Training in progress, step 1100, checkpoint

last-checkpoint/optimizer_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cd9f4e1d0bb326b818db1b6faa552753bc4a3328ac93e01b3631a83d08e1c95
+oid sha256:e2283e0a60eecf0e26db089b1ea106db4a8943588d7c5d1ae539887caf2a0623
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c1ce66274008394f36d101e20d4378dd480a6f7db7387a58eed60435a8f39a7
+oid sha256:039e2daa021420447c63254cecab80fa9d8c4955bb82c268ed4412f9d7cc457e
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b3e7a569d804afc7e9af01c045d344bcf8aa04435a748d8f22d80f77f68191f
+oid sha256:3bb386b06abed058c971637632b15f30bf72e3f0fed658811dd9d1879b2cc249
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84f72d90d6d6f96ffde5e12766b8aa3f0ebf70484ff977b4cc1380cfd2635d82
+oid sha256:b690d2a646fe4b43296ed7a11b9ed92846b14116b36ab4f256a0c0a38193fec5
 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:b7ec10706acfd7aebf2e0313a26ad47f112db6494baa4011866a112fa6459782
+oid sha256:40e60cce6b988d761a7cb0a778490b5bef357343f215f4368e74b271a3544add
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d45fd8c4f5cac20eb0715bd7c3583b8b9d6d50be52eb3b819ead289c264bf4c
+oid sha256:8fbc16fe00aa2316ff9c35dc5c163a58bd61d544a0b373903f53b1dd607744f0
 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:cc7bbedf822084a972aaf7dbfdc31778a6b5afdff5f9d51666b28397948c4cf6
+oid sha256:c26b5d36343cbeb9400248846e9572b9226655bba020bfffb57eb55ac503eaa0
 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:dc56dd27c16979078189d0168509b3491fac9a7018e2acd5413b0b5bfb9e62b8
+oid sha256:80e37075e6a4c78861839fc539511c538b95c0905a026bfa2e725cda89b0c3ea
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbefc2a9b5877ac52b5c278c40b832840a445a83b4f45552eae9c8d8fd7025ab
+oid sha256:47c3058111d1013a8c7bee77444904a0475c2f0bffb7d0c4d6c87291a641236d
 size 15088

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f7ee2bc06c634de7d668e8f27eb2c655185598b0005a48f28db9b8c13871cf8
+oid sha256:1ad5b62f0cc16eba86ed43478cd91d2660dc90a4ec6abf69d8eba3dc9fd166bb
 size 15088

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e89f6ffe398cd010021cbea856f31e9f12c086dc22192dd94cd4139ed13bc428
+oid sha256:4b7a7201b10eea93ada67755ff9fd428efa7903fb7a7749a862485dd229f2c71
 size 15088

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cac7e1aa01f996ea4ccf65c0edbca9c2218b27d0fee393e5dadf9e12f0a4ac0
+oid sha256:ccc03cdb9d7cd36d375ad07cb7f8faa863f3ab0b15c5d442b25b00ccb4f627e1
 size 15088

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca19ec64a3f37f86c1a9f3bd1615be54fe5912d912de79a7d3f808a593a2192d
+oid sha256:b064707c1d587f8d90b9fc42a28979d7e7f25a60fc5fe43535927f2c04c08c63
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.847457627118644,
+  "epoch": 0.9322033898305084,
   "eval_steps": 20,
-  "global_step": 1000,
+  "global_step": 1100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7619,6 +7619,766 @@
       "eval_samples_per_second": 5.83,
       "eval_steps_per_second": 0.2,
       "step": 1000
+    },
+    {
+      "epoch": 0.8483050847457627,
+      "grad_norm": 1.054631233215332,
+      "learning_rate": 1.3694792101976938e-06,
+      "loss": 0.0064,
+      "step": 1001
+    },
+    {
+      "epoch": 0.8491525423728814,
+      "grad_norm": 3.1577975749969482,
+      "learning_rate": 1.354574758753363e-06,
+      "loss": 0.0276,
+      "step": 1002
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 2.423903703689575,
+      "learning_rate": 1.339745962155613e-06,
+      "loss": 0.0236,
+      "step": 1003
+    },
+    {
+      "epoch": 0.8508474576271187,
+      "grad_norm": 0.5103369951248169,
+      "learning_rate": 1.324992950169065e-06,
+      "loss": 0.0016,
+      "step": 1004
+    },
+    {
+      "epoch": 0.8516949152542372,
+      "grad_norm": 2.461594343185425,
+      "learning_rate": 1.310315851895162e-06,
+      "loss": 0.0258,
+      "step": 1005
+    },
+    {
+      "epoch": 0.8525423728813559,
+      "grad_norm": 0.4233887195587158,
+      "learning_rate": 1.2957147957710292e-06,
+      "loss": 0.0016,
+      "step": 1006
+    },
+    {
+      "epoch": 0.8533898305084746,
+      "grad_norm": 1.1271721124649048,
+      "learning_rate": 1.28118990956837e-06,
+      "loss": 0.0051,
+      "step": 1007
+    },
+    {
+      "epoch": 0.8542372881355932,
+      "grad_norm": 1.2144718170166016,
+      "learning_rate": 1.2667413203923283e-06,
+      "loss": 0.0059,
+      "step": 1008
+    },
+    {
+      "epoch": 0.8550847457627119,
+      "grad_norm": 0.09200064092874527,
+      "learning_rate": 1.2523691546803872e-06,
+      "loss": 0.0003,
+      "step": 1009
+    },
+    {
+      "epoch": 0.8559322033898306,
+      "grad_norm": 0.7451255917549133,
+      "learning_rate": 1.2380735382012576e-06,
+      "loss": 0.0047,
+      "step": 1010
+    },
+    {
+      "epoch": 0.8567796610169491,
+      "grad_norm": 0.9666259288787842,
+      "learning_rate": 1.2238545960537795e-06,
+      "loss": 0.0044,
+      "step": 1011
+    },
+    {
+      "epoch": 0.8576271186440678,
+      "grad_norm": 0.9461873769760132,
+      "learning_rate": 1.2097124526658277e-06,
+      "loss": 0.0052,
+      "step": 1012
+    },
+    {
+      "epoch": 0.8584745762711864,
+      "grad_norm": 1.253847360610962,
+      "learning_rate": 1.1956472317932211e-06,
+      "loss": 0.0117,
+      "step": 1013
+    },
+    {
+      "epoch": 0.8593220338983051,
+      "grad_norm": 2.8636152744293213,
+      "learning_rate": 1.1816590565186414e-06,
+      "loss": 0.0236,
+      "step": 1014
+    },
+    {
+      "epoch": 0.8601694915254238,
+      "grad_norm": 0.7781552076339722,
+      "learning_rate": 1.1677480492505589e-06,
+      "loss": 0.0068,
+      "step": 1015
+    },
+    {
+      "epoch": 0.8610169491525423,
+      "grad_norm": 2.7591519355773926,
+      "learning_rate": 1.1539143317221524e-06,
+      "loss": 0.0293,
+      "step": 1016
+    },
+    {
+      "epoch": 0.861864406779661,
+      "grad_norm": 1.2667608261108398,
+      "learning_rate": 1.1401580249902566e-06,
+      "loss": 0.0135,
+      "step": 1017
+    },
+    {
+      "epoch": 0.8627118644067797,
+      "grad_norm": 1.1776992082595825,
+      "learning_rate": 1.1264792494342858e-06,
+      "loss": 0.0072,
+      "step": 1018
+    },
+    {
+      "epoch": 0.8635593220338983,
+      "grad_norm": 1.9288878440856934,
+      "learning_rate": 1.112878124755199e-06,
+      "loss": 0.0101,
+      "step": 1019
+    },
+    {
+      "epoch": 0.864406779661017,
+      "grad_norm": 1.5513525009155273,
+      "learning_rate": 1.0993547699744366e-06,
+      "loss": 0.0182,
+      "step": 1020
+    },
+    {
+      "epoch": 0.864406779661017,
+      "eval_accuracy": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 0.00010546201519900933,
+      "eval_precision": 1.0,
+      "eval_recall": 1.0,
+      "eval_runtime": 51.2385,
+      "eval_samples_per_second": 5.699,
+      "eval_steps_per_second": 0.195,
+      "step": 1020
+    },
+    {
+      "epoch": 0.8652542372881356,
+      "grad_norm": 1.8383911848068237,
+      "learning_rate": 1.0859093034328972e-06,
+      "loss": 0.0058,
+      "step": 1021
+    },
+    {
+      "epoch": 0.8661016949152542,
+      "grad_norm": 0.7148596048355103,
+      "learning_rate": 1.0725418427898792e-06,
+      "loss": 0.0033,
+      "step": 1022
+    },
+    {
+      "epoch": 0.8669491525423729,
+      "grad_norm": 0.8727383017539978,
+      "learning_rate": 1.0592525050220692e-06,
+      "loss": 0.006,
+      "step": 1023
+    },
+    {
+      "epoch": 0.8677966101694915,
+      "grad_norm": 1.3725224733352661,
+      "learning_rate": 1.0460414064225099e-06,
+      "loss": 0.007,
+      "step": 1024
+    },
+    {
+      "epoch": 0.8686440677966102,
+      "grad_norm": 0.29742565751075745,
+      "learning_rate": 1.0329086625995843e-06,
+      "loss": 0.0015,
+      "step": 1025
+    },
+    {
+      "epoch": 0.8694915254237288,
+      "grad_norm": 1.752211332321167,
+      "learning_rate": 1.0198543884760049e-06,
+      "loss": 0.0151,
+      "step": 1026
+    },
+    {
+      "epoch": 0.8703389830508474,
+      "grad_norm": 0.8796065449714661,
+      "learning_rate": 1.0068786982878087e-06,
+      "loss": 0.0052,
+      "step": 1027
+    },
+    {
+      "epoch": 0.8711864406779661,
+      "grad_norm": 1.1921021938323975,
+      "learning_rate": 9.939817055833534e-07,
+      "loss": 0.0079,
+      "step": 1028
+    },
+    {
+      "epoch": 0.8720338983050847,
+      "grad_norm": 3.8833506107330322,
+      "learning_rate": 9.811635232223283e-07,
+      "loss": 0.0188,
+      "step": 1029
+    },
+    {
+      "epoch": 0.8728813559322034,
+      "grad_norm": 0.4924924969673157,
+      "learning_rate": 9.684242633747642e-07,
+      "loss": 0.0018,
+      "step": 1030
+    },
+    {
+      "epoch": 0.8737288135593221,
+      "grad_norm": 0.3568030893802643,
+      "learning_rate": 9.55764037520055e-07,
+      "loss": 0.0021,
+      "step": 1031
+    },
+    {
+      "epoch": 0.8745762711864407,
+      "grad_norm": 1.1321516036987305,
+      "learning_rate": 9.43182956445976e-07,
+      "loss": 0.0187,
+      "step": 1032
+    },
+    {
+      "epoch": 0.8754237288135593,
+      "grad_norm": 1.1234910488128662,
+      "learning_rate": 9.306811302477214e-07,
+      "loss": 0.0054,
+      "step": 1033
+    },
+    {
+      "epoch": 0.8762711864406779,
+      "grad_norm": 1.4271575212478638,
+      "learning_rate": 9.182586683269323e-07,
+      "loss": 0.0063,
+      "step": 1034
+    },
+    {
+      "epoch": 0.8771186440677966,
+      "grad_norm": 1.43450129032135,
+      "learning_rate": 9.059156793907542e-07,
+      "loss": 0.0189,
+      "step": 1035
+    },
+    {
+      "epoch": 0.8779661016949153,
+      "grad_norm": 1.4197413921356201,
+      "learning_rate": 8.936522714508678e-07,
+      "loss": 0.0058,
+      "step": 1036
+    },
+    {
+      "epoch": 0.8788135593220339,
+      "grad_norm": 0.9812485575675964,
+      "learning_rate": 8.814685518225552e-07,
+      "loss": 0.0074,
+      "step": 1037
+    },
+    {
+      "epoch": 0.8796610169491526,
+      "grad_norm": 1.7358640432357788,
+      "learning_rate": 8.693646271237577e-07,
+      "loss": 0.0099,
+      "step": 1038
+    },
+    {
+      "epoch": 0.8805084745762712,
+      "grad_norm": 0.25579047203063965,
+      "learning_rate": 8.573406032741438e-07,
+      "loss": 0.0014,
+      "step": 1039
+    },
+    {
+      "epoch": 0.8813559322033898,
+      "grad_norm": 0.7132051587104797,
+      "learning_rate": 8.453965854941748e-07,
+      "loss": 0.0053,
+      "step": 1040
+    },
+    {
+      "epoch": 0.8813559322033898,
+      "eval_accuracy": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 0.00010203008423559368,
+      "eval_precision": 1.0,
+      "eval_recall": 1.0,
+      "eval_runtime": 51.4316,
+      "eval_samples_per_second": 5.677,
+      "eval_steps_per_second": 0.194,
+      "step": 1040
+    },
+    {
+      "epoch": 0.8822033898305085,
+      "grad_norm": 0.3814912736415863,
+      "learning_rate": 8.33532678304203e-07,
+      "loss": 0.0022,
+      "step": 1041
+    },
+    {
+      "epoch": 0.8830508474576271,
+      "grad_norm": 0.48492759466171265,
+      "learning_rate": 8.217489855235338e-07,
+      "loss": 0.0026,
+      "step": 1042
+    },
+    {
+      "epoch": 0.8838983050847458,
+      "grad_norm": 1.3368293046951294,
+      "learning_rate": 8.100456102695342e-07,
+      "loss": 0.0099,
+      "step": 1043
+    },
+    {
+      "epoch": 0.8847457627118644,
+      "grad_norm": 0.33328455686569214,
+      "learning_rate": 7.98422654956722e-07,
+      "loss": 0.0014,
+      "step": 1044
+    },
+    {
+      "epoch": 0.885593220338983,
+      "grad_norm": 2.369331121444702,
+      "learning_rate": 7.868802212958704e-07,
+      "loss": 0.0122,
+      "step": 1045
+    },
+    {
+      "epoch": 0.8864406779661017,
+      "grad_norm": 1.2063324451446533,
+      "learning_rate": 7.754184102931228e-07,
+      "loss": 0.0174,
+      "step": 1046
+    },
+    {
+      "epoch": 0.8872881355932203,
+      "grad_norm": 1.7367677688598633,
+      "learning_rate": 7.640373222491038e-07,
+      "loss": 0.0105,
+      "step": 1047
+    },
+    {
+      "epoch": 0.888135593220339,
+      "grad_norm": 1.0690417289733887,
+      "learning_rate": 7.527370567580416e-07,
+      "loss": 0.0054,
+      "step": 1048
+    },
+    {
+      "epoch": 0.8889830508474577,
+      "grad_norm": 2.0434165000915527,
+      "learning_rate": 7.415177127069029e-07,
+      "loss": 0.0161,
+      "step": 1049
+    },
+    {
+      "epoch": 0.8898305084745762,
+      "grad_norm": 2.049274206161499,
+      "learning_rate": 7.303793882745181e-07,
+      "loss": 0.0097,
+      "step": 1050
+    },
+    {
+      "epoch": 0.8906779661016949,
+      "grad_norm": 0.8351269960403442,
+      "learning_rate": 7.193221809307304e-07,
+      "loss": 0.0063,
+      "step": 1051
+    },
+    {
+      "epoch": 0.8915254237288136,
+      "grad_norm": 0.6742042303085327,
+      "learning_rate": 7.083461874355335e-07,
+      "loss": 0.0047,
+      "step": 1052
+    },
+    {
+      "epoch": 0.8923728813559322,
+      "grad_norm": 2.22886061668396,
+      "learning_rate": 6.974515038382379e-07,
+      "loss": 0.0125,
+      "step": 1053
+    },
+    {
+      "epoch": 0.8932203389830509,
+      "grad_norm": 2.4455456733703613,
+      "learning_rate": 6.866382254766158e-07,
+      "loss": 0.0186,
+      "step": 1054
+    },
+    {
+      "epoch": 0.8940677966101694,
+      "grad_norm": 2.354172945022583,
+      "learning_rate": 6.759064469760823e-07,
+      "loss": 0.0088,
+      "step": 1055
+    },
+    {
+      "epoch": 0.8949152542372881,
+      "grad_norm": 0.5831468105316162,
+      "learning_rate": 6.652562622488535e-07,
+      "loss": 0.0033,
+      "step": 1056
+    },
+    {
+      "epoch": 0.8957627118644068,
+      "grad_norm": 1.065117359161377,
+      "learning_rate": 6.546877644931315e-07,
+      "loss": 0.0129,
+      "step": 1057
+    },
+    {
+      "epoch": 0.8966101694915254,
+      "grad_norm": 1.6987978219985962,
+      "learning_rate": 6.442010461922888e-07,
+      "loss": 0.0125,
+      "step": 1058
+    },
+    {
+      "epoch": 0.8974576271186441,
+      "grad_norm": 0.6148873567581177,
+      "learning_rate": 6.33796199114055e-07,
+      "loss": 0.0027,
+      "step": 1059
+    },
+    {
+      "epoch": 0.8983050847457628,
+      "grad_norm": 1.205604076385498,
+      "learning_rate": 6.234733143097215e-07,
+      "loss": 0.0087,
+      "step": 1060
+    },
+    {
+      "epoch": 0.8983050847457628,
+      "eval_accuracy": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 9.550240793032572e-05,
+      "eval_precision": 1.0,
+      "eval_recall": 1.0,
+      "eval_runtime": 51.1494,
+      "eval_samples_per_second": 5.709,
+      "eval_steps_per_second": 0.196,
+      "step": 1060
+    },
+    {
+      "epoch": 0.8991525423728813,
+      "grad_norm": 3.041253089904785,
+      "learning_rate": 6.132324821133362e-07,
+      "loss": 0.0132,
+      "step": 1061
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.2654479146003723,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 0.001,
+      "step": 1062
+    },
+    {
+      "epoch": 0.9008474576271186,
+      "grad_norm": 0.14473998546600342,
+      "learning_rate": 5.929973332896677e-07,
+      "loss": 0.0009,
+      "step": 1063
+    },
+    {
+      "epoch": 0.9016949152542373,
+      "grad_norm": 0.26278120279312134,
+      "learning_rate": 5.830031937372005e-07,
+      "loss": 0.001,
+      "step": 1064
+    },
+    {
+      "epoch": 0.902542372881356,
+      "grad_norm": 1.2509464025497437,
+      "learning_rate": 5.730914609407634e-07,
+      "loss": 0.006,
+      "step": 1065
+    },
+    {
+      "epoch": 0.9033898305084745,
+      "grad_norm": 0.7587932348251343,
+      "learning_rate": 5.632622216364736e-07,
+      "loss": 0.0052,
+      "step": 1066
+    },
+    {
+      "epoch": 0.9042372881355932,
+      "grad_norm": 0.35142210125923157,
+      "learning_rate": 5.535155618385612e-07,
+      "loss": 0.0022,
+      "step": 1067
+    },
+    {
+      "epoch": 0.9050847457627119,
+      "grad_norm": 1.582571268081665,
+      "learning_rate": 5.438515668386124e-07,
+      "loss": 0.0121,
+      "step": 1068
+    },
+    {
+      "epoch": 0.9059322033898305,
+      "grad_norm": 0.8583706617355347,
+      "learning_rate": 5.342703212048306e-07,
+      "loss": 0.0033,
+      "step": 1069
+    },
+    {
+      "epoch": 0.9067796610169492,
+      "grad_norm": 1.316669225692749,
+      "learning_rate": 5.247719087812897e-07,
+      "loss": 0.0052,
+      "step": 1070
+    },
+    {
+      "epoch": 0.9076271186440678,
+      "grad_norm": 1.5841196775436401,
+      "learning_rate": 5.153564126872002e-07,
+      "loss": 0.0087,
+      "step": 1071
+    },
+    {
+      "epoch": 0.9084745762711864,
+      "grad_norm": 0.39058223366737366,
+      "learning_rate": 5.060239153161872e-07,
+      "loss": 0.0013,
+      "step": 1072
+    },
+    {
+      "epoch": 0.9093220338983051,
+      "grad_norm": 1.9693634510040283,
+      "learning_rate": 4.967744983355638e-07,
+      "loss": 0.0137,
+      "step": 1073
+    },
+    {
+      "epoch": 0.9101694915254237,
+      "grad_norm": 0.7177203297615051,
+      "learning_rate": 4.876082426856177e-07,
+      "loss": 0.0027,
+      "step": 1074
+    },
+    {
+      "epoch": 0.9110169491525424,
+      "grad_norm": 1.0042608976364136,
+      "learning_rate": 4.785252285789077e-07,
+      "loss": 0.021,
+      "step": 1075
+    },
+    {
+      "epoch": 0.911864406779661,
+      "grad_norm": 1.2595585584640503,
+      "learning_rate": 4.695255354995576e-07,
+      "loss": 0.0072,
+      "step": 1076
+    },
+    {
+      "epoch": 0.9127118644067796,
+      "grad_norm": 0.42359045147895813,
+      "learning_rate": 4.6060924220255654e-07,
+      "loss": 0.0029,
+      "step": 1077
+    },
+    {
+      "epoch": 0.9135593220338983,
+      "grad_norm": 1.1068620681762695,
+      "learning_rate": 4.5177642671308087e-07,
+      "loss": 0.0053,
+      "step": 1078
+    },
+    {
+      "epoch": 0.9144067796610169,
+      "grad_norm": 0.701837956905365,
+      "learning_rate": 4.430271663258001e-07,
+      "loss": 0.0047,
+      "step": 1079
+    },
+    {
+      "epoch": 0.9152542372881356,
+      "grad_norm": 0.43353769183158875,
+      "learning_rate": 4.343615376042065e-07,
+      "loss": 0.0017,
+      "step": 1080
+    },
+    {
+      "epoch": 0.9152542372881356,
+      "eval_accuracy": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 9.550563845550641e-05,
+      "eval_precision": 1.0,
+      "eval_recall": 1.0,
+      "eval_runtime": 51.4172,
+      "eval_samples_per_second": 5.679,
+      "eval_steps_per_second": 0.194,
+      "step": 1080
+    },
+    {
+      "epoch": 0.9161016949152543,
+      "grad_norm": 1.3469489812850952,
+      "learning_rate": 4.2577961637994544e-07,
+      "loss": 0.0116,
+      "step": 1081
+    },
+    {
+      "epoch": 0.9169491525423729,
+      "grad_norm": 1.7352731227874756,
+      "learning_rate": 4.172814777521483e-07,
+      "loss": 0.012,
+      "step": 1082
+    },
+    {
+      "epoch": 0.9177966101694915,
+      "grad_norm": 1.6800487041473389,
+      "learning_rate": 4.088671960867785e-07,
+      "loss": 0.0248,
+      "step": 1083
+    },
+    {
+      "epoch": 0.9186440677966101,
+      "grad_norm": 1.4252413511276245,
+      "learning_rate": 4.0053684501598076e-07,
+      "loss": 0.0083,
+      "step": 1084
+    },
+    {
+      "epoch": 0.9194915254237288,
+      "grad_norm": 2.737250804901123,
+      "learning_rate": 3.9229049743743087e-07,
+      "loss": 0.0172,
+      "step": 1085
+    },
+    {
+      "epoch": 0.9203389830508475,
+      "grad_norm": 1.0084242820739746,
+      "learning_rate": 3.8412822551370797e-07,
+      "loss": 0.0093,
+      "step": 1086
+    },
+    {
+      "epoch": 0.9211864406779661,
+      "grad_norm": 1.396519422531128,
+      "learning_rate": 3.7605010067165216e-07,
+      "loss": 0.016,
+      "step": 1087
+    },
+    {
+      "epoch": 0.9220338983050848,
+      "grad_norm": 3.1301279067993164,
+      "learning_rate": 3.68056193601749e-07,
+      "loss": 0.0136,
+      "step": 1088
+    },
+    {
+      "epoch": 0.9228813559322034,
+      "grad_norm": 1.233527421951294,
+      "learning_rate": 3.601465742575061e-07,
+      "loss": 0.0053,
+      "step": 1089
+    },
+    {
+      "epoch": 0.923728813559322,
+      "grad_norm": 1.5494545698165894,
+      "learning_rate": 3.5232131185484075e-07,
+      "loss": 0.0119,
+      "step": 1090
+    },
+    {
+      "epoch": 0.9245762711864407,
+      "grad_norm": 0.7201801538467407,
+      "learning_rate": 3.445804748714732e-07,
+      "loss": 0.0071,
+      "step": 1091
+    },
+    {
+      "epoch": 0.9254237288135593,
+      "grad_norm": 2.4075450897216797,
+      "learning_rate": 3.3692413104633226e-07,
+      "loss": 0.0131,
+      "step": 1092
+    },
+    {
+      "epoch": 0.926271186440678,
+      "grad_norm": 0.0901576578617096,
+      "learning_rate": 3.2935234737895837e-07,
+      "loss": 0.0005,
+      "step": 1093
+    },
+    {
+      "epoch": 0.9271186440677966,
+      "grad_norm": 0.39205268025398254,
+      "learning_rate": 3.2186519012891823e-07,
+      "loss": 0.0027,
+      "step": 1094
+    },
+    {
+      "epoch": 0.9279661016949152,
+      "grad_norm": 1.3817288875579834,
+      "learning_rate": 3.1446272481522544e-07,
+      "loss": 0.0158,
+      "step": 1095
+    },
+    {
+      "epoch": 0.9288135593220339,
+      "grad_norm": 2.032911777496338,
+      "learning_rate": 3.071450162157663e-07,
+      "loss": 0.0121,
+      "step": 1096
+    },
+    {
+      "epoch": 0.9296610169491526,
+      "grad_norm": 1.8076006174087524,
+      "learning_rate": 2.999121283667339e-07,
+      "loss": 0.0057,
+      "step": 1097
+    },
+    {
+      "epoch": 0.9305084745762712,
+      "grad_norm": 1.118698000907898,
+      "learning_rate": 2.9276412456206826e-07,
+      "loss": 0.0037,
+      "step": 1098
+    },
+    {
+      "epoch": 0.9313559322033899,
+      "grad_norm": 0.7791540026664734,
+      "learning_rate": 2.857010673529015e-07,
+      "loss": 0.0063,
+      "step": 1099
+    },
+    {
+      "epoch": 0.9322033898305084,
+      "grad_norm": 1.4591788053512573,
+      "learning_rate": 2.78723018547008e-07,
+      "loss": 0.0058,
+      "step": 1100
+    },
+    {
+      "epoch": 0.9322033898305084,
+      "eval_accuracy": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 0.00010077878687297925,
+      "eval_precision": 1.0,
+      "eval_recall": 1.0,
+      "eval_runtime": 51.6426,
+      "eval_samples_per_second": 5.654,
+      "eval_steps_per_second": 0.194,
+      "step": 1100
     }
   ],
   "logging_steps": 1,
@@ -7638,7 +8398,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.076975196163277e+17,
+  "total_flos": 3.384126928028959e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null