Training in progress, step 800, checkpoint

last-checkpoint/optimizer_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47369349058d9f265a07a2c0ef08b67452bffc5187fd4c745c4bac94546a6fe1
+oid sha256:c4366e69d60737b3779bf9a490440dab3b7129f75dd2feb73dc07db72babfbdf
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d50510b0f730cb5c824594a257dc78d9cd0f0f324db4149d578f71b4f5f6b523
+oid sha256:c6dd1a92d0a5135b333dcb0ee27f4083935df79d3cdbd2e1782a276fcaa9d154
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5c62ca5412596eb2cd44f1d5b0431527944d399ca97f86771a01c08e2bcdef8
+oid sha256:4835991b793120481b099eb89774026995ab06f7469520e242d29572c729356e
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0436864f261cedc81f4c1934c7762f1c640c553dea76637d2c3365a5862998bb
+oid sha256:cc58fcb266dccc572788bea6fad1f9f18f3c730bcccdaac874c4e3525aa012f7
 size 13990904

last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d9ef70e9be95016e13a78937658f66404e8ede47727af102e7f241f7cf7ad77
+oid sha256:10960d9381443ad0dcee2d617e86555e9074adf42f10ea5b5031e4d17e4541fc
 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:ed14a8743524674aa130aa11171caec211afebea652849304a313fa02bc1e7b4
+oid sha256:40b617e3c4555dd60638eed9d7607d51addbf2e88c7e24d50cc4af0a97e2c1ee
 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:fea02b7b1ee15158d6e0a23d9860f1c01ae8d91c79e2f7e42f8a04e7ef88ad41
+oid sha256:3aca6570204ebce4c6f1f377b28739749ab7e2db8774a4ae79b88318ecc645d3
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9623875cc6f8148d10a3ff5e872de2c2987ad9473b4a6a560df1d8ef4e01a0f6
+oid sha256:af486d9702ac04f9288a8d7f8d269fc56995d192739a371cdc0ab84562d444ee
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb98a3c24bcf7750fa7750f116a6d10d5ccebb8daba33a53a7f270b36b2ce893
+oid sha256:6651bb14848ddc09834acedbc497fa211b2b3bf1fd839c0a3e2edc297b450478
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9898bf1f7135405f4bbf1fe87622d1d22a7516940bda0af13d0cb131fe2777fc
+oid sha256:ae03e0e09af0ed507e28016716e1ab7cf741033f725d1d5e7ab0b16606ee820f
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:407914c8984b50d2b06804e7b77fcfba533e794950feb19c63755a81cb2e26bb
+oid sha256:38f2cc82eeba75672cf489909ffeec57c804049b636096ef6ef25670940386a2
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3ea4cc6c9042fb168359b86795e303250effc227e0d4527d836efe07f4521a6
+oid sha256:e86dc8922a03fbd7dae55bdea9fe0c57d7c92e7e4db833cf223eab9d601f3f59
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7b231cefd198a0bea4e7101f5c354fb7215e43b749b513c26e32fa2c6c06e95
+oid sha256:0693986dcdbacb610348452117526a26c1a6fb2feb944c0d12e677a07f1eaf73
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4736129905277402,
+  "epoch": 0.5412719891745602,
   "eval_steps": 20,
-  "global_step": 700,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5339,6 +5339,766 @@
       "eval_samples_per_second": 5.626,
       "eval_steps_per_second": 0.189,
       "step": 700
+    },
+    {
+      "epoch": 0.4742895805142084,
+      "grad_norm": 3.1701228618621826,
+      "learning_rate": 1.26147994095382e-05,
+      "loss": 0.1402,
+      "step": 701
+    },
+    {
+      "epoch": 0.4749661705006766,
+      "grad_norm": 3.6727280616760254,
+      "learning_rate": 1.2591992938930808e-05,
+      "loss": 0.1482,
+      "step": 702
+    },
+    {
+      "epoch": 0.47564276048714477,
+      "grad_norm": 2.606227159500122,
+      "learning_rate": 1.2569172006266192e-05,
+      "loss": 0.141,
+      "step": 703
+    },
+    {
+      "epoch": 0.476319350473613,
+      "grad_norm": 3.620513677597046,
+      "learning_rate": 1.2546336738874037e-05,
+      "loss": 0.1777,
+      "step": 704
+    },
+    {
+      "epoch": 0.4769959404600812,
+      "grad_norm": 4.079351902008057,
+      "learning_rate": 1.2523487264163997e-05,
+      "loss": 0.1614,
+      "step": 705
+    },
+    {
+      "epoch": 0.4776725304465494,
+      "grad_norm": 3.8010270595550537,
+      "learning_rate": 1.2500623709625008e-05,
+      "loss": 0.1359,
+      "step": 706
+    },
+    {
+      "epoch": 0.4783491204330176,
+      "grad_norm": 3.370544672012329,
+      "learning_rate": 1.2477746202824563e-05,
+      "loss": 0.1554,
+      "step": 707
+    },
+    {
+      "epoch": 0.4790257104194858,
+      "grad_norm": 5.698882579803467,
+      "learning_rate": 1.2454854871407993e-05,
+      "loss": 0.1387,
+      "step": 708
+    },
+    {
+      "epoch": 0.479702300405954,
+      "grad_norm": 3.655916213989258,
+      "learning_rate": 1.2431949843097776e-05,
+      "loss": 0.0942,
+      "step": 709
+    },
+    {
+      "epoch": 0.4803788903924222,
+      "grad_norm": 4.965806484222412,
+      "learning_rate": 1.2409031245692798e-05,
+      "loss": 0.1671,
+      "step": 710
+    },
+    {
+      "epoch": 0.4810554803788904,
+      "grad_norm": 4.127477645874023,
+      "learning_rate": 1.238609920706767e-05,
+      "loss": 0.1012,
+      "step": 711
+    },
+    {
+      "epoch": 0.4817320703653586,
+      "grad_norm": 4.219476222991943,
+      "learning_rate": 1.2363153855171985e-05,
+      "loss": 0.1406,
+      "step": 712
+    },
+    {
+      "epoch": 0.4824086603518268,
+      "grad_norm": 4.781118392944336,
+      "learning_rate": 1.2340195318029623e-05,
+      "loss": 0.1519,
+      "step": 713
+    },
+    {
+      "epoch": 0.48308525033829497,
+      "grad_norm": 2.8674471378326416,
+      "learning_rate": 1.2317223723738036e-05,
+      "loss": 0.0691,
+      "step": 714
+    },
+    {
+      "epoch": 0.4837618403247632,
+      "grad_norm": 3.4862661361694336,
+      "learning_rate": 1.2294239200467516e-05,
+      "loss": 0.1282,
+      "step": 715
+    },
+    {
+      "epoch": 0.4844384303112314,
+      "grad_norm": 2.642241954803467,
+      "learning_rate": 1.2271241876460507e-05,
+      "loss": 0.1144,
+      "step": 716
+    },
+    {
+      "epoch": 0.4851150202976996,
+      "grad_norm": 5.012102127075195,
+      "learning_rate": 1.2248231880030861e-05,
+      "loss": 0.1781,
+      "step": 717
+    },
+    {
+      "epoch": 0.4857916102841678,
+      "grad_norm": 3.223320484161377,
+      "learning_rate": 1.2225209339563144e-05,
+      "loss": 0.103,
+      "step": 718
+    },
+    {
+      "epoch": 0.486468200270636,
+      "grad_norm": 3.7974560260772705,
+      "learning_rate": 1.2202174383511916e-05,
+      "loss": 0.1277,
+      "step": 719
+    },
+    {
+      "epoch": 0.4871447902571042,
+      "grad_norm": 8.01950454711914,
+      "learning_rate": 1.2179127140400997e-05,
+      "loss": 0.2256,
+      "step": 720
+    },
+    {
+      "epoch": 0.4871447902571042,
+      "eval_accuracy": 0.7798165137614679,
+      "eval_f1": 0.375,
+      "eval_loss": 0.49802127480506897,
+      "eval_precision": 0.8372093023255814,
+      "eval_recall": 0.24161073825503357,
+      "eval_runtime": 52.7234,
+      "eval_samples_per_second": 5.652,
+      "eval_steps_per_second": 0.19,
+      "step": 720
+    },
+    {
+      "epoch": 0.4878213802435724,
+      "grad_norm": 5.34826135635376,
+      "learning_rate": 1.2156067738822777e-05,
+      "loss": 0.173,
+      "step": 721
+    },
+    {
+      "epoch": 0.4884979702300406,
+      "grad_norm": 2.6310982704162598,
+      "learning_rate": 1.213299630743747e-05,
+      "loss": 0.0958,
+      "step": 722
+    },
+    {
+      "epoch": 0.4891745602165088,
+      "grad_norm": 4.56181526184082,
+      "learning_rate": 1.2109912974972424e-05,
+      "loss": 0.1279,
+      "step": 723
+    },
+    {
+      "epoch": 0.489851150202977,
+      "grad_norm": 5.082941055297852,
+      "learning_rate": 1.2086817870221376e-05,
+      "loss": 0.158,
+      "step": 724
+    },
+    {
+      "epoch": 0.49052774018944517,
+      "grad_norm": 6.134848117828369,
+      "learning_rate": 1.2063711122043759e-05,
+      "loss": 0.1063,
+      "step": 725
+    },
+    {
+      "epoch": 0.4912043301759134,
+      "grad_norm": 3.6247506141662598,
+      "learning_rate": 1.204059285936397e-05,
+      "loss": 0.1078,
+      "step": 726
+    },
+    {
+      "epoch": 0.4918809201623816,
+      "grad_norm": 4.745319366455078,
+      "learning_rate": 1.2017463211170635e-05,
+      "loss": 0.1094,
+      "step": 727
+    },
+    {
+      "epoch": 0.4925575101488498,
+      "grad_norm": 5.845713138580322,
+      "learning_rate": 1.1994322306515926e-05,
+      "loss": 0.1373,
+      "step": 728
+    },
+    {
+      "epoch": 0.493234100135318,
+      "grad_norm": 3.4521119594573975,
+      "learning_rate": 1.1971170274514802e-05,
+      "loss": 0.0997,
+      "step": 729
+    },
+    {
+      "epoch": 0.4939106901217862,
+      "grad_norm": 4.090993404388428,
+      "learning_rate": 1.1948007244344334e-05,
+      "loss": 0.1578,
+      "step": 730
+    },
+    {
+      "epoch": 0.4945872801082544,
+      "grad_norm": 5.571890830993652,
+      "learning_rate": 1.1924833345242921e-05,
+      "loss": 0.1614,
+      "step": 731
+    },
+    {
+      "epoch": 0.4952638700947226,
+      "grad_norm": 4.286579132080078,
+      "learning_rate": 1.1901648706509637e-05,
+      "loss": 0.1557,
+      "step": 732
+    },
+    {
+      "epoch": 0.4959404600811908,
+      "grad_norm": 6.809506893157959,
+      "learning_rate": 1.1878453457503465e-05,
+      "loss": 0.1479,
+      "step": 733
+    },
+    {
+      "epoch": 0.496617050067659,
+      "grad_norm": 3.8739116191864014,
+      "learning_rate": 1.185524772764258e-05,
+      "loss": 0.1504,
+      "step": 734
+    },
+    {
+      "epoch": 0.4972936400541272,
+      "grad_norm": 3.7848074436187744,
+      "learning_rate": 1.1832031646403654e-05,
+      "loss": 0.1236,
+      "step": 735
+    },
+    {
+      "epoch": 0.4979702300405954,
+      "grad_norm": 4.305004596710205,
+      "learning_rate": 1.1808805343321102e-05,
+      "loss": 0.1505,
+      "step": 736
+    },
+    {
+      "epoch": 0.4986468200270636,
+      "grad_norm": 3.052428722381592,
+      "learning_rate": 1.1785568947986368e-05,
+      "loss": 0.1454,
+      "step": 737
+    },
+    {
+      "epoch": 0.4993234100135318,
+      "grad_norm": 7.71512508392334,
+      "learning_rate": 1.176232259004722e-05,
+      "loss": 0.2538,
+      "step": 738
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 5.634016990661621,
+      "learning_rate": 1.1739066399206997e-05,
+      "loss": 0.1768,
+      "step": 739
+    },
+    {
+      "epoch": 0.5006765899864682,
+      "grad_norm": 4.39807653427124,
+      "learning_rate": 1.1715800505223918e-05,
+      "loss": 0.2035,
+      "step": 740
+    },
+    {
+      "epoch": 0.5006765899864682,
+      "eval_accuracy": 0.7871559633027523,
+      "eval_f1": 0.40816326530612246,
+      "eval_loss": 0.4451703131198883,
+      "eval_precision": 0.851063829787234,
+      "eval_recall": 0.2684563758389262,
+      "eval_runtime": 53.0418,
+      "eval_samples_per_second": 5.618,
+      "eval_steps_per_second": 0.189,
+      "step": 740
+    },
+    {
+      "epoch": 0.5013531799729364,
+      "grad_norm": 4.298307418823242,
+      "learning_rate": 1.1692525037910325e-05,
+      "loss": 0.155,
+      "step": 741
+    },
+    {
+      "epoch": 0.5020297699594046,
+      "grad_norm": 3.8376667499542236,
+      "learning_rate": 1.166924012713198e-05,
+      "loss": 0.1715,
+      "step": 742
+    },
+    {
+      "epoch": 0.5027063599458728,
+      "grad_norm": 4.111176013946533,
+      "learning_rate": 1.164594590280734e-05,
+      "loss": 0.139,
+      "step": 743
+    },
+    {
+      "epoch": 0.503382949932341,
+      "grad_norm": 3.5634899139404297,
+      "learning_rate": 1.1622642494906819e-05,
+      "loss": 0.1315,
+      "step": 744
+    },
+    {
+      "epoch": 0.5040595399188093,
+      "grad_norm": 3.7423675060272217,
+      "learning_rate": 1.1599330033452078e-05,
+      "loss": 0.1789,
+      "step": 745
+    },
+    {
+      "epoch": 0.5047361299052774,
+      "grad_norm": 7.1124958992004395,
+      "learning_rate": 1.1576008648515286e-05,
+      "loss": 0.1674,
+      "step": 746
+    },
+    {
+      "epoch": 0.5054127198917456,
+      "grad_norm": 3.564636468887329,
+      "learning_rate": 1.1552678470218406e-05,
+      "loss": 0.1415,
+      "step": 747
+    },
+    {
+      "epoch": 0.5060893098782138,
+      "grad_norm": 7.098050117492676,
+      "learning_rate": 1.1529339628732462e-05,
+      "loss": 0.1789,
+      "step": 748
+    },
+    {
+      "epoch": 0.506765899864682,
+      "grad_norm": 7.915879726409912,
+      "learning_rate": 1.1505992254276808e-05,
+      "loss": 0.184,
+      "step": 749
+    },
+    {
+      "epoch": 0.5074424898511503,
+      "grad_norm": 3.962040424346924,
+      "learning_rate": 1.148263647711842e-05,
+      "loss": 0.1447,
+      "step": 750
+    },
+    {
+      "epoch": 0.5081190798376184,
+      "grad_norm": 2.833312749862671,
+      "learning_rate": 1.1459272427571148e-05,
+      "loss": 0.1153,
+      "step": 751
+    },
+    {
+      "epoch": 0.5087956698240866,
+      "grad_norm": 3.094414234161377,
+      "learning_rate": 1.1435900235995004e-05,
+      "loss": 0.1555,
+      "step": 752
+    },
+    {
+      "epoch": 0.5094722598105548,
+      "grad_norm": 3.7343735694885254,
+      "learning_rate": 1.141252003279542e-05,
+      "loss": 0.1781,
+      "step": 753
+    },
+    {
+      "epoch": 0.510148849797023,
+      "grad_norm": 2.3985371589660645,
+      "learning_rate": 1.1389131948422534e-05,
+      "loss": 0.1266,
+      "step": 754
+    },
+    {
+      "epoch": 0.5108254397834912,
+      "grad_norm": 2.8854312896728516,
+      "learning_rate": 1.1365736113370463e-05,
+      "loss": 0.1198,
+      "step": 755
+    },
+    {
+      "epoch": 0.5115020297699594,
+      "grad_norm": 3.6787984371185303,
+      "learning_rate": 1.1342332658176556e-05,
+      "loss": 0.1701,
+      "step": 756
+    },
+    {
+      "epoch": 0.5121786197564276,
+      "grad_norm": 3.9833555221557617,
+      "learning_rate": 1.1318921713420691e-05,
+      "loss": 0.1883,
+      "step": 757
+    },
+    {
+      "epoch": 0.5128552097428958,
+      "grad_norm": 5.8127031326293945,
+      "learning_rate": 1.1295503409724526e-05,
+      "loss": 0.19,
+      "step": 758
+    },
+    {
+      "epoch": 0.513531799729364,
+      "grad_norm": 3.7036736011505127,
+      "learning_rate": 1.1272077877750782e-05,
+      "loss": 0.1532,
+      "step": 759
+    },
+    {
+      "epoch": 0.5142083897158322,
+      "grad_norm": 3.996150255203247,
+      "learning_rate": 1.124864524820251e-05,
+      "loss": 0.1412,
+      "step": 760
+    },
+    {
+      "epoch": 0.5142083897158322,
+      "eval_accuracy": 0.7761467889908257,
+      "eval_f1": 0.34408602150537637,
+      "eval_loss": 0.4691689610481262,
+      "eval_precision": 0.8648648648648649,
+      "eval_recall": 0.21476510067114093,
+      "eval_runtime": 52.6721,
+      "eval_samples_per_second": 5.658,
+      "eval_steps_per_second": 0.19,
+      "step": 760
+    },
+    {
+      "epoch": 0.5148849797023004,
+      "grad_norm": 6.409296989440918,
+      "learning_rate": 1.1225205651822359e-05,
+      "loss": 0.264,
+      "step": 761
+    },
+    {
+      "epoch": 0.5155615696887687,
+      "grad_norm": 3.7257473468780518,
+      "learning_rate": 1.1201759219391858e-05,
+      "loss": 0.1302,
+      "step": 762
+    },
+    {
+      "epoch": 0.5162381596752368,
+      "grad_norm": 2.880531072616577,
+      "learning_rate": 1.1178306081730666e-05,
+      "loss": 0.1321,
+      "step": 763
+    },
+    {
+      "epoch": 0.516914749661705,
+      "grad_norm": 3.284871816635132,
+      "learning_rate": 1.1154846369695864e-05,
+      "loss": 0.1171,
+      "step": 764
+    },
+    {
+      "epoch": 0.5175913396481732,
+      "grad_norm": 3.0467426776885986,
+      "learning_rate": 1.1131380214181205e-05,
+      "loss": 0.1664,
+      "step": 765
+    },
+    {
+      "epoch": 0.5182679296346414,
+      "grad_norm": 4.38018274307251,
+      "learning_rate": 1.1107907746116402e-05,
+      "loss": 0.167,
+      "step": 766
+    },
+    {
+      "epoch": 0.5189445196211097,
+      "grad_norm": 2.9475748538970947,
+      "learning_rate": 1.108442909646639e-05,
+      "loss": 0.1161,
+      "step": 767
+    },
+    {
+      "epoch": 0.5196211096075778,
+      "grad_norm": 5.2659687995910645,
+      "learning_rate": 1.1060944396230583e-05,
+      "loss": 0.1163,
+      "step": 768
+    },
+    {
+      "epoch": 0.520297699594046,
+      "grad_norm": 3.119966983795166,
+      "learning_rate": 1.1037453776442164e-05,
+      "loss": 0.1693,
+      "step": 769
+    },
+    {
+      "epoch": 0.5209742895805142,
+      "grad_norm": 3.546898603439331,
+      "learning_rate": 1.1013957368167343e-05,
+      "loss": 0.1362,
+      "step": 770
+    },
+    {
+      "epoch": 0.5216508795669824,
+      "grad_norm": 3.2547402381896973,
+      "learning_rate": 1.099045530250463e-05,
+      "loss": 0.1175,
+      "step": 771
+    },
+    {
+      "epoch": 0.5223274695534507,
+      "grad_norm": 2.995699882507324,
+      "learning_rate": 1.0966947710584086e-05,
+      "loss": 0.1131,
+      "step": 772
+    },
+    {
+      "epoch": 0.5230040595399188,
+      "grad_norm": 2.557124614715576,
+      "learning_rate": 1.0943434723566624e-05,
+      "loss": 0.139,
+      "step": 773
+    },
+    {
+      "epoch": 0.523680649526387,
+      "grad_norm": 3.192425489425659,
+      "learning_rate": 1.091991647264325e-05,
+      "loss": 0.1644,
+      "step": 774
+    },
+    {
+      "epoch": 0.5243572395128552,
+      "grad_norm": 5.2245025634765625,
+      "learning_rate": 1.0896393089034336e-05,
+      "loss": 0.1449,
+      "step": 775
+    },
+    {
+      "epoch": 0.5250338294993234,
+      "grad_norm": 3.094622850418091,
+      "learning_rate": 1.0872864703988903e-05,
+      "loss": 0.1066,
+      "step": 776
+    },
+    {
+      "epoch": 0.5257104194857916,
+      "grad_norm": 2.3677878379821777,
+      "learning_rate": 1.0849331448783869e-05,
+      "loss": 0.1244,
+      "step": 777
+    },
+    {
+      "epoch": 0.5263870094722598,
+      "grad_norm": 5.578123569488525,
+      "learning_rate": 1.0825793454723325e-05,
+      "loss": 0.1779,
+      "step": 778
+    },
+    {
+      "epoch": 0.527063599458728,
+      "grad_norm": 5.073922157287598,
+      "learning_rate": 1.0802250853137808e-05,
+      "loss": 0.2355,
+      "step": 779
+    },
+    {
+      "epoch": 0.5277401894451962,
+      "grad_norm": 2.925035238265991,
+      "learning_rate": 1.0778703775383559e-05,
+      "loss": 0.1346,
+      "step": 780
+    },
+    {
+      "epoch": 0.5277401894451962,
+      "eval_accuracy": 0.8119266055045872,
+      "eval_f1": 0.5287356321839081,
+      "eval_loss": 0.40138694643974304,
+      "eval_precision": 0.8394160583941606,
+      "eval_recall": 0.3859060402684564,
+      "eval_runtime": 52.7212,
+      "eval_samples_per_second": 5.652,
+      "eval_steps_per_second": 0.19,
+      "step": 780
+    },
+    {
+      "epoch": 0.5284167794316644,
+      "grad_norm": 4.117710113525391,
+      "learning_rate": 1.0755152352841798e-05,
+      "loss": 0.1435,
+      "step": 781
+    },
+    {
+      "epoch": 0.5290933694181326,
+      "grad_norm": 4.172342777252197,
+      "learning_rate": 1.0731596716917978e-05,
+      "loss": 0.1428,
+      "step": 782
+    },
+    {
+      "epoch": 0.5297699594046008,
+      "grad_norm": 2.936666250228882,
+      "learning_rate": 1.0708036999041072e-05,
+      "loss": 0.1051,
+      "step": 783
+    },
+    {
+      "epoch": 0.530446549391069,
+      "grad_norm": 2.487924098968506,
+      "learning_rate": 1.0684473330662815e-05,
+      "loss": 0.0967,
+      "step": 784
+    },
+    {
+      "epoch": 0.5311231393775372,
+      "grad_norm": 3.894505739212036,
+      "learning_rate": 1.0660905843256995e-05,
+      "loss": 0.1088,
+      "step": 785
+    },
+    {
+      "epoch": 0.5317997293640054,
+      "grad_norm": 5.016809463500977,
+      "learning_rate": 1.0637334668318708e-05,
+      "loss": 0.1301,
+      "step": 786
+    },
+    {
+      "epoch": 0.5324763193504736,
+      "grad_norm": 3.1163365840911865,
+      "learning_rate": 1.0613759937363617e-05,
+      "loss": 0.125,
+      "step": 787
+    },
+    {
+      "epoch": 0.5331529093369418,
+      "grad_norm": 3.6140894889831543,
+      "learning_rate": 1.0590181781927229e-05,
+      "loss": 0.1339,
+      "step": 788
+    },
+    {
+      "epoch": 0.5338294993234101,
+      "grad_norm": 4.263391971588135,
+      "learning_rate": 1.0566600333564163e-05,
+      "loss": 0.2378,
+      "step": 789
+    },
+    {
+      "epoch": 0.5345060893098782,
+      "grad_norm": 5.283838748931885,
+      "learning_rate": 1.0543015723847402e-05,
+      "loss": 0.1762,
+      "step": 790
+    },
+    {
+      "epoch": 0.5351826792963464,
+      "grad_norm": 4.460554599761963,
+      "learning_rate": 1.0519428084367583e-05,
+      "loss": 0.1446,
+      "step": 791
+    },
+    {
+      "epoch": 0.5358592692828146,
+      "grad_norm": 3.4405527114868164,
+      "learning_rate": 1.0495837546732224e-05,
+      "loss": 0.0647,
+      "step": 792
+    },
+    {
+      "epoch": 0.5365358592692828,
+      "grad_norm": 2.5219104290008545,
+      "learning_rate": 1.0472244242565035e-05,
+      "loss": 0.0866,
+      "step": 793
+    },
+    {
+      "epoch": 0.5372124492557511,
+      "grad_norm": 4.9833221435546875,
+      "learning_rate": 1.044864830350515e-05,
+      "loss": 0.1009,
+      "step": 794
+    },
+    {
+      "epoch": 0.5378890392422192,
+      "grad_norm": 3.444195032119751,
+      "learning_rate": 1.042504986120641e-05,
+      "loss": 0.0941,
+      "step": 795
+    },
+    {
+      "epoch": 0.5385656292286874,
+      "grad_norm": 5.0867509841918945,
+      "learning_rate": 1.0401449047336622e-05,
+      "loss": 0.1377,
+      "step": 796
+    },
+    {
+      "epoch": 0.5392422192151556,
+      "grad_norm": 4.2269606590271,
+      "learning_rate": 1.0377845993576819e-05,
+      "loss": 0.1651,
+      "step": 797
+    },
+    {
+      "epoch": 0.5399188092016238,
+      "grad_norm": 5.579936504364014,
+      "learning_rate": 1.0354240831620542e-05,
+      "loss": 0.2036,
+      "step": 798
+    },
+    {
+      "epoch": 0.540595399188092,
+      "grad_norm": 3.619593858718872,
+      "learning_rate": 1.0330633693173083e-05,
+      "loss": 0.0519,
+      "step": 799
+    },
+    {
+      "epoch": 0.5412719891745602,
+      "grad_norm": 5.691805362701416,
+      "learning_rate": 1.0307024709950775e-05,
+      "loss": 0.1691,
+      "step": 800
+    },
+    {
+      "epoch": 0.5412719891745602,
+      "eval_accuracy": 0.7926605504587156,
+      "eval_f1": 0.4321608040201005,
+      "eval_loss": 0.48544931411743164,
+      "eval_precision": 0.86,
+      "eval_recall": 0.28859060402684567,
+      "eval_runtime": 53.0047,
+      "eval_samples_per_second": 5.622,
+      "eval_steps_per_second": 0.189,
+      "step": 800
     }
   ],
   "logging_steps": 1,
@@ -5358,7 +6118,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.1229008750379008e+17,
+  "total_flos": 2.4277215937665434e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null