Training in progress, step 4800, checkpoint

last-checkpoint/optimizer_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:103c8a005d78da93637edcfc6762cdbd98eff441bf18a70cfdcdb121a6d5e995
+oid sha256:6c34835f67b53db567973a16a8e448b8615e6557a11e3149bc2f986c8f31d6c5
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef52eca2efdfd0317da72350cf714e81dd5c4c5d6e632cfae2585b523403ada1
+oid sha256:657f42586acd7d0cc3d14eee3d143d915207926e4ab3c659b16f457345290a41
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80a26b2c8f89f3f8b84da07e1aeb9f0709af0650f4ca3fbaa49a4428931c0623
+oid sha256:366b39b831a6eea09b408c8b308e80db964da44d412b1ce3886e6e38f75efaaf
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2017e2fc7b2ccb72a40248569f6bd96f707fa6f4d774b6352ba78c05aa6efb66
+oid sha256:c2dd4d5065c33b42bc0eae21c2f3709232ad020152014fd906fb214ddfa1be4f
 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:e3c12aaec549a143fe7ab549cd17f0036b68dc637327ba8a2a14970c64ab2d5c
+oid sha256:54e380ae70ea12a09363003186ec146215b55131c35cede5d3bfe28602480e6d
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:056e8de7177eb64daa3a5d7255f493db59aa27884b406ae584093d475e73e7a2
+oid sha256:a8b755716455dff37c8949442d70fcca9b958c59b3c610a43e453634c3dd3033
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1507ba4e93643e0633f068f88045cbde052f443f59faece96806379693cb2fbf
+oid sha256:d8b0b75ea4133fbd02adaf69386dae7ad2ec0a988f538f3ea67f84f905b344bc
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34a44e1b6ab0130f79783559f5b15123a73ca143aa800a361ea38ffd1ccdced5
+oid sha256:1d159bb2c4b783df772f6462bc8f15cc9a9f382b5fcc5dbecc3c596f2943451a
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf87269bba14eb85bf189ad70dbfb1d6e89c64d8f3d4ede5526f7021aeeca6dc
+oid sha256:c42037bd30ba4defc1c7fccb0578160842e942d88d2174894d5bd3f306e325fe
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef4bd1fc7ac298649bb4942dcbfaf8517f3c39dec48982740d74838127f865b8
+oid sha256:d37940ed29d6f1dc9ecbe1de9c3ba790e473b166e9c38ac4d556164fafcd9d4d
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7858c279aa486a615cefb424056b504d18349585f4f84b6b4beb0a86ee49f8e2
+oid sha256:dd20b0d2fcb8ee11696e9347457e0dfa355fc6e57e65ef561da31e6bee64188b
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41d8ef42932b56917d4860294c573ed273684d0b32e96c29a3726f5280e43fc6
+oid sha256:f7c6d38f3bad3539d8a2815593d811a3100384d85579f0ef61196df21a031ede
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23eb92592a709d561f028a3a7e8550e3e801df557f06d2c5aad844da3f0ea42f
+oid sha256:dae249efb71b99256cc2766bebc4c2ea4fc717992bf904061a330f0cb5408645
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6934710438952416,
+  "epoch": 0.7082257469568425,
   "eval_steps": 20,
-  "global_step": 4700,
+  "global_step": 4800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -35739,6 +35739,766 @@
       "eval_samples_per_second": 5.876,
       "eval_steps_per_second": 0.202,
       "step": 4700
+    },
+    {
+      "epoch": 0.6936185909258576,
+      "grad_norm": 8.75732707977295,
+      "learning_rate": 5.19302917075707e-06,
+      "loss": 0.0309,
+      "step": 4701
+    },
+    {
+      "epoch": 0.6937661379564736,
+      "grad_norm": 2.6954081058502197,
+      "learning_rate": 5.18851296841836e-06,
+      "loss": 0.0874,
+      "step": 4702
+    },
+    {
+      "epoch": 0.6939136849870896,
+      "grad_norm": 2.049119472503662,
+      "learning_rate": 5.1839980427000695e-06,
+      "loss": 0.1053,
+      "step": 4703
+    },
+    {
+      "epoch": 0.6940612320177056,
+      "grad_norm": 1.6941841840744019,
+      "learning_rate": 5.1794843948001396e-06,
+      "loss": 0.0369,
+      "step": 4704
+    },
+    {
+      "epoch": 0.6942087790483217,
+      "grad_norm": 5.694141387939453,
+      "learning_rate": 5.1749720259161695e-06,
+      "loss": 0.0585,
+      "step": 4705
+    },
+    {
+      "epoch": 0.6943563260789377,
+      "grad_norm": 4.27250862121582,
+      "learning_rate": 5.17046093724541e-06,
+      "loss": 0.0332,
+      "step": 4706
+    },
+    {
+      "epoch": 0.6945038731095536,
+      "grad_norm": 1.8809525966644287,
+      "learning_rate": 5.16595112998477e-06,
+      "loss": 0.0549,
+      "step": 4707
+    },
+    {
+      "epoch": 0.6946514201401697,
+      "grad_norm": 1.3173998594284058,
+      "learning_rate": 5.161442605330844e-06,
+      "loss": 0.0141,
+      "step": 4708
+    },
+    {
+      "epoch": 0.6947989671707857,
+      "grad_norm": 2.760469436645508,
+      "learning_rate": 5.156935364479856e-06,
+      "loss": 0.0847,
+      "step": 4709
+    },
+    {
+      "epoch": 0.6949465142014017,
+      "grad_norm": 1.119059443473816,
+      "learning_rate": 5.152429408627701e-06,
+      "loss": 0.0219,
+      "step": 4710
+    },
+    {
+      "epoch": 0.6950940612320177,
+      "grad_norm": 4.338699817657471,
+      "learning_rate": 5.147924738969942e-06,
+      "loss": 0.0608,
+      "step": 4711
+    },
+    {
+      "epoch": 0.6952416082626337,
+      "grad_norm": 3.4097437858581543,
+      "learning_rate": 5.143421356701781e-06,
+      "loss": 0.0407,
+      "step": 4712
+    },
+    {
+      "epoch": 0.6953891552932497,
+      "grad_norm": 3.3604140281677246,
+      "learning_rate": 5.138919263018096e-06,
+      "loss": 0.0866,
+      "step": 4713
+    },
+    {
+      "epoch": 0.6955367023238658,
+      "grad_norm": 1.3192962408065796,
+      "learning_rate": 5.134418459113422e-06,
+      "loss": 0.0258,
+      "step": 4714
+    },
+    {
+      "epoch": 0.6956842493544817,
+      "grad_norm": 2.792595148086548,
+      "learning_rate": 5.129918946181934e-06,
+      "loss": 0.0566,
+      "step": 4715
+    },
+    {
+      "epoch": 0.6958317963850977,
+      "grad_norm": 1.9875514507293701,
+      "learning_rate": 5.12542072541749e-06,
+      "loss": 0.0257,
+      "step": 4716
+    },
+    {
+      "epoch": 0.6959793434157138,
+      "grad_norm": 1.403470516204834,
+      "learning_rate": 5.120923798013582e-06,
+      "loss": 0.0213,
+      "step": 4717
+    },
+    {
+      "epoch": 0.6961268904463298,
+      "grad_norm": 2.1419942378997803,
+      "learning_rate": 5.116428165163373e-06,
+      "loss": 0.0458,
+      "step": 4718
+    },
+    {
+      "epoch": 0.6962744374769457,
+      "grad_norm": 1.3339232206344604,
+      "learning_rate": 5.111933828059683e-06,
+      "loss": 0.0318,
+      "step": 4719
+    },
+    {
+      "epoch": 0.6964219845075618,
+      "grad_norm": 3.28307843208313,
+      "learning_rate": 5.1074407878949795e-06,
+      "loss": 0.0498,
+      "step": 4720
+    },
+    {
+      "epoch": 0.6964219845075618,
+      "eval_accuracy": 0.9811866859623734,
+      "eval_f1": 0.9679012345679012,
+      "eval_loss": 0.055511847138404846,
+      "eval_precision": 0.9849246231155779,
+      "eval_recall": 0.9514563106796117,
+      "eval_runtime": 52.8324,
+      "eval_samples_per_second": 5.508,
+      "eval_steps_per_second": 0.189,
+      "step": 4720
+    },
+    {
+      "epoch": 0.6965695315381778,
+      "grad_norm": 2.7041454315185547,
+      "learning_rate": 5.102949045861387e-06,
+      "loss": 0.0656,
+      "step": 4721
+    },
+    {
+      "epoch": 0.6967170785687938,
+      "grad_norm": 1.473251223564148,
+      "learning_rate": 5.098458603150691e-06,
+      "loss": 0.023,
+      "step": 4722
+    },
+    {
+      "epoch": 0.6968646255994098,
+      "grad_norm": 1.7501991987228394,
+      "learning_rate": 5.0939694609543355e-06,
+      "loss": 0.0344,
+      "step": 4723
+    },
+    {
+      "epoch": 0.6970121726300258,
+      "grad_norm": 1.2850037813186646,
+      "learning_rate": 5.089481620463407e-06,
+      "loss": 0.024,
+      "step": 4724
+    },
+    {
+      "epoch": 0.6971597196606418,
+      "grad_norm": 2.0505523681640625,
+      "learning_rate": 5.084995082868658e-06,
+      "loss": 0.0433,
+      "step": 4725
+    },
+    {
+      "epoch": 0.6973072666912579,
+      "grad_norm": 1.732586145401001,
+      "learning_rate": 5.0805098493604866e-06,
+      "loss": 0.0381,
+      "step": 4726
+    },
+    {
+      "epoch": 0.6974548137218739,
+      "grad_norm": 0.7503189444541931,
+      "learning_rate": 5.076025921128951e-06,
+      "loss": 0.0183,
+      "step": 4727
+    },
+    {
+      "epoch": 0.6976023607524898,
+      "grad_norm": 1.3052852153778076,
+      "learning_rate": 5.071543299363766e-06,
+      "loss": 0.0256,
+      "step": 4728
+    },
+    {
+      "epoch": 0.6977499077831059,
+      "grad_norm": 1.709081768989563,
+      "learning_rate": 5.067061985254287e-06,
+      "loss": 0.0469,
+      "step": 4729
+    },
+    {
+      "epoch": 0.6978974548137219,
+      "grad_norm": 2.1274194717407227,
+      "learning_rate": 5.062581979989537e-06,
+      "loss": 0.0336,
+      "step": 4730
+    },
+    {
+      "epoch": 0.6980450018443379,
+      "grad_norm": 1.1657981872558594,
+      "learning_rate": 5.058103284758179e-06,
+      "loss": 0.046,
+      "step": 4731
+    },
+    {
+      "epoch": 0.6981925488749539,
+      "grad_norm": 2.0870044231414795,
+      "learning_rate": 5.053625900748538e-06,
+      "loss": 0.0471,
+      "step": 4732
+    },
+    {
+      "epoch": 0.6983400959055699,
+      "grad_norm": 4.870445728302002,
+      "learning_rate": 5.0491498291485915e-06,
+      "loss": 0.1134,
+      "step": 4733
+    },
+    {
+      "epoch": 0.6984876429361859,
+      "grad_norm": 7.5975213050842285,
+      "learning_rate": 5.04467507114596e-06,
+      "loss": 0.1201,
+      "step": 4734
+    },
+    {
+      "epoch": 0.698635189966802,
+      "grad_norm": 1.4844144582748413,
+      "learning_rate": 5.040201627927918e-06,
+      "loss": 0.029,
+      "step": 4735
+    },
+    {
+      "epoch": 0.6987827369974179,
+      "grad_norm": 1.3683654069900513,
+      "learning_rate": 5.035729500681399e-06,
+      "loss": 0.0345,
+      "step": 4736
+    },
+    {
+      "epoch": 0.6989302840280339,
+      "grad_norm": 2.903507947921753,
+      "learning_rate": 5.031258690592982e-06,
+      "loss": 0.0789,
+      "step": 4737
+    },
+    {
+      "epoch": 0.69907783105865,
+      "grad_norm": 1.0233534574508667,
+      "learning_rate": 5.0267891988488895e-06,
+      "loss": 0.0261,
+      "step": 4738
+    },
+    {
+      "epoch": 0.699225378089266,
+      "grad_norm": 4.892428874969482,
+      "learning_rate": 5.022321026635011e-06,
+      "loss": 0.1184,
+      "step": 4739
+    },
+    {
+      "epoch": 0.6993729251198819,
+      "grad_norm": 3.0594170093536377,
+      "learning_rate": 5.017854175136867e-06,
+      "loss": 0.0327,
+      "step": 4740
+    },
+    {
+      "epoch": 0.6993729251198819,
+      "eval_accuracy": 0.9782923299565847,
+      "eval_f1": 0.9627791563275434,
+      "eval_loss": 0.06025285646319389,
+      "eval_precision": 0.9847715736040609,
+      "eval_recall": 0.941747572815534,
+      "eval_runtime": 51.3682,
+      "eval_samples_per_second": 5.665,
+      "eval_steps_per_second": 0.195,
+      "step": 4740
+    },
+    {
+      "epoch": 0.699520472150498,
+      "grad_norm": 2.0277719497680664,
+      "learning_rate": 5.013388645539641e-06,
+      "loss": 0.0156,
+      "step": 4741
+    },
+    {
+      "epoch": 0.699668019181114,
+      "grad_norm": 3.091407537460327,
+      "learning_rate": 5.0089244390281645e-06,
+      "loss": 0.0646,
+      "step": 4742
+    },
+    {
+      "epoch": 0.69981556621173,
+      "grad_norm": 0.809323251247406,
+      "learning_rate": 5.004461556786906e-06,
+      "loss": 0.016,
+      "step": 4743
+    },
+    {
+      "epoch": 0.699963113242346,
+      "grad_norm": 4.385626316070557,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.0838,
+      "step": 4744
+    },
+    {
+      "epoch": 0.700110660272962,
+      "grad_norm": 4.867463111877441,
+      "learning_rate": 4.995539769851218e-06,
+      "loss": 0.115,
+      "step": 4745
+    },
+    {
+      "epoch": 0.700258207303578,
+      "grad_norm": 1.2739475965499878,
+      "learning_rate": 4.9910808675239785e-06,
+      "loss": 0.0246,
+      "step": 4746
+    },
+    {
+      "epoch": 0.700405754334194,
+      "grad_norm": 1.8665733337402344,
+      "learning_rate": 4.986623294201359e-06,
+      "loss": 0.0216,
+      "step": 4747
+    },
+    {
+      "epoch": 0.7005533013648101,
+      "grad_norm": 3.2292773723602295,
+      "learning_rate": 4.982167051066072e-06,
+      "loss": 0.0992,
+      "step": 4748
+    },
+    {
+      "epoch": 0.700700848395426,
+      "grad_norm": 1.9645966291427612,
+      "learning_rate": 4.977712139300479e-06,
+      "loss": 0.06,
+      "step": 4749
+    },
+    {
+      "epoch": 0.700848395426042,
+      "grad_norm": 2.251530647277832,
+      "learning_rate": 4.973258560086595e-06,
+      "loss": 0.0505,
+      "step": 4750
+    },
+    {
+      "epoch": 0.7009959424566581,
+      "grad_norm": 3.1392159461975098,
+      "learning_rate": 4.9688063146060805e-06,
+      "loss": 0.0586,
+      "step": 4751
+    },
+    {
+      "epoch": 0.7011434894872741,
+      "grad_norm": 2.2067291736602783,
+      "learning_rate": 4.964355404040232e-06,
+      "loss": 0.0477,
+      "step": 4752
+    },
+    {
+      "epoch": 0.70129103651789,
+      "grad_norm": 1.406163215637207,
+      "learning_rate": 4.959905829570008e-06,
+      "loss": 0.0291,
+      "step": 4753
+    },
+    {
+      "epoch": 0.7014385835485061,
+      "grad_norm": 4.8565826416015625,
+      "learning_rate": 4.9554575923759926e-06,
+      "loss": 0.0792,
+      "step": 4754
+    },
+    {
+      "epoch": 0.7015861305791221,
+      "grad_norm": 2.68526554107666,
+      "learning_rate": 4.951010693638433e-06,
+      "loss": 0.0391,
+      "step": 4755
+    },
+    {
+      "epoch": 0.7017336776097381,
+      "grad_norm": 1.7152152061462402,
+      "learning_rate": 4.946565134537216e-06,
+      "loss": 0.0265,
+      "step": 4756
+    },
+    {
+      "epoch": 0.7018812246403541,
+      "grad_norm": 6.578200817108154,
+      "learning_rate": 4.942120916251866e-06,
+      "loss": 0.0637,
+      "step": 4757
+    },
+    {
+      "epoch": 0.7020287716709701,
+      "grad_norm": 3.0830886363983154,
+      "learning_rate": 4.937678039961562e-06,
+      "loss": 0.0234,
+      "step": 4758
+    },
+    {
+      "epoch": 0.7021763187015861,
+      "grad_norm": 3.7739224433898926,
+      "learning_rate": 4.933236506845119e-06,
+      "loss": 0.0807,
+      "step": 4759
+    },
+    {
+      "epoch": 0.7023238657322022,
+      "grad_norm": 3.905097723007202,
+      "learning_rate": 4.928796318080991e-06,
+      "loss": 0.0637,
+      "step": 4760
+    },
+    {
+      "epoch": 0.7023238657322022,
+      "eval_accuracy": 0.9797395079594791,
+      "eval_f1": 0.9655172413793104,
+      "eval_loss": 0.05525914207100868,
+      "eval_precision": 0.98,
+      "eval_recall": 0.9514563106796117,
+      "eval_runtime": 49.4588,
+      "eval_samples_per_second": 5.884,
+      "eval_steps_per_second": 0.202,
+      "step": 4760
+    },
+    {
+      "epoch": 0.7024714127628181,
+      "grad_norm": 9.33144474029541,
+      "learning_rate": 4.924357474847299e-06,
+      "loss": 0.0732,
+      "step": 4761
+    },
+    {
+      "epoch": 0.7026189597934341,
+      "grad_norm": 2.88041615486145,
+      "learning_rate": 4.91991997832178e-06,
+      "loss": 0.0888,
+      "step": 4762
+    },
+    {
+      "epoch": 0.7027665068240502,
+      "grad_norm": 4.127414226531982,
+      "learning_rate": 4.9154838296818246e-06,
+      "loss": 0.0478,
+      "step": 4763
+    },
+    {
+      "epoch": 0.7029140538546662,
+      "grad_norm": 2.960581064224243,
+      "learning_rate": 4.911049030104466e-06,
+      "loss": 0.0557,
+      "step": 4764
+    },
+    {
+      "epoch": 0.7030616008852821,
+      "grad_norm": 2.913341999053955,
+      "learning_rate": 4.906615580766384e-06,
+      "loss": 0.0587,
+      "step": 4765
+    },
+    {
+      "epoch": 0.7032091479158982,
+      "grad_norm": 2.4078097343444824,
+      "learning_rate": 4.902183482843888e-06,
+      "loss": 0.041,
+      "step": 4766
+    },
+    {
+      "epoch": 0.7033566949465142,
+      "grad_norm": 4.419480323791504,
+      "learning_rate": 4.897752737512944e-06,
+      "loss": 0.0448,
+      "step": 4767
+    },
+    {
+      "epoch": 0.7035042419771302,
+      "grad_norm": 2.7044637203216553,
+      "learning_rate": 4.8933233459491424e-06,
+      "loss": 0.0855,
+      "step": 4768
+    },
+    {
+      "epoch": 0.7036517890077462,
+      "grad_norm": 3.614534378051758,
+      "learning_rate": 4.888895309327728e-06,
+      "loss": 0.0531,
+      "step": 4769
+    },
+    {
+      "epoch": 0.7037993360383622,
+      "grad_norm": 5.617615699768066,
+      "learning_rate": 4.884468628823583e-06,
+      "loss": 0.0801,
+      "step": 4770
+    },
+    {
+      "epoch": 0.7039468830689782,
+      "grad_norm": 1.2464123964309692,
+      "learning_rate": 4.880043305611224e-06,
+      "loss": 0.0223,
+      "step": 4771
+    },
+    {
+      "epoch": 0.7040944300995943,
+      "grad_norm": 3.384556770324707,
+      "learning_rate": 4.875619340864815e-06,
+      "loss": 0.0683,
+      "step": 4772
+    },
+    {
+      "epoch": 0.7042419771302103,
+      "grad_norm": 3.4770638942718506,
+      "learning_rate": 4.871196735758153e-06,
+      "loss": 0.1092,
+      "step": 4773
+    },
+    {
+      "epoch": 0.7043895241608262,
+      "grad_norm": 3.406653642654419,
+      "learning_rate": 4.866775491464676e-06,
+      "loss": 0.1264,
+      "step": 4774
+    },
+    {
+      "epoch": 0.7045370711914423,
+      "grad_norm": 4.548017501831055,
+      "learning_rate": 4.86235560915747e-06,
+      "loss": 0.0511,
+      "step": 4775
+    },
+    {
+      "epoch": 0.7046846182220583,
+      "grad_norm": 1.751783847808838,
+      "learning_rate": 4.857937090009243e-06,
+      "loss": 0.0455,
+      "step": 4776
+    },
+    {
+      "epoch": 0.7048321652526743,
+      "grad_norm": 2.5198867321014404,
+      "learning_rate": 4.853519935192357e-06,
+      "loss": 0.0956,
+      "step": 4777
+    },
+    {
+      "epoch": 0.7049797122832903,
+      "grad_norm": 2.1479275226593018,
+      "learning_rate": 4.849104145878803e-06,
+      "loss": 0.0538,
+      "step": 4778
+    },
+    {
+      "epoch": 0.7051272593139063,
+      "grad_norm": 3.9840872287750244,
+      "learning_rate": 4.844689723240202e-06,
+      "loss": 0.0641,
+      "step": 4779
+    },
+    {
+      "epoch": 0.7052748063445223,
+      "grad_norm": 1.1084744930267334,
+      "learning_rate": 4.8402766684478396e-06,
+      "loss": 0.0089,
+      "step": 4780
+    },
+    {
+      "epoch": 0.7052748063445223,
+      "eval_accuracy": 0.9768451519536903,
+      "eval_f1": 0.9601990049751243,
+      "eval_loss": 0.06107376888394356,
+      "eval_precision": 0.9846938775510204,
+      "eval_recall": 0.9368932038834952,
+      "eval_runtime": 50.0538,
+      "eval_samples_per_second": 5.814,
+      "eval_steps_per_second": 0.2,
+      "step": 4780
+    },
+    {
+      "epoch": 0.7054223533751384,
+      "grad_norm": 1.3147999048233032,
+      "learning_rate": 4.835864982672612e-06,
+      "loss": 0.0576,
+      "step": 4781
+    },
+    {
+      "epoch": 0.7055699004057543,
+      "grad_norm": 1.7662733793258667,
+      "learning_rate": 4.831454667085059e-06,
+      "loss": 0.0417,
+      "step": 4782
+    },
+    {
+      "epoch": 0.7057174474363703,
+      "grad_norm": 2.976698398590088,
+      "learning_rate": 4.827045722855364e-06,
+      "loss": 0.1089,
+      "step": 4783
+    },
+    {
+      "epoch": 0.7058649944669864,
+      "grad_norm": 1.1642670631408691,
+      "learning_rate": 4.822638151153341e-06,
+      "loss": 0.0158,
+      "step": 4784
+    },
+    {
+      "epoch": 0.7060125414976024,
+      "grad_norm": 2.3276305198669434,
+      "learning_rate": 4.818231953148437e-06,
+      "loss": 0.0227,
+      "step": 4785
+    },
+    {
+      "epoch": 0.7061600885282183,
+      "grad_norm": 3.0932188034057617,
+      "learning_rate": 4.813827130009744e-06,
+      "loss": 0.0716,
+      "step": 4786
+    },
+    {
+      "epoch": 0.7063076355588344,
+      "grad_norm": 3.571537971496582,
+      "learning_rate": 4.809423682905977e-06,
+      "loss": 0.0715,
+      "step": 4787
+    },
+    {
+      "epoch": 0.7064551825894504,
+      "grad_norm": 3.9377129077911377,
+      "learning_rate": 4.805021613005494e-06,
+      "loss": 0.0279,
+      "step": 4788
+    },
+    {
+      "epoch": 0.7066027296200664,
+      "grad_norm": 2.9944138526916504,
+      "learning_rate": 4.80062092147629e-06,
+      "loss": 0.0664,
+      "step": 4789
+    },
+    {
+      "epoch": 0.7067502766506824,
+      "grad_norm": 1.9466123580932617,
+      "learning_rate": 4.796221609485983e-06,
+      "loss": 0.0783,
+      "step": 4790
+    },
+    {
+      "epoch": 0.7068978236812984,
+      "grad_norm": 1.0460115671157837,
+      "learning_rate": 4.791823678201841e-06,
+      "loss": 0.0294,
+      "step": 4791
+    },
+    {
+      "epoch": 0.7070453707119144,
+      "grad_norm": 2.0468013286590576,
+      "learning_rate": 4.78742712879075e-06,
+      "loss": 0.0377,
+      "step": 4792
+    },
+    {
+      "epoch": 0.7071929177425305,
+      "grad_norm": 1.687163233757019,
+      "learning_rate": 4.783031962419231e-06,
+      "loss": 0.0272,
+      "step": 4793
+    },
+    {
+      "epoch": 0.7073404647731465,
+      "grad_norm": 2.560441017150879,
+      "learning_rate": 4.778638180253456e-06,
+      "loss": 0.0734,
+      "step": 4794
+    },
+    {
+      "epoch": 0.7074880118037624,
+      "grad_norm": 2.3611509799957275,
+      "learning_rate": 4.774245783459212e-06,
+      "loss": 0.0925,
+      "step": 4795
+    },
+    {
+      "epoch": 0.7076355588343785,
+      "grad_norm": 1.7989883422851562,
+      "learning_rate": 4.769854773201915e-06,
+      "loss": 0.0644,
+      "step": 4796
+    },
+    {
+      "epoch": 0.7077831058649945,
+      "grad_norm": 2.3656089305877686,
+      "learning_rate": 4.765465150646633e-06,
+      "loss": 0.0647,
+      "step": 4797
+    },
+    {
+      "epoch": 0.7079306528956105,
+      "grad_norm": 2.227722406387329,
+      "learning_rate": 4.761076916958045e-06,
+      "loss": 0.0739,
+      "step": 4798
+    },
+    {
+      "epoch": 0.7080781999262264,
+      "grad_norm": 1.5509002208709717,
+      "learning_rate": 4.756690073300475e-06,
+      "loss": 0.0793,
+      "step": 4799
+    },
+    {
+      "epoch": 0.7082257469568425,
+      "grad_norm": 2.06139874458313,
+      "learning_rate": 4.752304620837876e-06,
+      "loss": 0.0219,
+      "step": 4800
+    },
+    {
+      "epoch": 0.7082257469568425,
+      "eval_accuracy": 0.9797395079594791,
+      "eval_f1": 0.9655172413793104,
+      "eval_loss": 0.057671889662742615,
+      "eval_precision": 0.98,
+      "eval_recall": 0.9514563106796117,
+      "eval_runtime": 48.7845,
+      "eval_samples_per_second": 5.965,
+      "eval_steps_per_second": 0.205,
+      "step": 4800
     }
   ],
   "logging_steps": 1,
@@ -35758,7 +36518,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4479325969514496e+18,
+  "total_flos": 1.4784399974879724e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null