Training in progress, step 796, checkpoint

last-checkpoint/optimizer_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5fb4d724032a1245dc6cde40f4e5188553186f46cc33db24ff9acace6d64996
+oid sha256:48e5ce1c2212972e0ee8fa6acfdc5fe7df39207e5e1d429d22cd6c4829a272f8
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79e385d511e036b931d8833bb9f18f12b276860005885c6db5883e2bb8ffb250
+oid sha256:93dd121cdddd15e48fcd42cb045bbb8a8e39d4232a174681b2cdaa9ed07b85eb
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92c37b03fb2e32f372fe4bc5de8cfbfdcd80d4c5f02647d02082856a40cb7d81
+oid sha256:707ca785fdb83e9a677cadab0002912b5646df48b9bd63b60b0591a97645591e
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fc189980b81b63a0f5eb185c059a38e0e687a3da1cdbabb13632220bbd92f29
+oid sha256:f082611bab0f154550bf11b7ca0c49ebe43062b816ee3a83869d5a2412633823
 size 13990904

last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22866ce89c0e7ab0cc0f664b14f5ba101d34c338fdb1a105f2b2815d715ca268
+oid sha256:f235ef16b952e646ad92819f0a31df94e9a7c582b782343d63a30806dabe2bdc
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ba3c5c58c231743a3320074589c773530610636502758ac373fb041860f7629
+oid sha256:62da1265788c6e1683096c46442efdda78216d2246f1388dffe91d72d296d173
 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:d79b8891ee0d25a2be271a38d0ac5e556ce0257bf5123113c070352f99023ae9
+oid sha256:e05ae6c050c4ce3e69cf64dc5998d9b4d837a7282fa6e13e8ae8223773018ec9
 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:bcec9183c14a35cf480d0f7871398da31d6da2b44461bb7bdc738de5f51e523a
+oid sha256:0dcecd4e3580ccc7518235fcc9a83b80759dfa32109d546cbc785d0520484363
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d9fa53e4b694823856182f5d79606d713a9c38f7b0a474c8e8377b701cc4064
+oid sha256:8677949dd4daed3baec81ffbd2cd16385a5e48ad21b6d9617dca6ad8d3852208
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e467e256d1aeb5c59910c1df837a848b831bc8f1a437fc0b52c0ae7e6a47b29
+oid sha256:d02f3cde49bdc5d47a7a3bd34420870f6779977fd607584630229b11257c105d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61a104e0586ff0fcc9930cb2ff4e524b78a6f6ffc91335870d99757828f52f1c
+oid sha256:5466abc13e9f7dc6b3a1f0b0f576e1e7a9167f3e7fe4636f5960f66d5bce0994
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d01842b4ecf9c63cb6983558b75f5223cbe340d5e106d6e47d3afec1652f1f03
+oid sha256:bfdc2a159496b904c20ff3524ab0e6f67acaa3473ffff10710c51ce54512492b
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff7644a4cf9b613e830e53fbdb92eb21facf6604e16b66cdc1f7a045b886b1a7
+oid sha256:3189f886684f438800e47ff516d16d4e6fed0c1fe8f4467bf9b081f31a300e46
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8786610878661087,
+  "epoch": 0.999163179916318,
   "eval_steps": 20,
-  "global_step": 700,
+  "global_step": 796,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5339,6 +5339,726 @@
       "eval_samples_per_second": 5.342,
       "eval_steps_per_second": 0.174,
       "step": 700
+    },
+    {
+      "epoch": 0.8799163179916318,
+      "grad_norm": 5.480141639709473,
+      "learning_rate": 8.562362692700121e-07,
+      "loss": 0.2179,
+      "step": 701
+    },
+    {
+      "epoch": 0.8811715481171548,
+      "grad_norm": 4.480906009674072,
+      "learning_rate": 8.385600752849387e-07,
+      "loss": 0.2641,
+      "step": 702
+    },
+    {
+      "epoch": 0.8824267782426778,
+      "grad_norm": 4.178032875061035,
+      "learning_rate": 8.210602561842696e-07,
+      "loss": 0.2121,
+      "step": 703
+    },
+    {
+      "epoch": 0.8836820083682009,
+      "grad_norm": 3.827854633331299,
+      "learning_rate": 8.037371488723078e-07,
+      "loss": 0.2251,
+      "step": 704
+    },
+    {
+      "epoch": 0.8849372384937239,
+      "grad_norm": 4.65687370300293,
+      "learning_rate": 7.865910868513316e-07,
+      "loss": 0.2668,
+      "step": 705
+    },
+    {
+      "epoch": 0.8861924686192468,
+      "grad_norm": 3.7226722240448,
+      "learning_rate": 7.69622400215162e-07,
+      "loss": 0.2322,
+      "step": 706
+    },
+    {
+      "epoch": 0.8874476987447699,
+      "grad_norm": 2.8721847534179688,
+      "learning_rate": 7.528314156428085e-07,
+      "loss": 0.2454,
+      "step": 707
+    },
+    {
+      "epoch": 0.8887029288702929,
+      "grad_norm": 6.672764301300049,
+      "learning_rate": 7.36218456392187e-07,
+      "loss": 0.2606,
+      "step": 708
+    },
+    {
+      "epoch": 0.8899581589958159,
+      "grad_norm": 8.37939167022705,
+      "learning_rate": 7.197838422938908e-07,
+      "loss": 0.1692,
+      "step": 709
+    },
+    {
+      "epoch": 0.891213389121339,
+      "grad_norm": 5.5875725746154785,
+      "learning_rate": 7.035278897450326e-07,
+      "loss": 0.2718,
+      "step": 710
+    },
+    {
+      "epoch": 0.8924686192468619,
+      "grad_norm": 3.284900188446045,
+      "learning_rate": 6.874509117031636e-07,
+      "loss": 0.2369,
+      "step": 711
+    },
+    {
+      "epoch": 0.8937238493723849,
+      "grad_norm": 3.2228903770446777,
+      "learning_rate": 6.715532176802298e-07,
+      "loss": 0.1676,
+      "step": 712
+    },
+    {
+      "epoch": 0.894979079497908,
+      "grad_norm": 4.319593906402588,
+      "learning_rate": 6.558351137366292e-07,
+      "loss": 0.2301,
+      "step": 713
+    },
+    {
+      "epoch": 0.896234309623431,
+      "grad_norm": 4.787438869476318,
+      "learning_rate": 6.402969024753147e-07,
+      "loss": 0.2494,
+      "step": 714
+    },
+    {
+      "epoch": 0.897489539748954,
+      "grad_norm": 5.25081205368042,
+      "learning_rate": 6.249388830359659e-07,
+      "loss": 0.1948,
+      "step": 715
+    },
+    {
+      "epoch": 0.8987447698744769,
+      "grad_norm": 4.489555835723877,
+      "learning_rate": 6.097613510892364e-07,
+      "loss": 0.3019,
+      "step": 716
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 5.4843339920043945,
+      "learning_rate": 5.947645988310524e-07,
+      "loss": 0.2591,
+      "step": 717
+    },
+    {
+      "epoch": 0.901255230125523,
+      "grad_norm": 3.593355417251587,
+      "learning_rate": 5.799489149769943e-07,
+      "loss": 0.2489,
+      "step": 718
+    },
+    {
+      "epoch": 0.902510460251046,
+      "grad_norm": 4.679093837738037,
+      "learning_rate": 5.653145847567376e-07,
+      "loss": 0.3109,
+      "step": 719
+    },
+    {
+      "epoch": 0.9037656903765691,
+      "grad_norm": 3.6788761615753174,
+      "learning_rate": 5.508618899085583e-07,
+      "loss": 0.1931,
+      "step": 720
+    },
+    {
+      "epoch": 0.9037656903765691,
+      "eval_accuracy": 0.8620309050772627,
+      "eval_f1": 0.7178329571106095,
+      "eval_loss": 0.2884938418865204,
+      "eval_precision": 0.8412698412698413,
+      "eval_recall": 0.6259842519685039,
+      "eval_runtime": 51.1882,
+      "eval_samples_per_second": 5.411,
+      "eval_steps_per_second": 0.176,
+      "step": 720
+    },
+    {
+      "epoch": 0.905020920502092,
+      "grad_norm": 6.400424957275391,
+      "learning_rate": 5.365911086739117e-07,
+      "loss": 0.2357,
+      "step": 721
+    },
+    {
+      "epoch": 0.906276150627615,
+      "grad_norm": 4.213512897491455,
+      "learning_rate": 5.225025157920782e-07,
+      "loss": 0.2613,
+      "step": 722
+    },
+    {
+      "epoch": 0.9075313807531381,
+      "grad_norm": 4.268280506134033,
+      "learning_rate": 5.08596382494867e-07,
+      "loss": 0.1831,
+      "step": 723
+    },
+    {
+      "epoch": 0.9087866108786611,
+      "grad_norm": 5.073379039764404,
+      "learning_rate": 4.948729765014004e-07,
+      "loss": 0.2215,
+      "step": 724
+    },
+    {
+      "epoch": 0.9100418410041841,
+      "grad_norm": 3.750990867614746,
+      "learning_rate": 4.813325620129572e-07,
+      "loss": 0.2024,
+      "step": 725
+    },
+    {
+      "epoch": 0.9112970711297071,
+      "grad_norm": 3.3088490962982178,
+      "learning_rate": 4.6797539970788843e-07,
+      "loss": 0.2044,
+      "step": 726
+    },
+    {
+      "epoch": 0.9125523012552301,
+      "grad_norm": 4.00676965713501,
+      "learning_rate": 4.548017467365917e-07,
+      "loss": 0.1813,
+      "step": 727
+    },
+    {
+      "epoch": 0.9138075313807531,
+      "grad_norm": 4.088128089904785,
+      "learning_rate": 4.4181185671657634e-07,
+      "loss": 0.2087,
+      "step": 728
+    },
+    {
+      "epoch": 0.9150627615062762,
+      "grad_norm": 2.8981070518493652,
+      "learning_rate": 4.290059797275614e-07,
+      "loss": 0.1629,
+      "step": 729
+    },
+    {
+      "epoch": 0.9163179916317992,
+      "grad_norm": 3.5616722106933594,
+      "learning_rate": 4.163843623066732e-07,
+      "loss": 0.2354,
+      "step": 730
+    },
+    {
+      "epoch": 0.9175732217573221,
+      "grad_norm": 3.7056453227996826,
+      "learning_rate": 4.0394724744369564e-07,
+      "loss": 0.2432,
+      "step": 731
+    },
+    {
+      "epoch": 0.9188284518828452,
+      "grad_norm": 6.088983535766602,
+      "learning_rate": 3.916948745763938e-07,
+      "loss": 0.1824,
+      "step": 732
+    },
+    {
+      "epoch": 0.9200836820083682,
+      "grad_norm": 4.606024742126465,
+      "learning_rate": 3.7962747958590453e-07,
+      "loss": 0.2111,
+      "step": 733
+    },
+    {
+      "epoch": 0.9213389121338912,
+      "grad_norm": 3.6736326217651367,
+      "learning_rate": 3.6774529479219e-07,
+      "loss": 0.183,
+      "step": 734
+    },
+    {
+      "epoch": 0.9225941422594143,
+      "grad_norm": 4.102712154388428,
+      "learning_rate": 3.560485489495724e-07,
+      "loss": 0.2266,
+      "step": 735
+    },
+    {
+      "epoch": 0.9238493723849373,
+      "grad_norm": 3.6704976558685303,
+      "learning_rate": 3.445374672423252e-07,
+      "loss": 0.1764,
+      "step": 736
+    },
+    {
+      "epoch": 0.9251046025104602,
+      "grad_norm": 3.65004825592041,
+      "learning_rate": 3.3321227128033983e-07,
+      "loss": 0.183,
+      "step": 737
+    },
+    {
+      "epoch": 0.9263598326359833,
+      "grad_norm": 5.921749591827393,
+      "learning_rate": 3.2207317909485834e-07,
+      "loss": 0.3058,
+      "step": 738
+    },
+    {
+      "epoch": 0.9276150627615063,
+      "grad_norm": 3.211097240447998,
+      "learning_rate": 3.1112040513427646e-07,
+      "loss": 0.2254,
+      "step": 739
+    },
+    {
+      "epoch": 0.9288702928870293,
+      "grad_norm": 3.559563398361206,
+      "learning_rate": 3.0035416026001573e-07,
+      "loss": 0.2251,
+      "step": 740
+    },
+    {
+      "epoch": 0.9288702928870293,
+      "eval_accuracy": 0.8631346578366446,
+      "eval_f1": 0.7194570135746606,
+      "eval_loss": 0.2898021638393402,
+      "eval_precision": 0.8457446808510638,
+      "eval_recall": 0.6259842519685039,
+      "eval_runtime": 51.6937,
+      "eval_samples_per_second": 5.358,
+      "eval_steps_per_second": 0.174,
+      "step": 740
+    },
+    {
+      "epoch": 0.9301255230125522,
+      "grad_norm": 5.178525447845459,
+      "learning_rate": 2.8977465174246156e-07,
+      "loss": 0.2279,
+      "step": 741
+    },
+    {
+      "epoch": 0.9313807531380753,
+      "grad_norm": 3.763082504272461,
+      "learning_rate": 2.7938208325697825e-07,
+      "loss": 0.2488,
+      "step": 742
+    },
+    {
+      "epoch": 0.9326359832635983,
+      "grad_norm": 3.6214609146118164,
+      "learning_rate": 2.691766548799779e-07,
+      "loss": 0.2449,
+      "step": 743
+    },
+    {
+      "epoch": 0.9338912133891213,
+      "grad_norm": 4.081825256347656,
+      "learning_rate": 2.591585630850835e-07,
+      "loss": 0.2272,
+      "step": 744
+    },
+    {
+      "epoch": 0.9351464435146444,
+      "grad_norm": 6.377195835113525,
+      "learning_rate": 2.493280007393295e-07,
+      "loss": 0.2366,
+      "step": 745
+    },
+    {
+      "epoch": 0.9364016736401674,
+      "grad_norm": 6.9662981033325195,
+      "learning_rate": 2.3968515709946296e-07,
+      "loss": 0.2034,
+      "step": 746
+    },
+    {
+      "epoch": 0.9376569037656903,
+      "grad_norm": 2.801429510116577,
+      "learning_rate": 2.3023021780829158e-07,
+      "loss": 0.2079,
+      "step": 747
+    },
+    {
+      "epoch": 0.9389121338912134,
+      "grad_norm": 5.810364246368408,
+      "learning_rate": 2.2096336489111025e-07,
+      "loss": 0.2818,
+      "step": 748
+    },
+    {
+      "epoch": 0.9401673640167364,
+      "grad_norm": 6.120866775512695,
+      "learning_rate": 2.1188477675220142e-07,
+      "loss": 0.3222,
+      "step": 749
+    },
+    {
+      "epoch": 0.9414225941422594,
+      "grad_norm": 4.8275957107543945,
+      "learning_rate": 2.0299462817139902e-07,
+      "loss": 0.2819,
+      "step": 750
+    },
+    {
+      "epoch": 0.9426778242677825,
+      "grad_norm": 3.9053924083709717,
+      "learning_rate": 1.942930903007212e-07,
+      "loss": 0.1928,
+      "step": 751
+    },
+    {
+      "epoch": 0.9439330543933054,
+      "grad_norm": 3.453087091445923,
+      "learning_rate": 1.8578033066107392e-07,
+      "loss": 0.1989,
+      "step": 752
+    },
+    {
+      "epoch": 0.9451882845188284,
+      "grad_norm": 3.622796058654785,
+      "learning_rate": 1.7745651313903157e-07,
+      "loss": 0.1392,
+      "step": 753
+    },
+    {
+      "epoch": 0.9464435146443515,
+      "grad_norm": 3.5609803199768066,
+      "learning_rate": 1.693217979836792e-07,
+      "loss": 0.1935,
+      "step": 754
+    },
+    {
+      "epoch": 0.9476987447698745,
+      "grad_norm": 4.004082679748535,
+      "learning_rate": 1.6137634180352303e-07,
+      "loss": 0.2124,
+      "step": 755
+    },
+    {
+      "epoch": 0.9489539748953975,
+      "grad_norm": 3.635117292404175,
+      "learning_rate": 1.5362029756348373e-07,
+      "loss": 0.2254,
+      "step": 756
+    },
+    {
+      "epoch": 0.9502092050209205,
+      "grad_norm": 6.247368812561035,
+      "learning_rate": 1.4605381458194568e-07,
+      "loss": 0.3048,
+      "step": 757
+    },
+    {
+      "epoch": 0.9514644351464435,
+      "grad_norm": 7.196407794952393,
+      "learning_rate": 1.386770385278835e-07,
+      "loss": 0.2386,
+      "step": 758
+    },
+    {
+      "epoch": 0.9527196652719665,
+      "grad_norm": 4.880216121673584,
+      "learning_rate": 1.3149011141805669e-07,
+      "loss": 0.286,
+      "step": 759
+    },
+    {
+      "epoch": 0.9539748953974896,
+      "grad_norm": 3.848249912261963,
+      "learning_rate": 1.2449317161427942e-07,
+      "loss": 0.178,
+      "step": 760
+    },
+    {
+      "epoch": 0.9539748953974896,
+      "eval_accuracy": 0.8631346578366446,
+      "eval_f1": 0.7194570135746606,
+      "eval_loss": 0.2888832986354828,
+      "eval_precision": 0.8457446808510638,
+      "eval_recall": 0.6259842519685039,
+      "eval_runtime": 51.4816,
+      "eval_samples_per_second": 5.381,
+      "eval_steps_per_second": 0.175,
+      "step": 760
+    },
+    {
+      "epoch": 0.9552301255230126,
+      "grad_norm": 4.997644424438477,
+      "learning_rate": 1.1768635382075289e-07,
+      "loss": 0.2997,
+      "step": 761
+    },
+    {
+      "epoch": 0.9564853556485355,
+      "grad_norm": 4.796181678771973,
+      "learning_rate": 1.1106978908147381e-07,
+      "loss": 0.2601,
+      "step": 762
+    },
+    {
+      "epoch": 0.9577405857740586,
+      "grad_norm": 3.6467103958129883,
+      "learning_rate": 1.0464360477771218e-07,
+      "loss": 0.2264,
+      "step": 763
+    },
+    {
+      "epoch": 0.9589958158995816,
+      "grad_norm": 5.8963303565979,
+      "learning_rate": 9.840792462555426e-08,
+      "loss": 0.2699,
+      "step": 764
+    },
+    {
+      "epoch": 0.9602510460251046,
+      "grad_norm": 4.986123561859131,
+      "learning_rate": 9.236286867352785e-08,
+      "loss": 0.2784,
+      "step": 765
+    },
+    {
+      "epoch": 0.9615062761506277,
+      "grad_norm": 4.026951313018799,
+      "learning_rate": 8.650855330028629e-08,
+      "loss": 0.2525,
+      "step": 766
+    },
+    {
+      "epoch": 0.9627615062761506,
+      "grad_norm": 5.082536220550537,
+      "learning_rate": 8.08450912123715e-08,
+      "loss": 0.2589,
+      "step": 767
+    },
+    {
+      "epoch": 0.9640167364016736,
+      "grad_norm": 5.790295124053955,
+      "learning_rate": 7.53725914420378e-08,
+      "loss": 0.2811,
+      "step": 768
+    },
+    {
+      "epoch": 0.9652719665271966,
+      "grad_norm": 4.651604175567627,
+      "learning_rate": 7.009115934516253e-08,
+      "loss": 0.2499,
+      "step": 769
+    },
+    {
+      "epoch": 0.9665271966527197,
+      "grad_norm": 4.613510608673096,
+      "learning_rate": 6.500089659920661e-08,
+      "loss": 0.2495,
+      "step": 770
+    },
+    {
+      "epoch": 0.9677824267782427,
+      "grad_norm": 4.089534759521484,
+      "learning_rate": 6.010190120126602e-08,
+      "loss": 0.2421,
+      "step": 771
+    },
+    {
+      "epoch": 0.9690376569037656,
+      "grad_norm": 4.79866886138916,
+      "learning_rate": 5.539426746618337e-08,
+      "loss": 0.2493,
+      "step": 772
+    },
+    {
+      "epoch": 0.9702928870292887,
+      "grad_norm": 4.052529335021973,
+      "learning_rate": 5.0878086024727104e-08,
+      "loss": 0.245,
+      "step": 773
+    },
+    {
+      "epoch": 0.9715481171548117,
+      "grad_norm": 3.7741782665252686,
+      "learning_rate": 4.6553443821852893e-08,
+      "loss": 0.2205,
+      "step": 774
+    },
+    {
+      "epoch": 0.9728033472803347,
+      "grad_norm": 3.792848587036133,
+      "learning_rate": 4.2420424115025004e-08,
+      "loss": 0.2297,
+      "step": 775
+    },
+    {
+      "epoch": 0.9740585774058578,
+      "grad_norm": 4.39737606048584,
+      "learning_rate": 3.847910647261754e-08,
+      "loss": 0.1941,
+      "step": 776
+    },
+    {
+      "epoch": 0.9753138075313807,
+      "grad_norm": 4.301551342010498,
+      "learning_rate": 3.472956677238015e-08,
+      "loss": 0.2069,
+      "step": 777
+    },
+    {
+      "epoch": 0.9765690376569037,
+      "grad_norm": 3.8330047130584717,
+      "learning_rate": 3.117187719997805e-08,
+      "loss": 0.209,
+      "step": 778
+    },
+    {
+      "epoch": 0.9778242677824268,
+      "grad_norm": 3.5165398120880127,
+      "learning_rate": 2.780610624760094e-08,
+      "loss": 0.1973,
+      "step": 779
+    },
+    {
+      "epoch": 0.9790794979079498,
+      "grad_norm": 4.450705528259277,
+      "learning_rate": 2.4632318712646264e-08,
+      "loss": 0.2431,
+      "step": 780
+    },
+    {
+      "epoch": 0.9790794979079498,
+      "eval_accuracy": 0.8631346578366446,
+      "eval_f1": 0.7194570135746606,
+      "eval_loss": 0.2885710895061493,
+      "eval_precision": 0.8457446808510638,
+      "eval_recall": 0.6259842519685039,
+      "eval_runtime": 51.066,
+      "eval_samples_per_second": 5.424,
+      "eval_steps_per_second": 0.176,
+      "step": 780
+    },
+    {
+      "epoch": 0.9803347280334728,
+      "grad_norm": 5.469013690948486,
+      "learning_rate": 2.1650575696471332e-08,
+      "loss": 0.2557,
+      "step": 781
+    },
+    {
+      "epoch": 0.9815899581589959,
+      "grad_norm": 3.630676031112671,
+      "learning_rate": 1.8860934603215365e-08,
+      "loss": 0.1707,
+      "step": 782
+    },
+    {
+      "epoch": 0.9828451882845188,
+      "grad_norm": 2.949327230453491,
+      "learning_rate": 1.626344913869593e-08,
+      "loss": 0.1495,
+      "step": 783
+    },
+    {
+      "epoch": 0.9841004184100418,
+      "grad_norm": 4.833507537841797,
+      "learning_rate": 1.3858169309376446e-08,
+      "loss": 0.2054,
+      "step": 784
+    },
+    {
+      "epoch": 0.9853556485355649,
+      "grad_norm": 4.511420249938965,
+      "learning_rate": 1.1645141421399164e-08,
+      "loss": 0.2058,
+      "step": 785
+    },
+    {
+      "epoch": 0.9866108786610879,
+      "grad_norm": 4.471105098724365,
+      "learning_rate": 9.624408079699221e-09,
+      "loss": 0.2349,
+      "step": 786
+    },
+    {
+      "epoch": 0.9878661087866109,
+      "grad_norm": 4.504687309265137,
+      "learning_rate": 7.796008187177518e-09,
+      "loss": 0.2564,
+      "step": 787
+    },
+    {
+      "epoch": 0.9891213389121339,
+      "grad_norm": 4.099091053009033,
+      "learning_rate": 6.1599769439590896e-09,
+      "loss": 0.2413,
+      "step": 788
+    },
+    {
+      "epoch": 0.9903765690376569,
+      "grad_norm": 3.7011802196502686,
+      "learning_rate": 4.716345846711434e-09,
+      "loss": 0.2547,
+      "step": 789
+    },
+    {
+      "epoch": 0.9916317991631799,
+      "grad_norm": 4.092798233032227,
+      "learning_rate": 3.465142688036105e-09,
+      "loss": 0.2754,
+      "step": 790
+    },
+    {
+      "epoch": 0.992887029288703,
+      "grad_norm": 3.2027719020843506,
+      "learning_rate": 2.4063915559402463e-09,
+      "loss": 0.2205,
+      "step": 791
+    },
+    {
+      "epoch": 0.994142259414226,
+      "grad_norm": 4.241121768951416,
+      "learning_rate": 1.540112833366969e-09,
+      "loss": 0.2476,
+      "step": 792
+    },
+    {
+      "epoch": 0.9953974895397489,
+      "grad_norm": 3.92455792427063,
+      "learning_rate": 8.663231978034425e-10,
+      "loss": 0.2345,
+      "step": 793
+    },
+    {
+      "epoch": 0.9966527196652719,
+      "grad_norm": 5.164183616638184,
+      "learning_rate": 3.850356209633699e-10,
+      "loss": 0.2975,
+      "step": 794
+    },
+    {
+      "epoch": 0.997907949790795,
+      "grad_norm": 7.26465368270874,
+      "learning_rate": 9.625936853385753e-11,
+      "loss": 0.3067,
+      "step": 795
+    },
+    {
+      "epoch": 0.999163179916318,
+      "grad_norm": 4.6205949783325195,
+      "learning_rate": 0.0,
+      "loss": 0.2553,
+      "step": 796
     }
   ],
   "logging_steps": 1,
@@ -5353,12 +6073,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.5677470361033114e+17,
+  "total_flos": 2.917806194389156e+17,
   "train_batch_size": 6,
   "trial_name": null,
   "trial_params": null