Training in progress, step 788, checkpoint

last-checkpoint/optimizer_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1d6658706a2b1b22d02af67ed32e150daada045c6218fcbac8d61cdee6f387a
+oid sha256:69b1ac8f77262327f2155611e8d5111c41ee52a7f01be46ecae2dd31f0b8f49e
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a53a5f077427c1fb6c1be3beda662bcb3c55295e52e5aac6cdd521540645e78
+oid sha256:0d62ca3f9188a97f25cf575e661ee2de17789532c15c5526f6e9926fa35457bc
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b4033bcd984ed883ee9f4753f5acd2a5f9698c3b391651526fe5836282d38a7
+oid sha256:ebaf35def2b53d8d851d2baddd6487b7bc118dc35eb096447ad4c6725147a010
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3abd615b881caa9b6b112faf16e7d3d92e8f14de7b312bdedd386f878060361e
+oid sha256:c93fab8485f73ec1505d15bba19c02007a5c47c730f655dcde91bd3835d8469a
 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:fd4ac688667fed33dbac29dd54010210058743290dae20597420324bc4b12d61
+oid sha256:d5ea01144229c20d5f4f164e1115e7e7f20c8bf8907e53d2e493239c444b05ee
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:386c4e28b7b6c76dc1bee240fa0bb1bfba0d8ccb93833317aef937e1c66e8e56
+oid sha256:925df7029bfec4f89243de6438ee08f2524a59718d43759af21b805141a14322
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bc8d6adc4a8ca28639d5097e8d755b737723c2a73e02a639554d412e2af015c
+oid sha256:5bad6b78dd073d1f0d86e8dcf23fc2afa0a97ea37b3dad4ef04e4913365bedf7
 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:ce7adf139cb5be3fa94f558d2253b67614e8f5e40c792e0a5458dcecd0d865b5
+oid sha256:33e154012f872d5ec4602117d98da569b8d5e2a2e8454cbf7367b1dced09bc47
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b8846b74d96cda2078cccff557518227c163d02a7e2b4a593daa2acbfe4642d
+oid sha256:d521bb7ac0b13415ca6efedd41d80cbc772aab6ad3c3c0470b3572d96c41464b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:075424ce87fff9c2e036af3f101cf627348425b5ff8402b4a0c190100ea3ad91
+oid sha256:5edee2ab01fed2ff8d23e5f1f088f012e9092a9561906a58069fb86ff88b7442
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2ac8d82137e7b493f65b02fe60e742d00785831acde45a3e931ec88619a5dca
+oid sha256:2c9f3ce2974485d5c2274eb5be2f8d8fbdb354727a36be1232561afe54a5cc9c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cd75e3ece083256eebd1a793ba9c4d81a6d9e08a128d64453489d62e892f1f6
+oid sha256:0b5e79f599e7b8d906ab68d7fa413face856a5a40141a232718ef5c2cf1432d6
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c7b277ba7269f25114908097aae9c5e108d3ce5eac98d48cc795839db8493c9
+oid sha256:932734b25fc4b0095c06417a23d21a34a66399d86559972ec9e2af484a90fa85
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8879492600422833,
+  "epoch": 0.9995771670190274,
   "eval_steps": 20,
-  "global_step": 700,
+  "global_step": 788,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5339,6 +5339,670 @@
       "eval_samples_per_second": 5.361,
       "eval_steps_per_second": 0.174,
       "step": 700
+    },
+    {
+      "epoch": 0.8892177589852008,
+      "grad_norm": 3.024763584136963,
+      "learning_rate": 7.338896466055934e-07,
+      "loss": 0.1503,
+      "step": 701
+    },
+    {
+      "epoch": 0.8904862579281184,
+      "grad_norm": 5.726973533630371,
+      "learning_rate": 7.173190915528494e-07,
+      "loss": 0.2625,
+      "step": 702
+    },
+    {
+      "epoch": 0.8917547568710359,
+      "grad_norm": 3.9381308555603027,
+      "learning_rate": 7.009307917244912e-07,
+      "loss": 0.1853,
+      "step": 703
+    },
+    {
+      "epoch": 0.8930232558139535,
+      "grad_norm": 6.115716457366943,
+      "learning_rate": 6.847250688867512e-07,
+      "loss": 0.204,
+      "step": 704
+    },
+    {
+      "epoch": 0.8942917547568711,
+      "grad_norm": 6.009361743927002,
+      "learning_rate": 6.687022412211608e-07,
+      "loss": 0.2365,
+      "step": 705
+    },
+    {
+      "epoch": 0.8955602536997885,
+      "grad_norm": 4.4307332038879395,
+      "learning_rate": 6.52862623318311e-07,
+      "loss": 0.1889,
+      "step": 706
+    },
+    {
+      "epoch": 0.8968287526427061,
+      "grad_norm": 4.24178409576416,
+      "learning_rate": 6.372065261716664e-07,
+      "loss": 0.1632,
+      "step": 707
+    },
+    {
+      "epoch": 0.8980972515856237,
+      "grad_norm": 3.5372025966644287,
+      "learning_rate": 6.217342571714679e-07,
+      "loss": 0.1961,
+      "step": 708
+    },
+    {
+      "epoch": 0.8993657505285412,
+      "grad_norm": 4.413094997406006,
+      "learning_rate": 6.064461200986893e-07,
+      "loss": 0.2418,
+      "step": 709
+    },
+    {
+      "epoch": 0.9006342494714588,
+      "grad_norm": 5.046213150024414,
+      "learning_rate": 5.913424151190772e-07,
+      "loss": 0.2449,
+      "step": 710
+    },
+    {
+      "epoch": 0.9019027484143763,
+      "grad_norm": 4.061814785003662,
+      "learning_rate": 5.764234387772593e-07,
+      "loss": 0.2165,
+      "step": 711
+    },
+    {
+      "epoch": 0.9031712473572938,
+      "grad_norm": 4.079103469848633,
+      "learning_rate": 5.616894839909181e-07,
+      "loss": 0.2452,
+      "step": 712
+    },
+    {
+      "epoch": 0.9044397463002114,
+      "grad_norm": 3.2785000801086426,
+      "learning_rate": 5.471408400450395e-07,
+      "loss": 0.1731,
+      "step": 713
+    },
+    {
+      "epoch": 0.905708245243129,
+      "grad_norm": 5.047578811645508,
+      "learning_rate": 5.327777925862399e-07,
+      "loss": 0.2437,
+      "step": 714
+    },
+    {
+      "epoch": 0.9069767441860465,
+      "grad_norm": 4.548726558685303,
+      "learning_rate": 5.186006236171492e-07,
+      "loss": 0.2111,
+      "step": 715
+    },
+    {
+      "epoch": 0.908245243128964,
+      "grad_norm": 3.2352497577667236,
+      "learning_rate": 5.046096114908783e-07,
+      "loss": 0.1582,
+      "step": 716
+    },
+    {
+      "epoch": 0.9095137420718816,
+      "grad_norm": 4.062112331390381,
+      "learning_rate": 4.908050309055545e-07,
+      "loss": 0.1853,
+      "step": 717
+    },
+    {
+      "epoch": 0.9107822410147992,
+      "grad_norm": 3.6328508853912354,
+      "learning_rate": 4.771871528989247e-07,
+      "loss": 0.2202,
+      "step": 718
+    },
+    {
+      "epoch": 0.9120507399577167,
+      "grad_norm": 5.491158962249756,
+      "learning_rate": 4.6375624484303993e-07,
+      "loss": 0.245,
+      "step": 719
+    },
+    {
+      "epoch": 0.9133192389006343,
+      "grad_norm": 4.557428359985352,
+      "learning_rate": 4.505125704389968e-07,
+      "loss": 0.2277,
+      "step": 720
+    },
+    {
+      "epoch": 0.9133192389006343,
+      "eval_accuracy": 0.8675496688741722,
+      "eval_f1": 0.7345132743362832,
+      "eval_loss": 0.2847309410572052,
+      "eval_precision": 0.8383838383838383,
+      "eval_recall": 0.6535433070866141,
+      "eval_runtime": 50.2843,
+      "eval_samples_per_second": 5.509,
+      "eval_steps_per_second": 0.179,
+      "step": 720
+    },
+    {
+      "epoch": 0.9145877378435519,
+      "grad_norm": 6.393286228179932,
+      "learning_rate": 4.374563897117701e-07,
+      "loss": 0.2023,
+      "step": 721
+    },
+    {
+      "epoch": 0.9158562367864693,
+      "grad_norm": 3.4379963874816895,
+      "learning_rate": 4.2458795900509943e-07,
+      "loss": 0.2034,
+      "step": 722
+    },
+    {
+      "epoch": 0.9171247357293869,
+      "grad_norm": 3.457280397415161,
+      "learning_rate": 4.11907530976462e-07,
+      "loss": 0.1882,
+      "step": 723
+    },
+    {
+      "epoch": 0.9183932346723045,
+      "grad_norm": 5.479604244232178,
+      "learning_rate": 3.9941535459210535e-07,
+      "loss": 0.1896,
+      "step": 724
+    },
+    {
+      "epoch": 0.919661733615222,
+      "grad_norm": 4.309389591217041,
+      "learning_rate": 3.8711167512216816e-07,
+      "loss": 0.2101,
+      "step": 725
+    },
+    {
+      "epoch": 0.9209302325581395,
+      "grad_norm": 3.776045799255371,
+      "learning_rate": 3.7499673413585516e-07,
+      "loss": 0.2342,
+      "step": 726
+    },
+    {
+      "epoch": 0.9221987315010571,
+      "grad_norm": 4.307753086090088,
+      "learning_rate": 3.6307076949670173e-07,
+      "loss": 0.2191,
+      "step": 727
+    },
+    {
+      "epoch": 0.9234672304439746,
+      "grad_norm": 4.025116920471191,
+      "learning_rate": 3.513340153578981e-07,
+      "loss": 0.2486,
+      "step": 728
+    },
+    {
+      "epoch": 0.9247357293868922,
+      "grad_norm": 5.146588325500488,
+      "learning_rate": 3.3978670215769726e-07,
+      "loss": 0.2288,
+      "step": 729
+    },
+    {
+      "epoch": 0.9260042283298098,
+      "grad_norm": 4.41669225692749,
+      "learning_rate": 3.284290566148873e-07,
+      "loss": 0.3089,
+      "step": 730
+    },
+    {
+      "epoch": 0.9272727272727272,
+      "grad_norm": 4.287278175354004,
+      "learning_rate": 3.1726130172433756e-07,
+      "loss": 0.2162,
+      "step": 731
+    },
+    {
+      "epoch": 0.9285412262156448,
+      "grad_norm": 6.512703895568848,
+      "learning_rate": 3.062836567526262e-07,
+      "loss": 0.3019,
+      "step": 732
+    },
+    {
+      "epoch": 0.9298097251585624,
+      "grad_norm": 4.87605094909668,
+      "learning_rate": 2.954963372337327e-07,
+      "loss": 0.2448,
+      "step": 733
+    },
+    {
+      "epoch": 0.9310782241014799,
+      "grad_norm": 5.300022125244141,
+      "learning_rate": 2.848995549648048e-07,
+      "loss": 0.1657,
+      "step": 734
+    },
+    {
+      "epoch": 0.9323467230443975,
+      "grad_norm": 3.4938764572143555,
+      "learning_rate": 2.744935180019992e-07,
+      "loss": 0.1821,
+      "step": 735
+    },
+    {
+      "epoch": 0.9336152219873151,
+      "grad_norm": 4.725379467010498,
+      "learning_rate": 2.642784306564017e-07,
+      "loss": 0.2246,
+      "step": 736
+    },
+    {
+      "epoch": 0.9348837209302325,
+      "grad_norm": 4.498754024505615,
+      "learning_rate": 2.542544934900115e-07,
+      "loss": 0.1903,
+      "step": 737
+    },
+    {
+      "epoch": 0.9361522198731501,
+      "grad_norm": 3.992305040359497,
+      "learning_rate": 2.444219033118012e-07,
+      "loss": 0.1987,
+      "step": 738
+    },
+    {
+      "epoch": 0.9374207188160677,
+      "grad_norm": 4.835594654083252,
+      "learning_rate": 2.3478085317386157e-07,
+      "loss": 0.1839,
+      "step": 739
+    },
+    {
+      "epoch": 0.9386892177589852,
+      "grad_norm": 4.230025768280029,
+      "learning_rate": 2.2533153236760197e-07,
+      "loss": 0.2099,
+      "step": 740
+    },
+    {
+      "epoch": 0.9386892177589852,
+      "eval_accuracy": 0.8719646799116998,
+      "eval_f1": 0.7433628318584071,
+      "eval_loss": 0.2828395962715149,
+      "eval_precision": 0.8484848484848485,
+      "eval_recall": 0.6614173228346457,
+      "eval_runtime": 52.0079,
+      "eval_samples_per_second": 5.326,
+      "eval_steps_per_second": 0.173,
+      "step": 740
+    },
+    {
+      "epoch": 0.9399577167019028,
+      "grad_norm": 3.8719146251678467,
+      "learning_rate": 2.160741264200361e-07,
+      "loss": 0.1284,
+      "step": 741
+    },
+    {
+      "epoch": 0.9412262156448203,
+      "grad_norm": 3.105536699295044,
+      "learning_rate": 2.070088170901441e-07,
+      "loss": 0.198,
+      "step": 742
+    },
+    {
+      "epoch": 0.9424947145877378,
+      "grad_norm": 5.078315258026123,
+      "learning_rate": 1.981357823652974e-07,
+      "loss": 0.2043,
+      "step": 743
+    },
+    {
+      "epoch": 0.9437632135306554,
+      "grad_norm": 2.7954623699188232,
+      "learning_rate": 1.8945519645776955e-07,
+      "loss": 0.1437,
+      "step": 744
+    },
+    {
+      "epoch": 0.945031712473573,
+      "grad_norm": 4.234827995300293,
+      "learning_rate": 1.8096722980131097e-07,
+      "loss": 0.2144,
+      "step": 745
+    },
+    {
+      "epoch": 0.9463002114164905,
+      "grad_norm": 4.860174655914307,
+      "learning_rate": 1.7267204904780621e-07,
+      "loss": 0.203,
+      "step": 746
+    },
+    {
+      "epoch": 0.947568710359408,
+      "grad_norm": 4.2235188484191895,
+      "learning_rate": 1.64569817064002e-07,
+      "loss": 0.2186,
+      "step": 747
+    },
+    {
+      "epoch": 0.9488372093023256,
+      "grad_norm": 4.688875675201416,
+      "learning_rate": 1.5666069292830544e-07,
+      "loss": 0.299,
+      "step": 748
+    },
+    {
+      "epoch": 0.9501057082452431,
+      "grad_norm": 3.522006034851074,
+      "learning_rate": 1.489448319276676e-07,
+      "loss": 0.1852,
+      "step": 749
+    },
+    {
+      "epoch": 0.9513742071881607,
+      "grad_norm": 3.4337916374206543,
+      "learning_rate": 1.4142238555452603e-07,
+      "loss": 0.2085,
+      "step": 750
+    },
+    {
+      "epoch": 0.9526427061310783,
+      "grad_norm": 4.442638874053955,
+      "learning_rate": 1.3409350150383804e-07,
+      "loss": 0.3052,
+      "step": 751
+    },
+    {
+      "epoch": 0.9539112050739957,
+      "grad_norm": 4.747457981109619,
+      "learning_rate": 1.2695832367017657e-07,
+      "loss": 0.157,
+      "step": 752
+    },
+    {
+      "epoch": 0.9551797040169133,
+      "grad_norm": 4.382355213165283,
+      "learning_rate": 1.200169921449068e-07,
+      "loss": 0.139,
+      "step": 753
+    },
+    {
+      "epoch": 0.9564482029598309,
+      "grad_norm": 4.102878570556641,
+      "learning_rate": 1.1326964321343503e-07,
+      "loss": 0.2203,
+      "step": 754
+    },
+    {
+      "epoch": 0.9577167019027484,
+      "grad_norm": 5.611064434051514,
+      "learning_rate": 1.0671640935252969e-07,
+      "loss": 0.279,
+      "step": 755
+    },
+    {
+      "epoch": 0.958985200845666,
+      "grad_norm": 3.508052110671997,
+      "learning_rate": 1.0035741922772902e-07,
+      "loss": 0.1757,
+      "step": 756
+    },
+    {
+      "epoch": 0.9602536997885835,
+      "grad_norm": 8.137269973754883,
+      "learning_rate": 9.419279769080524e-08,
+      "loss": 0.3384,
+      "step": 757
+    },
+    {
+      "epoch": 0.961522198731501,
+      "grad_norm": 5.806704521179199,
+      "learning_rate": 8.822266577731775e-08,
+      "loss": 0.1737,
+      "step": 758
+    },
+    {
+      "epoch": 0.9627906976744186,
+      "grad_norm": 3.4643378257751465,
+      "learning_rate": 8.244714070423709e-08,
+      "loss": 0.2046,
+      "step": 759
+    },
+    {
+      "epoch": 0.9640591966173362,
+      "grad_norm": 4.203879356384277,
+      "learning_rate": 7.686633586764247e-08,
+      "loss": 0.2167,
+      "step": 760
+    },
+    {
+      "epoch": 0.9640591966173362,
+      "eval_accuracy": 0.8708609271523179,
+      "eval_f1": 0.7405764966740577,
+      "eval_loss": 0.2835051715373993,
+      "eval_precision": 0.8477157360406091,
+      "eval_recall": 0.65748031496063,
+      "eval_runtime": 51.121,
+      "eval_samples_per_second": 5.419,
+      "eval_steps_per_second": 0.176,
+      "step": 760
+    },
+    {
+      "epoch": 0.9653276955602537,
+      "grad_norm": 3.5984137058258057,
+      "learning_rate": 7.14803608404957e-08,
+      "loss": 0.2524,
+      "step": 761
+    },
+    {
+      "epoch": 0.9665961945031712,
+      "grad_norm": 3.3036506175994873,
+      "learning_rate": 6.62893213704885e-08,
+      "loss": 0.2024,
+      "step": 762
+    },
+    {
+      "epoch": 0.9678646934460888,
+      "grad_norm": 4.572678089141846,
+      "learning_rate": 6.129331937796856e-08,
+      "loss": 0.1583,
+      "step": 763
+    },
+    {
+      "epoch": 0.9691331923890063,
+      "grad_norm": 5.103546619415283,
+      "learning_rate": 5.64924529539379e-08,
+      "loss": 0.2218,
+      "step": 764
+    },
+    {
+      "epoch": 0.9704016913319239,
+      "grad_norm": 5.696028232574463,
+      "learning_rate": 5.1886816358125425e-08,
+      "loss": 0.1784,
+      "step": 765
+    },
+    {
+      "epoch": 0.9716701902748415,
+      "grad_norm": 4.081172466278076,
+      "learning_rate": 4.747650001713622e-08,
+      "loss": 0.2345,
+      "step": 766
+    },
+    {
+      "epoch": 0.972938689217759,
+      "grad_norm": 3.9841372966766357,
+      "learning_rate": 4.326159052267964e-08,
+      "loss": 0.1854,
+      "step": 767
+    },
+    {
+      "epoch": 0.9742071881606765,
+      "grad_norm": 4.337159156799316,
+      "learning_rate": 3.924217062986402e-08,
+      "loss": 0.2464,
+      "step": 768
+    },
+    {
+      "epoch": 0.9754756871035941,
+      "grad_norm": 3.1016838550567627,
+      "learning_rate": 3.541831925557571e-08,
+      "loss": 0.1883,
+      "step": 769
+    },
+    {
+      "epoch": 0.9767441860465116,
+      "grad_norm": 4.459488391876221,
+      "learning_rate": 3.179011147693034e-08,
+      "loss": 0.2386,
+      "step": 770
+    },
+    {
+      "epoch": 0.9780126849894292,
+      "grad_norm": 6.270811080932617,
+      "learning_rate": 2.835761852979291e-08,
+      "loss": 0.2679,
+      "step": 771
+    },
+    {
+      "epoch": 0.9792811839323468,
+      "grad_norm": 5.3437604904174805,
+      "learning_rate": 2.512090780738552e-08,
+      "loss": 0.2517,
+      "step": 772
+    },
+    {
+      "epoch": 0.9805496828752642,
+      "grad_norm": 2.9482016563415527,
+      "learning_rate": 2.2080042858961815e-08,
+      "loss": 0.1528,
+      "step": 773
+    },
+    {
+      "epoch": 0.9818181818181818,
+      "grad_norm": 6.166524887084961,
+      "learning_rate": 1.9235083388559063e-08,
+      "loss": 0.2392,
+      "step": 774
+    },
+    {
+      "epoch": 0.9830866807610994,
+      "grad_norm": 3.6311111450195312,
+      "learning_rate": 1.6586085253824657e-08,
+      "loss": 0.2192,
+      "step": 775
+    },
+    {
+      "epoch": 0.9843551797040169,
+      "grad_norm": 3.79732084274292,
+      "learning_rate": 1.4133100464922556e-08,
+      "loss": 0.1825,
+      "step": 776
+    },
+    {
+      "epoch": 0.9856236786469345,
+      "grad_norm": 2.6432785987854004,
+      "learning_rate": 1.187617718350853e-08,
+      "loss": 0.1475,
+      "step": 777
+    },
+    {
+      "epoch": 0.986892177589852,
+      "grad_norm": 2.565079927444458,
+      "learning_rate": 9.81535972178871e-09,
+      "loss": 0.157,
+      "step": 778
+    },
+    {
+      "epoch": 0.9881606765327695,
+      "grad_norm": 4.657979965209961,
+      "learning_rate": 7.950688541646934e-09,
+      "loss": 0.2102,
+      "step": 779
+    },
+    {
+      "epoch": 0.9894291754756871,
+      "grad_norm": 5.906298637390137,
+      "learning_rate": 6.282200253847625e-09,
+      "loss": 0.1901,
+      "step": 780
+    },
+    {
+      "epoch": 0.9894291754756871,
+      "eval_accuracy": 0.8686534216335541,
+      "eval_f1": 0.7373068432671082,
+      "eval_loss": 0.28413623571395874,
+      "eval_precision": 0.8391959798994975,
+      "eval_recall": 0.65748031496063,
+      "eval_runtime": 51.8309,
+      "eval_samples_per_second": 5.344,
+      "eval_steps_per_second": 0.174,
+      "step": 780
+    },
+    {
+      "epoch": 0.9906976744186047,
+      "grad_norm": 4.27111291885376,
+      "learning_rate": 4.809927617324128e-09,
+      "loss": 0.2112,
+      "step": 781
+    },
+    {
+      "epoch": 0.9919661733615222,
+      "grad_norm": 6.234564781188965,
+      "learning_rate": 3.533899538528118e-09,
+      "loss": 0.2754,
+      "step": 782
+    },
+    {
+      "epoch": 0.9932346723044397,
+      "grad_norm": 5.112316131591797,
+      "learning_rate": 2.4541410708667223e-09,
+      "loss": 0.2337,
+      "step": 783
+    },
+    {
+      "epoch": 0.9945031712473573,
+      "grad_norm": 4.032815933227539,
+      "learning_rate": 1.5706734142106883e-09,
+      "loss": 0.2389,
+      "step": 784
+    },
+    {
+      "epoch": 0.9957716701902748,
+      "grad_norm": 3.928197145462036,
+      "learning_rate": 8.835139144736104e-10,
+      "loss": 0.2295,
+      "step": 785
+    },
+    {
+      "epoch": 0.9970401691331924,
+      "grad_norm": 5.0506815910339355,
+      "learning_rate": 3.9267606327775266e-10,
+      "loss": 0.1851,
+      "step": 786
+    },
+    {
+      "epoch": 0.99830866807611,
+      "grad_norm": 4.563787937164307,
+      "learning_rate": 9.816949768204354e-11,
+      "loss": 0.2297,
+      "step": 787
+    },
+    {
+      "epoch": 0.9995771670190274,
+      "grad_norm": 5.677037715911865,
+      "learning_rate": 0.0,
+      "loss": 0.19,
+      "step": 788
     }
   ],
   "logging_steps": 1,
@@ -5353,12 +6017,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.6256102807044096e+17,
+  "total_flos": 2.9528591072598426e+17,
   "train_batch_size": 6,
   "trial_name": null,
   "trial_params": null