Training in progress, step 900, checkpoint

last-checkpoint/optimizer_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13c6a70f40405e1514ee690d2d726a2eda5a808e23b37141e1da7a8283e88cdf
+oid sha256:f10781c11ffaf9ea683a2b9f148eb6193b387a9596cdc379a39b151cd96a6ed5
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77005f8b4684233cd23fddeff831b0d7e2ba62b3e49ad7a6cdea1eb4a2266062
+oid sha256:bcf3f3cdff38b04513f755ff5fe51279597bda35fbcaa4540464c148299a7f9e
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29098ecbbc98e2ef7a0cc07c296555201b1c17dca6827e0aa4cf057bea4a9f44
+oid sha256:1dc1a1054bf5e72ab6406fa75f22272a912c3f7bbd26beeb517e468dd796f561
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f652669b1e9274a8b5ae329032551769dfa863b129e44530c77af4bd3839fa88
+oid sha256:b097daac12a3b8b7f8fcea6b0e0e5e800da493141828f17b047144768f29ae8f
 size 13990904

last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16ba980f4f3d9b276084055bf854883cd8c20fff6dac637fe7d56a8f557c17bc
+oid sha256:e1df521389c648fdcef151c1c1e25fab57cd32c9327cc1b006ccdb91fc6f5d67
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02373d01a9b56c3ab4e93e681e07a39bbe2a3e309506f2577c5603847075a2d5
+oid sha256:ae8fd1bc5f3874f74cbf8d19c56ced874b79d0ccd52ef55818ff2c390665de3c
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76193e492b66f206f41d94e761d55e6caa9895ede10807dab878b119033c4ba4
+oid sha256:96fbe9720baae575304e11b03a17222867f50d6f3ebad7cd3cb637d5a5090a69
 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:b4fa8b30a010a9033e33cf6f70de911ed412917cb3e71fef02176a307d0fa0db
+oid sha256:aa226dcc75cd45e2a65534f271d6d0332f19bf340356a6fcbb4abc05014edf1a
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f5f448f19b831b7c400641f7b6b4e0c34ca48f5591ef366c69f1b81cf80708e
+oid sha256:bf5199703b02897f2e6dba9bbe7832a4cfd69f57db643f127248f75efd8407b4
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1754427aaf72ee1d3c16166e944ab7191d6b9de8ecf0cbfa02abfb3be73c9e3c
+oid sha256:f62c44c56b2b450cc845f1235736c0f44aa7ba742b15a431a1981fb423cc4478
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8a09b07e23f077bec42858b2249cc45be4297d07e415b868653ab2077bf84f2
+oid sha256:7d284546937b7cec049fbd19fe40bdfbb6cccd69f90c9dbe3362cce0f376dfb6
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e0a99091149f689ab6fee861f9feda216a8bd712b9090eced1630dd585cae9e
+oid sha256:59b063a39beefca37081a83deeee992f65df1869639ae07f04be730e3c0c93b0
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e32d4de911f8fbacfa50c5d8b5d57dd58209aafb1f3c2bd72675b52ec971bf10
+oid sha256:c088b819c91734ec9375d4bee9cef712d419d6d66dfa44c6220ac51400b3e249
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3792367859682389,
+  "epoch": 0.4266413842142688,
   "eval_steps": 20,
-  "global_step": 800,
+  "global_step": 900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6099,6 +6099,766 @@
       "eval_samples_per_second": 5.351,
       "eval_steps_per_second": 0.178,
       "step": 800
+    },
+    {
+      "epoch": 0.3797108319506992,
+      "grad_norm": 5.758953094482422,
+      "learning_rate": 1.5598635898056754e-05,
+      "loss": 0.1493,
+      "step": 801
+    },
+    {
+      "epoch": 0.3801848779331595,
+      "grad_norm": 6.0659661293029785,
+      "learning_rate": 1.5584913398801407e-05,
+      "loss": 0.2677,
+      "step": 802
+    },
+    {
+      "epoch": 0.38065892391561984,
+      "grad_norm": 5.709496974945068,
+      "learning_rate": 1.557117559841013e-05,
+      "loss": 0.1173,
+      "step": 803
+    },
+    {
+      "epoch": 0.3811329698980801,
+      "grad_norm": 3.090986728668213,
+      "learning_rate": 1.5557422534520742e-05,
+      "loss": 0.1074,
+      "step": 804
+    },
+    {
+      "epoch": 0.3816070158805404,
+      "grad_norm": 4.4366254806518555,
+      "learning_rate": 1.5543654244812873e-05,
+      "loss": 0.1772,
+      "step": 805
+    },
+    {
+      "epoch": 0.3820810618630007,
+      "grad_norm": 4.978272914886475,
+      "learning_rate": 1.5529870767007883e-05,
+      "loss": 0.1848,
+      "step": 806
+    },
+    {
+      "epoch": 0.382555107845461,
+      "grad_norm": 6.076455116271973,
+      "learning_rate": 1.5516072138868726e-05,
+      "loss": 0.1394,
+      "step": 807
+    },
+    {
+      "epoch": 0.3830291538279213,
+      "grad_norm": 4.194643497467041,
+      "learning_rate": 1.5502258398199873e-05,
+      "loss": 0.1906,
+      "step": 808
+    },
+    {
+      "epoch": 0.3835031998103816,
+      "grad_norm": 5.475553512573242,
+      "learning_rate": 1.5488429582847194e-05,
+      "loss": 0.1588,
+      "step": 809
+    },
+    {
+      "epoch": 0.3839772457928419,
+      "grad_norm": 4.989933967590332,
+      "learning_rate": 1.5474585730697866e-05,
+      "loss": 0.2083,
+      "step": 810
+    },
+    {
+      "epoch": 0.3844512917753022,
+      "grad_norm": 5.500510215759277,
+      "learning_rate": 1.546072687968026e-05,
+      "loss": 0.128,
+      "step": 811
+    },
+    {
+      "epoch": 0.3849253377577625,
+      "grad_norm": 5.7488884925842285,
+      "learning_rate": 1.5446853067763836e-05,
+      "loss": 0.1925,
+      "step": 812
+    },
+    {
+      "epoch": 0.3853993837402228,
+      "grad_norm": 5.636148929595947,
+      "learning_rate": 1.5432964332959047e-05,
+      "loss": 0.1603,
+      "step": 813
+    },
+    {
+      "epoch": 0.3858734297226831,
+      "grad_norm": 4.349088191986084,
+      "learning_rate": 1.5419060713317233e-05,
+      "loss": 0.0912,
+      "step": 814
+    },
+    {
+      "epoch": 0.3863474757051434,
+      "grad_norm": 5.55099630355835,
+      "learning_rate": 1.5405142246930505e-05,
+      "loss": 0.2131,
+      "step": 815
+    },
+    {
+      "epoch": 0.3868215216876037,
+      "grad_norm": 5.109293460845947,
+      "learning_rate": 1.539120897193166e-05,
+      "loss": 0.1662,
+      "step": 816
+    },
+    {
+      "epoch": 0.387295567670064,
+      "grad_norm": 5.997527122497559,
+      "learning_rate": 1.537726092649406e-05,
+      "loss": 0.1758,
+      "step": 817
+    },
+    {
+      "epoch": 0.38776961365252427,
+      "grad_norm": 7.689452648162842,
+      "learning_rate": 1.536329814883154e-05,
+      "loss": 0.1838,
+      "step": 818
+    },
+    {
+      "epoch": 0.3882436596349846,
+      "grad_norm": 4.673219203948975,
+      "learning_rate": 1.5349320677198288e-05,
+      "loss": 0.2374,
+      "step": 819
+    },
+    {
+      "epoch": 0.3887177056174449,
+      "grad_norm": 5.657802104949951,
+      "learning_rate": 1.533532854988876e-05,
+      "loss": 0.2015,
+      "step": 820
+    },
+    {
+      "epoch": 0.3887177056174449,
+      "eval_accuracy": 0.9911433172302737,
+      "eval_f1": 0.9026548672566371,
+      "eval_loss": 0.02378522790968418,
+      "eval_precision": 0.8360655737704918,
+      "eval_recall": 0.9807692307692307,
+      "eval_runtime": 50.0097,
+      "eval_samples_per_second": 5.419,
+      "eval_steps_per_second": 0.18,
+      "step": 820
+    },
+    {
+      "epoch": 0.3891917515999052,
+      "grad_norm": 5.630519390106201,
+      "learning_rate": 1.532132180523756e-05,
+      "loss": 0.1689,
+      "step": 821
+    },
+    {
+      "epoch": 0.38966579758236547,
+      "grad_norm": 5.623863220214844,
+      "learning_rate": 1.5307300481619334e-05,
+      "loss": 0.1882,
+      "step": 822
+    },
+    {
+      "epoch": 0.3901398435648258,
+      "grad_norm": 4.633841037750244,
+      "learning_rate": 1.529326461744868e-05,
+      "loss": 0.1186,
+      "step": 823
+    },
+    {
+      "epoch": 0.3906138895472861,
+      "grad_norm": 3.7852747440338135,
+      "learning_rate": 1.5279214251180034e-05,
+      "loss": 0.14,
+      "step": 824
+    },
+    {
+      "epoch": 0.3910879355297464,
+      "grad_norm": 7.2971510887146,
+      "learning_rate": 1.5265149421307545e-05,
+      "loss": 0.2072,
+      "step": 825
+    },
+    {
+      "epoch": 0.39156198151220667,
+      "grad_norm": 4.57223653793335,
+      "learning_rate": 1.525107016636501e-05,
+      "loss": 0.1995,
+      "step": 826
+    },
+    {
+      "epoch": 0.392036027494667,
+      "grad_norm": 3.6118946075439453,
+      "learning_rate": 1.5236976524925743e-05,
+      "loss": 0.1314,
+      "step": 827
+    },
+    {
+      "epoch": 0.3925100734771273,
+      "grad_norm": 18.717708587646484,
+      "learning_rate": 1.5222868535602455e-05,
+      "loss": 0.2795,
+      "step": 828
+    },
+    {
+      "epoch": 0.39298411945958756,
+      "grad_norm": 5.223725318908691,
+      "learning_rate": 1.5208746237047196e-05,
+      "loss": 0.167,
+      "step": 829
+    },
+    {
+      "epoch": 0.39345816544204787,
+      "grad_norm": 6.281686782836914,
+      "learning_rate": 1.5194609667951192e-05,
+      "loss": 0.2476,
+      "step": 830
+    },
+    {
+      "epoch": 0.3939322114245082,
+      "grad_norm": 5.123955249786377,
+      "learning_rate": 1.5180458867044783e-05,
+      "loss": 0.1243,
+      "step": 831
+    },
+    {
+      "epoch": 0.3944062574069685,
+      "grad_norm": 5.037649631500244,
+      "learning_rate": 1.5166293873097293e-05,
+      "loss": 0.1332,
+      "step": 832
+    },
+    {
+      "epoch": 0.39488030338942876,
+      "grad_norm": 7.415771961212158,
+      "learning_rate": 1.5152114724916932e-05,
+      "loss": 0.2292,
+      "step": 833
+    },
+    {
+      "epoch": 0.39535434937188907,
+      "grad_norm": 4.953770637512207,
+      "learning_rate": 1.5137921461350693e-05,
+      "loss": 0.1386,
+      "step": 834
+    },
+    {
+      "epoch": 0.3958283953543494,
+      "grad_norm": 4.328691482543945,
+      "learning_rate": 1.512371412128424e-05,
+      "loss": 0.1527,
+      "step": 835
+    },
+    {
+      "epoch": 0.3963024413368097,
+      "grad_norm": 4.749328136444092,
+      "learning_rate": 1.5109492743641791e-05,
+      "loss": 0.1742,
+      "step": 836
+    },
+    {
+      "epoch": 0.39677648731926995,
+      "grad_norm": 3.8692128658294678,
+      "learning_rate": 1.509525736738604e-05,
+      "loss": 0.179,
+      "step": 837
+    },
+    {
+      "epoch": 0.39725053330173027,
+      "grad_norm": 4.17873477935791,
+      "learning_rate": 1.5081008031518027e-05,
+      "loss": 0.1642,
+      "step": 838
+    },
+    {
+      "epoch": 0.3977245792841906,
+      "grad_norm": 3.9594457149505615,
+      "learning_rate": 1.5066744775077036e-05,
+      "loss": 0.1177,
+      "step": 839
+    },
+    {
+      "epoch": 0.39819862526665084,
+      "grad_norm": 7.010453224182129,
+      "learning_rate": 1.505246763714049e-05,
+      "loss": 0.1752,
+      "step": 840
+    },
+    {
+      "epoch": 0.39819862526665084,
+      "eval_accuracy": 0.9895330112721417,
+      "eval_f1": 0.8888888888888888,
+      "eval_loss": 0.025310639292001724,
+      "eval_precision": 0.8,
+      "eval_recall": 1.0,
+      "eval_runtime": 49.9935,
+      "eval_samples_per_second": 5.421,
+      "eval_steps_per_second": 0.18,
+      "step": 840
+    },
+    {
+      "epoch": 0.39867267124911115,
+      "grad_norm": 4.036323070526123,
+      "learning_rate": 1.5038176656823844e-05,
+      "loss": 0.0904,
+      "step": 841
+    },
+    {
+      "epoch": 0.39914671723157147,
+      "grad_norm": 3.6895594596862793,
+      "learning_rate": 1.5023871873280475e-05,
+      "loss": 0.1252,
+      "step": 842
+    },
+    {
+      "epoch": 0.3996207632140318,
+      "grad_norm": 10.439888000488281,
+      "learning_rate": 1.5009553325701582e-05,
+      "loss": 0.2124,
+      "step": 843
+    },
+    {
+      "epoch": 0.40009480919649204,
+      "grad_norm": 4.229457378387451,
+      "learning_rate": 1.499522105331607e-05,
+      "loss": 0.1908,
+      "step": 844
+    },
+    {
+      "epoch": 0.40056885517895235,
+      "grad_norm": 6.920833110809326,
+      "learning_rate": 1.4980875095390447e-05,
+      "loss": 0.2047,
+      "step": 845
+    },
+    {
+      "epoch": 0.40104290116141267,
+      "grad_norm": 2.879361629486084,
+      "learning_rate": 1.4966515491228717e-05,
+      "loss": 0.1008,
+      "step": 846
+    },
+    {
+      "epoch": 0.401516947143873,
+      "grad_norm": 5.6754631996154785,
+      "learning_rate": 1.495214228017227e-05,
+      "loss": 0.1698,
+      "step": 847
+    },
+    {
+      "epoch": 0.40199099312633324,
+      "grad_norm": 4.049121379852295,
+      "learning_rate": 1.4937755501599774e-05,
+      "loss": 0.2256,
+      "step": 848
+    },
+    {
+      "epoch": 0.40246503910879355,
+      "grad_norm": 5.170472145080566,
+      "learning_rate": 1.4923355194927069e-05,
+      "loss": 0.2448,
+      "step": 849
+    },
+    {
+      "epoch": 0.40293908509125387,
+      "grad_norm": 4.938206195831299,
+      "learning_rate": 1.490894139960706e-05,
+      "loss": 0.2282,
+      "step": 850
+    },
+    {
+      "epoch": 0.4034131310737141,
+      "grad_norm": 6.50287389755249,
+      "learning_rate": 1.4894514155129605e-05,
+      "loss": 0.1854,
+      "step": 851
+    },
+    {
+      "epoch": 0.40388717705617444,
+      "grad_norm": 4.345598220825195,
+      "learning_rate": 1.4880073501021407e-05,
+      "loss": 0.1649,
+      "step": 852
+    },
+    {
+      "epoch": 0.40436122303863475,
+      "grad_norm": 6.99996280670166,
+      "learning_rate": 1.4865619476845914e-05,
+      "loss": 0.2396,
+      "step": 853
+    },
+    {
+      "epoch": 0.40483526902109507,
+      "grad_norm": 4.84694766998291,
+      "learning_rate": 1.4851152122203198e-05,
+      "loss": 0.1963,
+      "step": 854
+    },
+    {
+      "epoch": 0.4053093150035553,
+      "grad_norm": 3.466024160385132,
+      "learning_rate": 1.4836671476729862e-05,
+      "loss": 0.1761,
+      "step": 855
+    },
+    {
+      "epoch": 0.40578336098601564,
+      "grad_norm": 4.219127178192139,
+      "learning_rate": 1.482217758009891e-05,
+      "loss": 0.129,
+      "step": 856
+    },
+    {
+      "epoch": 0.40625740696847595,
+      "grad_norm": 3.5250399112701416,
+      "learning_rate": 1.4807670472019657e-05,
+      "loss": 0.1151,
+      "step": 857
+    },
+    {
+      "epoch": 0.40673145295093627,
+      "grad_norm": 4.0963053703308105,
+      "learning_rate": 1.4793150192237615e-05,
+      "loss": 0.1368,
+      "step": 858
+    },
+    {
+      "epoch": 0.4072054989333965,
+      "grad_norm": 5.257630348205566,
+      "learning_rate": 1.4778616780534383e-05,
+      "loss": 0.1364,
+      "step": 859
+    },
+    {
+      "epoch": 0.40767954491585684,
+      "grad_norm": 5.789881706237793,
+      "learning_rate": 1.4764070276727528e-05,
+      "loss": 0.212,
+      "step": 860
+    },
+    {
+      "epoch": 0.40767954491585684,
+      "eval_accuracy": 0.9911433172302737,
+      "eval_f1": 0.9009009009009009,
+      "eval_loss": 0.02501463145017624,
+      "eval_precision": 0.847457627118644,
+      "eval_recall": 0.9615384615384616,
+      "eval_runtime": 50.2315,
+      "eval_samples_per_second": 5.395,
+      "eval_steps_per_second": 0.179,
+      "step": 860
+    },
+    {
+      "epoch": 0.40815359089831715,
+      "grad_norm": 5.214051246643066,
+      "learning_rate": 1.4749510720670506e-05,
+      "loss": 0.1629,
+      "step": 861
+    },
+    {
+      "epoch": 0.4086276368807774,
+      "grad_norm": 5.269729137420654,
+      "learning_rate": 1.473493815225251e-05,
+      "loss": 0.2231,
+      "step": 862
+    },
+    {
+      "epoch": 0.4091016828632377,
+      "grad_norm": 5.787201881408691,
+      "learning_rate": 1.4720352611398394e-05,
+      "loss": 0.237,
+      "step": 863
+    },
+    {
+      "epoch": 0.40957572884569804,
+      "grad_norm": 3.796096086502075,
+      "learning_rate": 1.4705754138068557e-05,
+      "loss": 0.1696,
+      "step": 864
+    },
+    {
+      "epoch": 0.41004977482815835,
+      "grad_norm": 4.975426197052002,
+      "learning_rate": 1.4691142772258826e-05,
+      "loss": 0.1847,
+      "step": 865
+    },
+    {
+      "epoch": 0.4105238208106186,
+      "grad_norm": 3.5773916244506836,
+      "learning_rate": 1.467651855400035e-05,
+      "loss": 0.1927,
+      "step": 866
+    },
+    {
+      "epoch": 0.4109978667930789,
+      "grad_norm": 3.7105495929718018,
+      "learning_rate": 1.466188152335948e-05,
+      "loss": 0.1435,
+      "step": 867
+    },
+    {
+      "epoch": 0.41147191277553924,
+      "grad_norm": 5.359220027923584,
+      "learning_rate": 1.4647231720437687e-05,
+      "loss": 0.2145,
+      "step": 868
+    },
+    {
+      "epoch": 0.41194595875799955,
+      "grad_norm": 3.0884811878204346,
+      "learning_rate": 1.4632569185371424e-05,
+      "loss": 0.1535,
+      "step": 869
+    },
+    {
+      "epoch": 0.4124200047404598,
+      "grad_norm": 8.89234733581543,
+      "learning_rate": 1.4617893958332025e-05,
+      "loss": 0.1519,
+      "step": 870
+    },
+    {
+      "epoch": 0.4128940507229201,
+      "grad_norm": 5.38965368270874,
+      "learning_rate": 1.4603206079525607e-05,
+      "loss": 0.1654,
+      "step": 871
+    },
+    {
+      "epoch": 0.41336809670538044,
+      "grad_norm": 4.978879928588867,
+      "learning_rate": 1.4588505589192936e-05,
+      "loss": 0.1561,
+      "step": 872
+    },
+    {
+      "epoch": 0.4138421426878407,
+      "grad_norm": 5.315103054046631,
+      "learning_rate": 1.4573792527609343e-05,
+      "loss": 0.2338,
+      "step": 873
+    },
+    {
+      "epoch": 0.414316188670301,
+      "grad_norm": 3.3019869327545166,
+      "learning_rate": 1.455906693508459e-05,
+      "loss": 0.1383,
+      "step": 874
+    },
+    {
+      "epoch": 0.4147902346527613,
+      "grad_norm": 5.54788875579834,
+      "learning_rate": 1.4544328851962774e-05,
+      "loss": 0.1859,
+      "step": 875
+    },
+    {
+      "epoch": 0.41526428063522164,
+      "grad_norm": 4.469765663146973,
+      "learning_rate": 1.452957831862222e-05,
+      "loss": 0.1507,
+      "step": 876
+    },
+    {
+      "epoch": 0.4157383266176819,
+      "grad_norm": 5.146998405456543,
+      "learning_rate": 1.4514815375475351e-05,
+      "loss": 0.1831,
+      "step": 877
+    },
+    {
+      "epoch": 0.4162123726001422,
+      "grad_norm": 4.996446132659912,
+      "learning_rate": 1.4500040062968597e-05,
+      "loss": 0.1769,
+      "step": 878
+    },
+    {
+      "epoch": 0.4166864185826025,
+      "grad_norm": 8.464068412780762,
+      "learning_rate": 1.4485252421582274e-05,
+      "loss": 0.3377,
+      "step": 879
+    },
+    {
+      "epoch": 0.41716046456506284,
+      "grad_norm": 5.580779075622559,
+      "learning_rate": 1.4470452491830477e-05,
+      "loss": 0.1556,
+      "step": 880
+    },
+    {
+      "epoch": 0.41716046456506284,
+      "eval_accuracy": 0.9927536231884058,
+      "eval_f1": 0.9158878504672897,
+      "eval_loss": 0.024685567244887352,
+      "eval_precision": 0.8909090909090909,
+      "eval_recall": 0.9423076923076923,
+      "eval_runtime": 49.595,
+      "eval_samples_per_second": 5.464,
+      "eval_steps_per_second": 0.181,
+      "step": 880
+    },
+    {
+      "epoch": 0.4176345105475231,
+      "grad_norm": 4.486780166625977,
+      "learning_rate": 1.4455640314260972e-05,
+      "loss": 0.1155,
+      "step": 881
+    },
+    {
+      "epoch": 0.4181085565299834,
+      "grad_norm": 4.462590217590332,
+      "learning_rate": 1.4440815929455072e-05,
+      "loss": 0.2113,
+      "step": 882
+    },
+    {
+      "epoch": 0.4185826025124437,
+      "grad_norm": 4.029243469238281,
+      "learning_rate": 1.442597937802754e-05,
+      "loss": 0.1435,
+      "step": 883
+    },
+    {
+      "epoch": 0.419056648494904,
+      "grad_norm": 3.141965389251709,
+      "learning_rate": 1.4411130700626467e-05,
+      "loss": 0.117,
+      "step": 884
+    },
+    {
+      "epoch": 0.4195306944773643,
+      "grad_norm": 4.770340919494629,
+      "learning_rate": 1.4396269937933176e-05,
+      "loss": 0.1502,
+      "step": 885
+    },
+    {
+      "epoch": 0.4200047404598246,
+      "grad_norm": 6.025394916534424,
+      "learning_rate": 1.4381397130662092e-05,
+      "loss": 0.1583,
+      "step": 886
+    },
+    {
+      "epoch": 0.4204787864422849,
+      "grad_norm": 4.995217800140381,
+      "learning_rate": 1.4366512319560642e-05,
+      "loss": 0.1963,
+      "step": 887
+    },
+    {
+      "epoch": 0.4209528324247452,
+      "grad_norm": 5.447535037994385,
+      "learning_rate": 1.4351615545409137e-05,
+      "loss": 0.1628,
+      "step": 888
+    },
+    {
+      "epoch": 0.4214268784072055,
+      "grad_norm": 5.995816230773926,
+      "learning_rate": 1.433670684902066e-05,
+      "loss": 0.157,
+      "step": 889
+    },
+    {
+      "epoch": 0.4219009243896658,
+      "grad_norm": 5.347133159637451,
+      "learning_rate": 1.4321786271240975e-05,
+      "loss": 0.1771,
+      "step": 890
+    },
+    {
+      "epoch": 0.4223749703721261,
+      "grad_norm": 9.27304458618164,
+      "learning_rate": 1.4306853852948383e-05,
+      "loss": 0.1654,
+      "step": 891
+    },
+    {
+      "epoch": 0.4228490163545864,
+      "grad_norm": 4.350383758544922,
+      "learning_rate": 1.4291909635053627e-05,
+      "loss": 0.1535,
+      "step": 892
+    },
+    {
+      "epoch": 0.4233230623370467,
+      "grad_norm": 2.4228219985961914,
+      "learning_rate": 1.4276953658499775e-05,
+      "loss": 0.0949,
+      "step": 893
+    },
+    {
+      "epoch": 0.423797108319507,
+      "grad_norm": 6.395793914794922,
+      "learning_rate": 1.4261985964262118e-05,
+      "loss": 0.1808,
+      "step": 894
+    },
+    {
+      "epoch": 0.42427115430196727,
+      "grad_norm": 3.162377119064331,
+      "learning_rate": 1.4247006593348042e-05,
+      "loss": 0.1139,
+      "step": 895
+    },
+    {
+      "epoch": 0.4247452002844276,
+      "grad_norm": 8.321721076965332,
+      "learning_rate": 1.4232015586796938e-05,
+      "loss": 0.2048,
+      "step": 896
+    },
+    {
+      "epoch": 0.4252192462668879,
+      "grad_norm": 2.381802797317505,
+      "learning_rate": 1.4217012985680054e-05,
+      "loss": 0.116,
+      "step": 897
+    },
+    {
+      "epoch": 0.4256932922493482,
+      "grad_norm": 4.9117913246154785,
+      "learning_rate": 1.4201998831100424e-05,
+      "loss": 0.1995,
+      "step": 898
+    },
+    {
+      "epoch": 0.42616733823180847,
+      "grad_norm": 3.578552484512329,
+      "learning_rate": 1.4186973164192722e-05,
+      "loss": 0.1651,
+      "step": 899
+    },
+    {
+      "epoch": 0.4266413842142688,
+      "grad_norm": 3.712299108505249,
+      "learning_rate": 1.417193602612317e-05,
+      "loss": 0.1495,
+      "step": 900
+    },
+    {
+      "epoch": 0.4266413842142688,
+      "eval_accuracy": 0.9919484702093397,
+      "eval_f1": 0.9107142857142857,
+      "eval_loss": 0.014072530902922153,
+      "eval_precision": 0.85,
+      "eval_recall": 0.9807692307692307,
+      "eval_runtime": 49.6759,
+      "eval_samples_per_second": 5.455,
+      "eval_steps_per_second": 0.181,
+      "step": 900
     }
   ],
   "logging_steps": 1,
@@ -6118,7 +6878,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.137990661972951e+17,
+  "total_flos": 2.4024256691673498e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null