Training in progress, step 4900, checkpoint

last-checkpoint/optimizer_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c34835f67b53db567973a16a8e448b8615e6557a11e3149bc2f986c8f31d6c5
+oid sha256:5f48600485612031ae7d08480c42c14f7e55fa5be1fc83e6965daaefac1578ed
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:657f42586acd7d0cc3d14eee3d143d915207926e4ab3c659b16f457345290a41
+oid sha256:286cbc8f9c82356efad32d77e4449b7e7801e820e0deb6b7b98d71b6bab5062f
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:366b39b831a6eea09b408c8b308e80db964da44d412b1ce3886e6e38f75efaaf
+oid sha256:15a67401eee4a37a9e835749bc6e0322123ea3a28cc648bc7dd2a83bb8a7ff4e
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2dd4d5065c33b42bc0eae21c2f3709232ad020152014fd906fb214ddfa1be4f
+oid sha256:1d79e47a4f7904ffa9a17abf53c34f6cf1d1e80be21492c956e18ee92fa28db6
 size 13990904

last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54e380ae70ea12a09363003186ec146215b55131c35cede5d3bfe28602480e6d
+oid sha256:f355e06d917af386e441ef5712d7c0e133dfad797b309c4052962713d7d16998
 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:a8b755716455dff37c8949442d70fcca9b958c59b3c610a43e453634c3dd3033
+oid sha256:3c19f861897d099fe47cd1a922c531ecf1757f1f5ea3dec8b467a7e8a164e0bb
 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:d8b0b75ea4133fbd02adaf69386dae7ad2ec0a988f538f3ea67f84f905b344bc
+oid sha256:9aa3b21cec5e74646c4c466204052f79067da3e431b2f4b21a4083fe0c176bc5
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d159bb2c4b783df772f6462bc8f15cc9a9f382b5fcc5dbecc3c596f2943451a
+oid sha256:884b915c6c74574630f3a660e7ec99212e6cfe4b53864e8e776a5af34aaee44f
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c42037bd30ba4defc1c7fccb0578160842e942d88d2174894d5bd3f306e325fe
+oid sha256:904edbd8679be6e1235f2a13e443d12502a66ba0256e839f5db286dde4aea005
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d37940ed29d6f1dc9ecbe1de9c3ba790e473b166e9c38ac4d556164fafcd9d4d
+oid sha256:0d20b1384e41f54437696db275a705bb18854947da49966fc9d71944162c609a
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd20b0d2fcb8ee11696e9347457e0dfa355fc6e57e65ef561da31e6bee64188b
+oid sha256:faca2a197e8186428ee4d44e91df1468b4c3165b0bec5d79ba6df93402aa5bc7
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7c6d38f3bad3539d8a2815593d811a3100384d85579f0ef61196df21a031ede
+oid sha256:54684be4b97948c650106a3ab42d3c8b9aad7eb30b902bf6652491a516ce11c3
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dae249efb71b99256cc2766bebc4c2ea4fc717992bf904061a330f0cb5408645
+oid sha256:6ce9c32fbaf4f547c1ed5704443d0e621891a337200d3b16de3c4c9fcfdca067
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7082257469568425,
+  "epoch": 0.7229804500184434,
   "eval_steps": 20,
-  "global_step": 4800,
+  "global_step": 4900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -36499,6 +36499,766 @@
       "eval_samples_per_second": 5.965,
       "eval_steps_per_second": 0.205,
       "step": 4800
+    },
+    {
+      "epoch": 0.7083732939874585,
+      "grad_norm": 1.3491781949996948,
+      "learning_rate": 4.747920560733825e-06,
+      "loss": 0.0497,
+      "step": 4801
+    },
+    {
+      "epoch": 0.7085208410180746,
+      "grad_norm": 2.348538398742676,
+      "learning_rate": 4.743537894151535e-06,
+      "loss": 0.0424,
+      "step": 4802
+    },
+    {
+      "epoch": 0.7086683880486905,
+      "grad_norm": 3.854368209838867,
+      "learning_rate": 4.739156622253854e-06,
+      "loss": 0.0865,
+      "step": 4803
+    },
+    {
+      "epoch": 0.7088159350793065,
+      "grad_norm": 2.624882698059082,
+      "learning_rate": 4.7347767462032465e-06,
+      "loss": 0.087,
+      "step": 4804
+    },
+    {
+      "epoch": 0.7089634821099225,
+      "grad_norm": 1.3223381042480469,
+      "learning_rate": 4.730398267161822e-06,
+      "loss": 0.0526,
+      "step": 4805
+    },
+    {
+      "epoch": 0.7091110291405386,
+      "grad_norm": 1.99947190284729,
+      "learning_rate": 4.726021186291309e-06,
+      "loss": 0.0633,
+      "step": 4806
+    },
+    {
+      "epoch": 0.7092585761711545,
+      "grad_norm": 1.5057780742645264,
+      "learning_rate": 4.721645504753059e-06,
+      "loss": 0.0285,
+      "step": 4807
+    },
+    {
+      "epoch": 0.7094061232017705,
+      "grad_norm": 1.374821662902832,
+      "learning_rate": 4.717271223708076e-06,
+      "loss": 0.0353,
+      "step": 4808
+    },
+    {
+      "epoch": 0.7095536702323866,
+      "grad_norm": 1.7715858221054077,
+      "learning_rate": 4.712898344316973e-06,
+      "loss": 0.0333,
+      "step": 4809
+    },
+    {
+      "epoch": 0.7097012172630026,
+      "grad_norm": 4.284231662750244,
+      "learning_rate": 4.708526867739988e-06,
+      "loss": 0.1314,
+      "step": 4810
+    },
+    {
+      "epoch": 0.7098487642936185,
+      "grad_norm": 1.2447797060012817,
+      "learning_rate": 4.704156795137006e-06,
+      "loss": 0.0256,
+      "step": 4811
+    },
+    {
+      "epoch": 0.7099963113242346,
+      "grad_norm": 2.242856502532959,
+      "learning_rate": 4.699788127667517e-06,
+      "loss": 0.0563,
+      "step": 4812
+    },
+    {
+      "epoch": 0.7101438583548506,
+      "grad_norm": 2.6883840560913086,
+      "learning_rate": 4.695420866490655e-06,
+      "loss": 0.1042,
+      "step": 4813
+    },
+    {
+      "epoch": 0.7102914053854666,
+      "grad_norm": 2.614682197570801,
+      "learning_rate": 4.691055012765179e-06,
+      "loss": 0.035,
+      "step": 4814
+    },
+    {
+      "epoch": 0.7104389524160827,
+      "grad_norm": 4.825432300567627,
+      "learning_rate": 4.686690567649461e-06,
+      "loss": 0.0966,
+      "step": 4815
+    },
+    {
+      "epoch": 0.7105864994466986,
+      "grad_norm": 2.8247244358062744,
+      "learning_rate": 4.682327532301518e-06,
+      "loss": 0.0735,
+      "step": 4816
+    },
+    {
+      "epoch": 0.7107340464773146,
+      "grad_norm": 2.1444296836853027,
+      "learning_rate": 4.677965907878976e-06,
+      "loss": 0.0604,
+      "step": 4817
+    },
+    {
+      "epoch": 0.7108815935079307,
+      "grad_norm": 0.9742994904518127,
+      "learning_rate": 4.6736056955391e-06,
+      "loss": 0.0223,
+      "step": 4818
+    },
+    {
+      "epoch": 0.7110291405385467,
+      "grad_norm": 6.483880519866943,
+      "learning_rate": 4.669246896438774e-06,
+      "loss": 0.0939,
+      "step": 4819
+    },
+    {
+      "epoch": 0.7111766875691626,
+      "grad_norm": 1.5703705549240112,
+      "learning_rate": 4.664889511734509e-06,
+      "loss": 0.0171,
+      "step": 4820
+    },
+    {
+      "epoch": 0.7111766875691626,
+      "eval_accuracy": 0.9811866859623734,
+      "eval_f1": 0.9679012345679012,
+      "eval_loss": 0.05624791607260704,
+      "eval_precision": 0.9849246231155779,
+      "eval_recall": 0.9514563106796117,
+      "eval_runtime": 48.9838,
+      "eval_samples_per_second": 5.941,
+      "eval_steps_per_second": 0.204,
+      "step": 4820
+    },
+    {
+      "epoch": 0.7113242345997787,
+      "grad_norm": 1.573594093322754,
+      "learning_rate": 4.660533542582427e-06,
+      "loss": 0.0643,
+      "step": 4821
+    },
+    {
+      "epoch": 0.7114717816303947,
+      "grad_norm": 1.3411532640457153,
+      "learning_rate": 4.656178990138307e-06,
+      "loss": 0.0131,
+      "step": 4822
+    },
+    {
+      "epoch": 0.7116193286610107,
+      "grad_norm": 2.8468737602233887,
+      "learning_rate": 4.651825855557522e-06,
+      "loss": 0.041,
+      "step": 4823
+    },
+    {
+      "epoch": 0.7117668756916267,
+      "grad_norm": 3.8967766761779785,
+      "learning_rate": 4.647474139995075e-06,
+      "loss": 0.051,
+      "step": 4824
+    },
+    {
+      "epoch": 0.7119144227222427,
+      "grad_norm": 4.845344543457031,
+      "learning_rate": 4.643123844605603e-06,
+      "loss": 0.12,
+      "step": 4825
+    },
+    {
+      "epoch": 0.7120619697528587,
+      "grad_norm": 2.19871187210083,
+      "learning_rate": 4.638774970543356e-06,
+      "loss": 0.0703,
+      "step": 4826
+    },
+    {
+      "epoch": 0.7122095167834748,
+      "grad_norm": 2.758091688156128,
+      "learning_rate": 4.634427518962209e-06,
+      "loss": 0.0515,
+      "step": 4827
+    },
+    {
+      "epoch": 0.7123570638140907,
+      "grad_norm": 3.0133373737335205,
+      "learning_rate": 4.630081491015669e-06,
+      "loss": 0.0366,
+      "step": 4828
+    },
+    {
+      "epoch": 0.7125046108447067,
+      "grad_norm": 2.8721578121185303,
+      "learning_rate": 4.625736887856848e-06,
+      "loss": 0.0813,
+      "step": 4829
+    },
+    {
+      "epoch": 0.7126521578753228,
+      "grad_norm": 2.369920253753662,
+      "learning_rate": 4.621393710638496e-06,
+      "loss": 0.0935,
+      "step": 4830
+    },
+    {
+      "epoch": 0.7127997049059388,
+      "grad_norm": 1.4751105308532715,
+      "learning_rate": 4.61705196051297e-06,
+      "loss": 0.021,
+      "step": 4831
+    },
+    {
+      "epoch": 0.7129472519365547,
+      "grad_norm": 1.4269704818725586,
+      "learning_rate": 4.612711638632263e-06,
+      "loss": 0.0262,
+      "step": 4832
+    },
+    {
+      "epoch": 0.7130947989671708,
+      "grad_norm": 3.1407742500305176,
+      "learning_rate": 4.608372746147983e-06,
+      "loss": 0.0233,
+      "step": 4833
+    },
+    {
+      "epoch": 0.7132423459977868,
+      "grad_norm": 2.9399356842041016,
+      "learning_rate": 4.604035284211356e-06,
+      "loss": 0.0394,
+      "step": 4834
+    },
+    {
+      "epoch": 0.7133898930284028,
+      "grad_norm": 2.724482774734497,
+      "learning_rate": 4.5996992539732255e-06,
+      "loss": 0.0161,
+      "step": 4835
+    },
+    {
+      "epoch": 0.7135374400590188,
+      "grad_norm": 2.8107852935791016,
+      "learning_rate": 4.595364656584066e-06,
+      "loss": 0.0552,
+      "step": 4836
+    },
+    {
+      "epoch": 0.7136849870896348,
+      "grad_norm": 1.3565391302108765,
+      "learning_rate": 4.591031493193967e-06,
+      "loss": 0.0463,
+      "step": 4837
+    },
+    {
+      "epoch": 0.7138325341202508,
+      "grad_norm": 1.0748212337493896,
+      "learning_rate": 4.58669976495263e-06,
+      "loss": 0.0237,
+      "step": 4838
+    },
+    {
+      "epoch": 0.7139800811508669,
+      "grad_norm": 2.125095844268799,
+      "learning_rate": 4.58236947300939e-06,
+      "loss": 0.059,
+      "step": 4839
+    },
+    {
+      "epoch": 0.7141276281814829,
+      "grad_norm": 4.943905830383301,
+      "learning_rate": 4.5780406185131866e-06,
+      "loss": 0.0388,
+      "step": 4840
+    },
+    {
+      "epoch": 0.7141276281814829,
+      "eval_accuracy": 0.9811866859623734,
+      "eval_f1": 0.9679012345679012,
+      "eval_loss": 0.05590560659766197,
+      "eval_precision": 0.9849246231155779,
+      "eval_recall": 0.9514563106796117,
+      "eval_runtime": 49.5376,
+      "eval_samples_per_second": 5.874,
+      "eval_steps_per_second": 0.202,
+      "step": 4840
+    },
+    {
+      "epoch": 0.7142751752120988,
+      "grad_norm": 5.2195143699646,
+      "learning_rate": 4.573713202612585e-06,
+      "loss": 0.0585,
+      "step": 4841
+    },
+    {
+      "epoch": 0.7144227222427149,
+      "grad_norm": 2.1044042110443115,
+      "learning_rate": 4.569387226455776e-06,
+      "loss": 0.0464,
+      "step": 4842
+    },
+    {
+      "epoch": 0.7145702692733309,
+      "grad_norm": 3.341923236846924,
+      "learning_rate": 4.565062691190549e-06,
+      "loss": 0.0573,
+      "step": 4843
+    },
+    {
+      "epoch": 0.7147178163039469,
+      "grad_norm": 2.710599899291992,
+      "learning_rate": 4.560739597964334e-06,
+      "loss": 0.0401,
+      "step": 4844
+    },
+    {
+      "epoch": 0.7148653633345629,
+      "grad_norm": 1.703153371810913,
+      "learning_rate": 4.556417947924158e-06,
+      "loss": 0.0293,
+      "step": 4845
+    },
+    {
+      "epoch": 0.7150129103651789,
+      "grad_norm": 1.2568097114562988,
+      "learning_rate": 4.552097742216676e-06,
+      "loss": 0.0319,
+      "step": 4846
+    },
+    {
+      "epoch": 0.7151604573957949,
+      "grad_norm": 1.016923427581787,
+      "learning_rate": 4.5477789819881645e-06,
+      "loss": 0.0239,
+      "step": 4847
+    },
+    {
+      "epoch": 0.715308004426411,
+      "grad_norm": 1.6680554151535034,
+      "learning_rate": 4.543461668384505e-06,
+      "loss": 0.0476,
+      "step": 4848
+    },
+    {
+      "epoch": 0.7154555514570269,
+      "grad_norm": 2.5092504024505615,
+      "learning_rate": 4.539145802551195e-06,
+      "loss": 0.0806,
+      "step": 4849
+    },
+    {
+      "epoch": 0.7156030984876429,
+      "grad_norm": 2.4317209720611572,
+      "learning_rate": 4.5348313856333596e-06,
+      "loss": 0.073,
+      "step": 4850
+    },
+    {
+      "epoch": 0.715750645518259,
+      "grad_norm": 1.3609871864318848,
+      "learning_rate": 4.530518418775734e-06,
+      "loss": 0.0152,
+      "step": 4851
+    },
+    {
+      "epoch": 0.715898192548875,
+      "grad_norm": 3.874760150909424,
+      "learning_rate": 4.526206903122661e-06,
+      "loss": 0.0327,
+      "step": 4852
+    },
+    {
+      "epoch": 0.7160457395794909,
+      "grad_norm": 1.1470457315444946,
+      "learning_rate": 4.521896839818112e-06,
+      "loss": 0.035,
+      "step": 4853
+    },
+    {
+      "epoch": 0.716193286610107,
+      "grad_norm": 2.0697035789489746,
+      "learning_rate": 4.517588230005659e-06,
+      "loss": 0.0278,
+      "step": 4854
+    },
+    {
+      "epoch": 0.716340833640723,
+      "grad_norm": 2.5554862022399902,
+      "learning_rate": 4.5132810748284975e-06,
+      "loss": 0.0793,
+      "step": 4855
+    },
+    {
+      "epoch": 0.716488380671339,
+      "grad_norm": 1.2551517486572266,
+      "learning_rate": 4.5089753754294394e-06,
+      "loss": 0.0272,
+      "step": 4856
+    },
+    {
+      "epoch": 0.716635927701955,
+      "grad_norm": 8.998085975646973,
+      "learning_rate": 4.5046711329509e-06,
+      "loss": 0.028,
+      "step": 4857
+    },
+    {
+      "epoch": 0.716783474732571,
+      "grad_norm": 1.6881085634231567,
+      "learning_rate": 4.500368348534918e-06,
+      "loss": 0.0705,
+      "step": 4858
+    },
+    {
+      "epoch": 0.716931021763187,
+      "grad_norm": 2.618722677230835,
+      "learning_rate": 4.496067023323137e-06,
+      "loss": 0.0557,
+      "step": 4859
+    },
+    {
+      "epoch": 0.717078568793803,
+      "grad_norm": 0.3381759524345398,
+      "learning_rate": 4.491767158456817e-06,
+      "loss": 0.0057,
+      "step": 4860
+    },
+    {
+      "epoch": 0.717078568793803,
+      "eval_accuracy": 0.9768451519536903,
+      "eval_f1": 0.9601990049751243,
+      "eval_loss": 0.05862228944897652,
+      "eval_precision": 0.9846938775510204,
+      "eval_recall": 0.9368932038834952,
+      "eval_runtime": 49.7409,
+      "eval_samples_per_second": 5.85,
+      "eval_steps_per_second": 0.201,
+      "step": 4860
+    },
+    {
+      "epoch": 0.7172261158244191,
+      "grad_norm": 2.75651216506958,
+      "learning_rate": 4.487468755076837e-06,
+      "loss": 0.0498,
+      "step": 4861
+    },
+    {
+      "epoch": 0.717373662855035,
+      "grad_norm": 3.354355573654175,
+      "learning_rate": 4.483171814323679e-06,
+      "loss": 0.0943,
+      "step": 4862
+    },
+    {
+      "epoch": 0.717521209885651,
+      "grad_norm": 3.9032034873962402,
+      "learning_rate": 4.478876337337435e-06,
+      "loss": 0.1044,
+      "step": 4863
+    },
+    {
+      "epoch": 0.7176687569162671,
+      "grad_norm": 1.7555657625198364,
+      "learning_rate": 4.474582325257818e-06,
+      "loss": 0.0443,
+      "step": 4864
+    },
+    {
+      "epoch": 0.7178163039468831,
+      "grad_norm": 3.1032423973083496,
+      "learning_rate": 4.470289779224152e-06,
+      "loss": 0.0742,
+      "step": 4865
+    },
+    {
+      "epoch": 0.717963850977499,
+      "grad_norm": 2.7565388679504395,
+      "learning_rate": 4.46599870037536e-06,
+      "loss": 0.0395,
+      "step": 4866
+    },
+    {
+      "epoch": 0.7181113980081151,
+      "grad_norm": 1.0605816841125488,
+      "learning_rate": 4.461709089849993e-06,
+      "loss": 0.0187,
+      "step": 4867
+    },
+    {
+      "epoch": 0.7182589450387311,
+      "grad_norm": 2.2450878620147705,
+      "learning_rate": 4.457420948786193e-06,
+      "loss": 0.0306,
+      "step": 4868
+    },
+    {
+      "epoch": 0.7184064920693471,
+      "grad_norm": 3.1171584129333496,
+      "learning_rate": 4.453134278321727e-06,
+      "loss": 0.0923,
+      "step": 4869
+    },
+    {
+      "epoch": 0.7185540390999631,
+      "grad_norm": 2.8394124507904053,
+      "learning_rate": 4.448849079593972e-06,
+      "loss": 0.0305,
+      "step": 4870
+    },
+    {
+      "epoch": 0.7187015861305791,
+      "grad_norm": 2.4069812297821045,
+      "learning_rate": 4.4445653537399e-06,
+      "loss": 0.0549,
+      "step": 4871
+    },
+    {
+      "epoch": 0.7188491331611951,
+      "grad_norm": 3.646878242492676,
+      "learning_rate": 4.440283101896113e-06,
+      "loss": 0.0394,
+      "step": 4872
+    },
+    {
+      "epoch": 0.7189966801918112,
+      "grad_norm": 1.8418575525283813,
+      "learning_rate": 4.436002325198801e-06,
+      "loss": 0.0738,
+      "step": 4873
+    },
+    {
+      "epoch": 0.7191442272224271,
+      "grad_norm": 5.827348709106445,
+      "learning_rate": 4.431723024783771e-06,
+      "loss": 0.0814,
+      "step": 4874
+    },
+    {
+      "epoch": 0.7192917742530431,
+      "grad_norm": 2.071404218673706,
+      "learning_rate": 4.427445201786451e-06,
+      "loss": 0.0459,
+      "step": 4875
+    },
+    {
+      "epoch": 0.7194393212836592,
+      "grad_norm": 0.9559571743011475,
+      "learning_rate": 4.423168857341859e-06,
+      "loss": 0.0068,
+      "step": 4876
+    },
+    {
+      "epoch": 0.7195868683142752,
+      "grad_norm": 5.078649044036865,
+      "learning_rate": 4.418893992584624e-06,
+      "loss": 0.086,
+      "step": 4877
+    },
+    {
+      "epoch": 0.7197344153448911,
+      "grad_norm": 1.5742383003234863,
+      "learning_rate": 4.414620608648989e-06,
+      "loss": 0.0372,
+      "step": 4878
+    },
+    {
+      "epoch": 0.7198819623755072,
+      "grad_norm": 2.6624889373779297,
+      "learning_rate": 4.410348706668805e-06,
+      "loss": 0.0686,
+      "step": 4879
+    },
+    {
+      "epoch": 0.7200295094061232,
+      "grad_norm": 2.357564926147461,
+      "learning_rate": 4.406078287777517e-06,
+      "loss": 0.0507,
+      "step": 4880
+    },
+    {
+      "epoch": 0.7200295094061232,
+      "eval_accuracy": 0.975397973950796,
+      "eval_f1": 0.9576059850374065,
+      "eval_loss": 0.05922112986445427,
+      "eval_precision": 0.9846153846153847,
+      "eval_recall": 0.9320388349514563,
+      "eval_runtime": 49.9173,
+      "eval_samples_per_second": 5.83,
+      "eval_steps_per_second": 0.2,
+      "step": 4880
+    },
+    {
+      "epoch": 0.7201770564367392,
+      "grad_norm": 2.5022599697113037,
+      "learning_rate": 4.401809353108194e-06,
+      "loss": 0.0502,
+      "step": 4881
+    },
+    {
+      "epoch": 0.7203246034673553,
+      "grad_norm": 2.529521942138672,
+      "learning_rate": 4.397541903793493e-06,
+      "loss": 0.074,
+      "step": 4882
+    },
+    {
+      "epoch": 0.7204721504979712,
+      "grad_norm": 2.8516416549682617,
+      "learning_rate": 4.393275940965692e-06,
+      "loss": 0.0966,
+      "step": 4883
+    },
+    {
+      "epoch": 0.7206196975285872,
+      "grad_norm": 3.647569179534912,
+      "learning_rate": 4.389011465756672e-06,
+      "loss": 0.0859,
+      "step": 4884
+    },
+    {
+      "epoch": 0.7207672445592033,
+      "grad_norm": 2.2108426094055176,
+      "learning_rate": 4.3847484792979065e-06,
+      "loss": 0.077,
+      "step": 4885
+    },
+    {
+      "epoch": 0.7209147915898193,
+      "grad_norm": 4.508794784545898,
+      "learning_rate": 4.380486982720494e-06,
+      "loss": 0.0146,
+      "step": 4886
+    },
+    {
+      "epoch": 0.7210623386204352,
+      "grad_norm": 1.7417070865631104,
+      "learning_rate": 4.376226977155118e-06,
+      "loss": 0.0699,
+      "step": 4887
+    },
+    {
+      "epoch": 0.7212098856510513,
+      "grad_norm": 3.349015951156616,
+      "learning_rate": 4.37196846373208e-06,
+      "loss": 0.0757,
+      "step": 4888
+    },
+    {
+      "epoch": 0.7213574326816673,
+      "grad_norm": 5.347111225128174,
+      "learning_rate": 4.367711443581286e-06,
+      "loss": 0.1619,
+      "step": 4889
+    },
+    {
+      "epoch": 0.7215049797122833,
+      "grad_norm": 1.6683688163757324,
+      "learning_rate": 4.363455917832231e-06,
+      "loss": 0.0316,
+      "step": 4890
+    },
+    {
+      "epoch": 0.7216525267428993,
+      "grad_norm": 3.199214220046997,
+      "learning_rate": 4.359201887614034e-06,
+      "loss": 0.0764,
+      "step": 4891
+    },
+    {
+      "epoch": 0.7218000737735153,
+      "grad_norm": 2.8147830963134766,
+      "learning_rate": 4.3549493540554e-06,
+      "loss": 0.0564,
+      "step": 4892
+    },
+    {
+      "epoch": 0.7219476208041313,
+      "grad_norm": 2.7976462841033936,
+      "learning_rate": 4.350698318284638e-06,
+      "loss": 0.0635,
+      "step": 4893
+    },
+    {
+      "epoch": 0.7220951678347474,
+      "grad_norm": 2.589905261993408,
+      "learning_rate": 4.346448781429681e-06,
+      "loss": 0.046,
+      "step": 4894
+    },
+    {
+      "epoch": 0.7222427148653633,
+      "grad_norm": 3.977156400680542,
+      "learning_rate": 4.342200744618038e-06,
+      "loss": 0.0791,
+      "step": 4895
+    },
+    {
+      "epoch": 0.7223902618959793,
+      "grad_norm": 2.2973368167877197,
+      "learning_rate": 4.33795420897683e-06,
+      "loss": 0.0559,
+      "step": 4896
+    },
+    {
+      "epoch": 0.7225378089265954,
+      "grad_norm": 2.4549851417541504,
+      "learning_rate": 4.333709175632782e-06,
+      "loss": 0.0492,
+      "step": 4897
+    },
+    {
+      "epoch": 0.7226853559572114,
+      "grad_norm": 1.2905851602554321,
+      "learning_rate": 4.329465645712223e-06,
+      "loss": 0.0361,
+      "step": 4898
+    },
+    {
+      "epoch": 0.7228329029878273,
+      "grad_norm": 1.1179414987564087,
+      "learning_rate": 4.325223620341072e-06,
+      "loss": 0.018,
+      "step": 4899
+    },
+    {
+      "epoch": 0.7229804500184434,
+      "grad_norm": 3.536717653274536,
+      "learning_rate": 4.320983100644861e-06,
+      "loss": 0.0478,
+      "step": 4900
+    },
+    {
+      "epoch": 0.7229804500184434,
+      "eval_accuracy": 0.9811866859623734,
+      "eval_f1": 0.9679012345679012,
+      "eval_loss": 0.056641675531864166,
+      "eval_precision": 0.9849246231155779,
+      "eval_recall": 0.9514563106796117,
+      "eval_runtime": 50.1675,
+      "eval_samples_per_second": 5.801,
+      "eval_steps_per_second": 0.199,
+      "step": 4900
     }
   ],
   "logging_steps": 1,
@@ -36518,7 +37278,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4784399974879724e+18,
+  "total_flos": 1.50930288213282e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null