994273435429e-05,
+      "loss": 0.0791,
+      "step": 3535
+    },
+    {
+      "epoch": 0.5217263002582073,
+      "grad_norm": 3.4218335151672363,
+      "learning_rate": 1.0984816908612787e-05,
+      "loss": 0.0471,
+      "step": 3536
+    },
+    {
+      "epoch": 0.5218738472888234,
+      "grad_norm": 2.2550787925720215,
+      "learning_rate": 1.097969082157215e-05,
+      "loss": 0.0442,
+      "step": 3537
+    },
+    {
+      "epoch": 0.5220213943194393,
+      "grad_norm": 4.873686790466309,
+      "learning_rate": 1.0974564474592475e-05,
+      "loss": 0.071,
+      "step": 3538
+    },
+    {
+      "epoch": 0.5221689413500553,
+      "grad_norm": 2.3027725219726562,
+      "learning_rate": 1.0969437869033923e-05,
+      "loss": 0.0323,
+      "step": 3539
+    },
+    {
+      "epoch": 0.5223164883806714,
+      "grad_norm": 1.5242536067962646,
+      "learning_rate": 1.0964311006256725e-05,
+      "loss": 0.0547,
+      "step": 3540
+    },
+    {
+      "epoch": 0.5223164883806714,
+      "eval_accuracy": 0.9739507959479016,
+      "eval_f1": 0.9558823529411765,
+      "eval_loss": 0.057289425283670425,
+      "eval_precision": 0.9653465346534653,
+      "eval_recall": 0.9466019417475728,
+      "eval_runtime": 49.7325,
+      "eval_samples_per_second": 5.851,
+      "eval_steps_per_second": 0.201,
+      "step": 3540
+    },
+    {
+      "epoch": 0.5224640354112874,
+      "grad_norm": 1.0918387174606323,
+      "learning_rate": 1.0959183887621177e-05,
+      "loss": 0.0143,
+      "step": 3541
+    },
+    {
+      "epoch": 0.5226115824419033,
+      "grad_norm": 2.3980836868286133,
+      "learning_rate": 1.0954056514487645e-05,
+      "loss": 0.061,
+      "step": 3542
+    },
+    {
+      "epoch": 0.5227591294725193,
+      "grad_norm": 4.099221706390381,
+      "learning_rate": 1.094892888821657e-05,
+      "loss": 0.0662,
+      "step": 3543
+    },
+    {
+      "epoch": 0.5229066765031354,
+      "grad_norm": 3.6991629600524902,
+      "learning_rate": 1.094380101016844e-05,
+      "loss": 0.111,
+      "step": 3544
+    },
+    {
+      "epoch": 0.5230542235337514,
+      "grad_norm": 2.514206886291504,
+      "learning_rate": 1.0938672881703833e-05,
+      "loss": 0.0417,
+      "step": 3545
+    },
+    {
+      "epoch": 0.5232017705643673,
+      "grad_norm": 2.7861063480377197,
+      "learning_rate": 1.093354450418338e-05,
+      "loss": 0.0457,
+      "step": 3546
+    },
+    {
+      "epoch": 0.5233493175949834,
+      "grad_norm": 2.9248032569885254,
+      "learning_rate": 1.0928415878967781e-05,
+      "loss": 0.0946,
+      "step": 3547
+    },
+    {
+      "epoch": 0.5234968646255994,
+      "grad_norm": 1.7036411762237549,
+      "learning_rate": 1.0923287007417802e-05,
+      "loss": 0.0275,
+      "step": 3548
+    },
+    {
+      "epoch": 0.5236444116562154,
+      "grad_norm": 1.976135492324829,
+      "learning_rate": 1.0918157890894274e-05,
+      "loss": 0.0384,
+      "step": 3549
+    },
+    {
+      "epoch": 0.5237919586868315,
+      "grad_norm": 2.986879587173462,
+      "learning_rate": 1.0913028530758096e-05,
+      "loss": 0.0647,
+      "step": 3550
+    },
+    {
+      "epoch": 0.5239395057174474,
+      "grad_norm": 4.570195198059082,
+      "learning_rate": 1.0907898928370222e-05,
+      "loss": 0.1014,
+      "step": 3551
+    },
+    {
+      "epoch": 0.5240870527480634,
+      "grad_norm": 2.2751247882843018,
+      "learning_rate": 1.0902769085091687e-05,
+      "loss": 0.0924,
+      "step": 3552
+    },
+    {
+      "epoch": 0.5242345997786795,
+      "grad_norm": 1.7858340740203857,
+      "learning_rate": 1.089763900228357e-05,
+      "loss": 0.0527,
+      "step": 3553
+    },
+    {
+      "epoch": 0.5243821468092955,
+      "grad_norm": 1.6592340469360352,
+      "learning_rate": 1.0892508681307032e-05,
+      "loss": 0.0619,
+      "step": 3554
+    },
+    {
+      "epoch": 0.5245296938399114,
+      "grad_norm": 2.0850613117218018,
+      "learning_rate": 1.0887378123523287e-05,
+      "loss": 0.0467,
+      "step": 3555
+    },
+    {
+      "epoch": 0.5246772408705275,
+      "grad_norm": 4.593194961547852,
+      "learning_rate": 1.0882247330293607e-05,
+      "loss": 0.0592,
+      "step": 3556
+    },
+    {
+      "epoch": 0.5248247879011435,
+      "grad_norm": 3.315997838973999,
+      "learning_rate": 1.0877116302979345e-05,
+      "loss": 0.0922,
+      "step": 3557
+    },
+    {
+      "epoch": 0.5249723349317595,
+      "grad_norm": 2.3332576751708984,
+      "learning_rate": 1.0871985042941893e-05,
+      "loss": 0.0618,
+      "step": 3558
+    },
+    {
+      "epoch": 0.5251198819623755,
+      "grad_norm": 5.566976547241211,
+      "learning_rate": 1.0866853551542723e-05,
+      "loss": 0.1125,
+      "step": 3559
+    },
+    {
+      "epoch": 0.5252674289929915,
+      "grad_norm": 1.3656704425811768,
+      "learning_rate": 1.086172183014336e-05,
+      "loss": 0.0204,
+      "step": 3560
+    },
+    {
+      "epoch": 0.5252674289929915,
+      "eval_accuracy": 0.975397973950796,
+      "eval_f1": 0.9582309582309583,
+      "eval_loss": 0.05937637761235237,
+      "eval_precision": 0.9701492537313433,
+      "eval_recall": 0.9466019417475728,
+      "eval_runtime": 50.7983,
+      "eval_samples_per_second": 5.729,
+      "eval_steps_per_second": 0.197,
+      "step": 3560
+    },
+    {
+      "epoch": 0.5254149760236075,
+      "grad_norm": 1.3643617630004883,
+      "learning_rate": 1.0856589880105388e-05,
+      "loss": 0.0296,
+      "step": 3561
+    },
+    {
+      "epoch": 0.5255625230542236,
+      "grad_norm": 1.5215461254119873,
+      "learning_rate": 1.085145770279046e-05,
+      "loss": 0.0296,
+      "step": 3562
+    },
+    {
+      "epoch": 0.5257100700848395,
+      "grad_norm": 2.7468132972717285,
+      "learning_rate": 1.0846325299560278e-05,
+      "loss": 0.0865,
+      "step": 3563
+    },
+    {
+      "epoch": 0.5258576171154555,
+      "grad_norm": 2.774982452392578,
+      "learning_rate": 1.0841192671776621e-05,
+      "loss": 0.0902,
+      "step": 3564
+    },
+    {
+      "epoch": 0.5260051641460716,
+      "grad_norm": 2.7266316413879395,
+      "learning_rate": 1.0836059820801305e-05,
+      "loss": 0.1313,
+      "step": 3565
+    },
+    {
+      "epoch": 0.5261527111766876,
+      "grad_norm": 1.377890706062317,
+      "learning_rate": 1.0830926747996225e-05,
+      "loss": 0.0301,
+      "step": 3566
+    },
+    {
+      "epoch": 0.5263002582073035,
+      "grad_norm": 1.1492201089859009,
+      "learning_rate": 1.0825793454723325e-05,
+      "loss": 0.0336,
+      "step": 3567
+    },
+    {
+      "epoch": 0.5264478052379196,
+      "grad_norm": 2.800081968307495,
+      "learning_rate": 1.0820659942344609e-05,
+      "loss": 0.0639,
+      "step": 3568
+    },
+    {
+      "epoch": 0.5265953522685356,
+      "grad_norm": 1.6292766332626343,
+      "learning_rate": 1.0815526212222141e-05,
+      "loss": 0.0731,
+      "step": 3569
+    },
+    {
+      "epoch": 0.5267428992991516,
+      "grad_norm": 1.7465286254882812,
+      "learning_rate": 1.0810392265718034e-05,
+      "loss": 0.0214,
+      "step": 3570
+    },
+    {
+      "epoch": 0.5268904463297676,
+      "grad_norm": 4.0834197998046875,
+      "learning_rate": 1.080525810419448e-05,
+      "loss": 0.0991,
+      "step": 3571
+    },
+    {
+      "epoch": 0.5270379933603836,
+      "grad_norm": 1.60231614112854,
+      "learning_rate": 1.0800123729013703e-05,
+      "loss": 0.0668,
+      "step": 3572
+    },
+    {
+      "epoch": 0.5271855403909996,
+      "grad_norm": 2.3066658973693848,
+      "learning_rate": 1.0794989141537997e-05,
+      "loss": 0.1016,
+      "step": 3573
+    },
+    {
+      "epoch": 0.5273330874216157,
+      "grad_norm": 1.236547589302063,
+      "learning_rate": 1.078985434312971e-05,
+      "loss": 0.0292,
+      "step": 3574
+    },
+    {
+      "epoch": 0.5274806344522317,
+      "grad_norm": 1.3361313343048096,
+      "learning_rate": 1.0784719335151248e-05,
+      "loss": 0.0466,
+      "step": 3575
+    },
+    {
+      "epoch": 0.5276281814828476,
+      "grad_norm": 1.3268588781356812,
+      "learning_rate": 1.0779584118965068e-05,
+      "loss": 0.0321,
+      "step": 3576
+    },
+    {
+      "epoch": 0.5277757285134637,
+      "grad_norm": 1.567400336265564,
+      "learning_rate": 1.0774448695933683e-05,
+      "loss": 0.0688,
+      "step": 3577
+    },
+    {
+      "epoch": 0.5279232755440797,
+      "grad_norm": 2.6386070251464844,
+      "learning_rate": 1.0769313067419666e-05,
+      "loss": 0.016,
+      "step": 3578
+    },
+    {
+      "epoch": 0.5280708225746957,
+      "grad_norm": 2.8470680713653564,
+      "learning_rate": 1.0764177234785644e-05,
+      "loss": 0.0581,
+      "step": 3579
+    },
+    {
+      "epoch": 0.5282183696053117,
+      "grad_norm": 1.7170813083648682,
+      "learning_rate": 1.0759041199394289e-05,
+      "loss": 0.0595,
+      "step": 3580
+    },
+    {
+      "epoch": 0.5282183696053117,
+      "eval_accuracy": 0.975397973950796,
+      "eval_f1": 0.9578163771712159,
+      "eval_loss": 0.06021639332175255,
+      "eval_precision": 0.9796954314720813,
+      "eval_recall": 0.9368932038834952,
+      "eval_runtime": 49.6835,
+      "eval_samples_per_second": 5.857,
+      "eval_steps_per_second": 0.201,
+      "step": 3580
+    },
+    {
+      "epoch": 0.5283659166359277,
+      "grad_norm": 3.634925127029419,
+      "learning_rate": 1.0753904962608334e-05,
+      "loss": 0.0781,
+      "step": 3581
+    },
+    {
+      "epoch": 0.5285134636665437,
+      "grad_norm": 0.9435338973999023,
+      "learning_rate": 1.074876852579057e-05,
+      "loss": 0.0271,
+      "step": 3582
+    },
+    {
+      "epoch": 0.5286610106971598,
+      "grad_norm": 0.8338215351104736,
+      "learning_rate": 1.074363189030383e-05,
+      "loss": 0.0165,
+      "step": 3583
+    },
+    {
+      "epoch": 0.5288085577277757,
+      "grad_norm": 0.8123714923858643,
+      "learning_rate": 1.0738495057511003e-05,
+      "loss": 0.0207,
+      "step": 3584
+    },
+    {
+      "epoch": 0.5289561047583917,
+      "grad_norm": 3.053124189376831,
+      "learning_rate": 1.073335802877504e-05,
+      "loss": 0.0471,
+      "step": 3585
+    },
+    {
+      "epoch": 0.5291036517890078,
+      "grad_norm": 1.5023503303527832,
+      "learning_rate": 1.0728220805458935e-05,
+      "loss": 0.052,
+      "step": 3586
+    },
+    {
+      "epoch": 0.5292511988196238,
+      "grad_norm": 3.0605030059814453,
+      "learning_rate": 1.0723083388925731e-05,
+      "loss": 0.0758,
+      "step": 3587
+    },
+    {
+      "epoch": 0.5293987458502397,
+      "grad_norm": 4.905116558074951,
+      "learning_rate": 1.0717945780538527e-05,
+      "loss": 0.2057,
+      "step": 3588
+    },
+    {
+      "epoch": 0.5295462928808558,
+      "grad_norm": 2.5521600246429443,
+      "learning_rate": 1.0712807981660478e-05,
+      "loss": 0.0507,
+      "step": 3589
+    },
+    {
+      "epoch": 0.5296938399114718,
+      "grad_norm": 1.739632248878479,
+      "learning_rate": 1.0707669993654778e-05,
+      "loss": 0.0502,
+      "step": 3590
+    },
+    {
+      "epoch": 0.5298413869420878,
+      "grad_norm": 2.5149118900299072,
+      "learning_rate": 1.0702531817884681e-05,
+      "loss": 0.0704,
+      "step": 3591
+    },
+    {
+      "epoch": 0.5299889339727037,
+      "grad_norm": 2.5621867179870605,
+      "learning_rate": 1.0697393455713483e-05,
+      "loss": 0.0577,
+      "step": 3592
+    },
+    {
+      "epoch": 0.5301364810033198,
+      "grad_norm": 2.1689069271087646,
+      "learning_rate": 1.0692254908504542e-05,
+      "loss": 0.0489,
+      "step": 3593
+    },
+    {
+      "epoch": 0.5302840280339358,
+      "grad_norm": 1.0757484436035156,
+      "learning_rate": 1.0687116177621244e-05,
+      "loss": 0.0278,
+      "step": 3594
+    },
+    {
+      "epoch": 0.5304315750645519,
+      "grad_norm": 1.871010422706604,
+      "learning_rate": 1.0681977264427046e-05,
+      "loss": 0.0642,
+      "step": 3595
+    },
+    {
+      "epoch": 0.5305791220951679,
+      "grad_norm": 2.093369483947754,
+      "learning_rate": 1.067683817028544e-05,
+      "loss": 0.0527,
+      "step": 3596
+    },
+    {
+      "epoch": 0.5307266691257838,
+      "grad_norm": 2.046318769454956,
+      "learning_rate": 1.0671698896559968e-05,
+      "loss": 0.0725,
+      "step": 3597
+    },
+    {
+      "epoch": 0.5308742161563998,
+      "grad_norm": 2.6404740810394287,
+      "learning_rate": 1.0666559444614225e-05,
+      "loss": 0.0556,
+      "step": 3598
+    },
+    {
+      "epoch": 0.5310217631870159,
+      "grad_norm": 2.6905758380889893,
+      "learning_rate": 1.0661419815811846e-05,
+      "loss": 0.0428,
+      "step": 3599
+    },
+    {
+      "epoch": 0.5311693102176319,
+      "grad_norm": 5.128182411193848,
+      "learning_rate": 1.0656280011516523e-05,
+      "loss": 0.0574,
+      "step": 3600
+    },
+    {
+      "epoch": 0.5311693102176319,
+      "eval_accuracy": 0.9710564399421129,
+      "eval_f1": 0.9512195121951219,
+      "eval_loss": 0.06035442277789116,
+      "eval_precision": 0.9558823529411765,
+      "eval_recall": 0.9466019417475728,
+      "eval_runtime": 50.258,
+      "eval_samples_per_second": 5.79,
+      "eval_steps_per_second": 0.199,
+      "step": 3600
     }
   ],
   "logging_steps": 1,
@@ -26638,7 +27398,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0784648068658627e+18,
+  "total_flos": 1.1091422408962212e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null