Training in progress, step 800, checkpoint

last-checkpoint/optimizer_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7dc1d8e3e4567fe89f4044c634b8f92aedf608d5bdd3f24fc45d9218d18c608
+oid sha256:690953a5f1eaa9653131c0bd57c0088778a2758f6f1caff67bc9dc9bd0a61e4e
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fa097179e7a3cbf7bef3aa37244226bfd1640b93c7ba0b5dfaa41fa616ac02a
+oid sha256:961a2146c9b2e620d54c67901bd3fa375b0dd4b3895406d10bf2578c5745f6ec
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ed962c5c5afe2495377b16a9858edd276c71d561e3acc283b688b0a7992d8b8
+oid sha256:d6e7156894345a02a9422f425abf2ddc88061246f26736af17b7bd221ea2b39c
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b4f176ea9f6443c51ec492b348b90b111f939183a5e003fcf58ccce5a48bed8
+oid sha256:afb3878b0710bfa44676e56faea2bf2e81a1c4bc0b34feb980fc568965e9b5bf
 size 13990904

last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e1032191a70fdd167493a8a8fad09fb846d227558db21ec9589296a5451c68d
+oid sha256:d17c8c706eb940a9d1d5520139b6ffe5a44eb3dd61f2326391f6febfc3a6784f
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43a2e4e249d34019134215ddaa4cc63e8644939816a9a88ec74d584e3f0992dc
+oid sha256:2101a5cc6a3e4ee7d9bcd0e452c1b7b0e0ae6c681cf45975f0c718f88b871286
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14dadeb199fe580ea06456c94dcbb2d45ed31e34770c0b224e435256b01449ac
+oid sha256:03595f74c1fc252124eeec1b051b356f6d7bf67292b9806a2f8674da24f88c10
 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:bd840616de0e70d365cbe915046e9309ff83ea7be6461314be0447bd565a18fc
+oid sha256:b14a06466128fc4e8a81dd91b128a90acb8f65c2f692c8d576ff2e0ea82b7812
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f4b633cac6d9b72a3e5d722d9f2722a25aaa75c4863f524e50216508a581110
+oid sha256:037251a482261d469d05ca212322fd7a8b0d86b1e9774acdb0dd0d30ed213fb4
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b00b812fe39f4d94693255c049b0abd4bfba391cf4f816905b3d288faf6ee1ba
+oid sha256:971deb5c5f50d793d58f55fcc23e2e2e3d0e3e15819213e61585330da863b511
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8934e21fbebe2892e28c801cf4e90276a2f5fc0d5159b41c7d9ebdd5b89cbbbd
+oid sha256:6969e1b0dfca6ead716e7d65a7048792f64786424a159e6ca34b0c6558b3ebd0
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c08fecc49906d862bfc6e72f4697782e40b17c8a512b907777ac3c47be4f8aa5
+oid sha256:26ac0fcb20e2693146b5db8fdd7935ee7136850497cc891b3eff53fc7c189e4b
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:328d400156bec7fe19b325dd69ca88353a35391b51331286aebee3364fe74ad0
+oid sha256:2ff85c01ce8c147a5568f0e98607017d923cd6d903d76df137d87352cddf54da
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8663366336633663,
+  "epoch": 0.9900990099009901,
   "eval_steps": 20,
-  "global_step": 700,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5339,6 +5339,766 @@
       "eval_samples_per_second": 5.719,
       "eval_steps_per_second": 0.186,
       "step": 700
+    },
+    {
+      "epoch": 0.8675742574257426,
+      "grad_norm": 4.760046005249023,
+      "learning_rate": 1.0500673022258923e-06,
+      "loss": 0.1807,
+      "step": 701
+    },
+    {
+      "epoch": 0.8688118811881188,
+      "grad_norm": 3.5298335552215576,
+      "learning_rate": 1.030874440453944e-06,
+      "loss": 0.1995,
+      "step": 702
+    },
+    {
+      "epoch": 0.870049504950495,
+      "grad_norm": 5.2245049476623535,
+      "learning_rate": 1.0118490653919855e-06,
+      "loss": 0.2404,
+      "step": 703
+    },
+    {
+      "epoch": 0.8712871287128713,
+      "grad_norm": 3.6648762226104736,
+      "learning_rate": 9.92991532314057e-07,
+      "loss": 0.1154,
+      "step": 704
+    },
+    {
+      "epoch": 0.8725247524752475,
+      "grad_norm": 6.1605424880981445,
+      "learning_rate": 9.743021933599695e-07,
+      "loss": 0.2483,
+      "step": 705
+    },
+    {
+      "epoch": 0.8737623762376238,
+      "grad_norm": 4.078556060791016,
+      "learning_rate": 9.557813975287266e-07,
+      "loss": 0.2285,
+      "step": 706
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 4.299773216247559,
+      "learning_rate": 9.374294906720083e-07,
+      "loss": 0.1815,
+      "step": 707
+    },
+    {
+      "epoch": 0.8762376237623762,
+      "grad_norm": 4.190319061279297,
+      "learning_rate": 9.192468154877187e-07,
+      "loss": 0.2049,
+      "step": 708
+    },
+    {
+      "epoch": 0.8774752475247525,
+      "grad_norm": 6.507383823394775,
+      "learning_rate": 9.012337115135772e-07,
+      "loss": 0.2033,
+      "step": 709
+    },
+    {
+      "epoch": 0.8787128712871287,
+      "grad_norm": 4.297817707061768,
+      "learning_rate": 8.833905151207833e-07,
+      "loss": 0.1332,
+      "step": 710
+    },
+    {
+      "epoch": 0.879950495049505,
+      "grad_norm": 4.102233409881592,
+      "learning_rate": 8.657175595077317e-07,
+      "loss": 0.1851,
+      "step": 711
+    },
+    {
+      "epoch": 0.8811881188118812,
+      "grad_norm": 7.134310722351074,
+      "learning_rate": 8.482151746937983e-07,
+      "loss": 0.1696,
+      "step": 712
+    },
+    {
+      "epoch": 0.8824257425742574,
+      "grad_norm": 4.428358554840088,
+      "learning_rate": 8.308836875131665e-07,
+      "loss": 0.2061,
+      "step": 713
+    },
+    {
+      "epoch": 0.8836633663366337,
+      "grad_norm": 3.750676393508911,
+      "learning_rate": 8.137234216087353e-07,
+      "loss": 0.1409,
+      "step": 714
+    },
+    {
+      "epoch": 0.8849009900990099,
+      "grad_norm": 4.440266132354736,
+      "learning_rate": 7.967346974260626e-07,
+      "loss": 0.1741,
+      "step": 715
+    },
+    {
+      "epoch": 0.8861386138613861,
+      "grad_norm": 4.9036736488342285,
+      "learning_rate": 7.799178322073941e-07,
+      "loss": 0.1559,
+      "step": 716
+    },
+    {
+      "epoch": 0.8873762376237624,
+      "grad_norm": 4.0620856285095215,
+      "learning_rate": 7.632731399857329e-07,
+      "loss": 0.1934,
+      "step": 717
+    },
+    {
+      "epoch": 0.8886138613861386,
+      "grad_norm": 4.675508975982666,
+      "learning_rate": 7.468009315789748e-07,
+      "loss": 0.176,
+      "step": 718
+    },
+    {
+      "epoch": 0.8898514851485149,
+      "grad_norm": 4.654139041900635,
+      "learning_rate": 7.305015145841055e-07,
+      "loss": 0.1992,
+      "step": 719
+    },
+    {
+      "epoch": 0.8910891089108911,
+      "grad_norm": 5.478711128234863,
+      "learning_rate": 7.143751933714583e-07,
+      "loss": 0.2218,
+      "step": 720
+    },
+    {
+      "epoch": 0.8910891089108911,
+      "eval_accuracy": 0.8625277161862528,
+      "eval_f1": 0.7181818181818181,
+      "eval_loss": 0.29504844546318054,
+      "eval_precision": 0.8449197860962567,
+      "eval_recall": 0.6245059288537549,
+      "eval_runtime": 48.4336,
+      "eval_samples_per_second": 5.699,
+      "eval_steps_per_second": 0.186,
+      "step": 720
+    },
+    {
+      "epoch": 0.8923267326732673,
+      "grad_norm": 4.685728073120117,
+      "learning_rate": 6.984222690790277e-07,
+      "loss": 0.1942,
+      "step": 721
+    },
+    {
+      "epoch": 0.8935643564356436,
+      "grad_norm": 4.345710754394531,
+      "learning_rate": 6.826430396068451e-07,
+      "loss": 0.1774,
+      "step": 722
+    },
+    {
+      "epoch": 0.8948019801980198,
+      "grad_norm": 4.9782328605651855,
+      "learning_rate": 6.67037799611423e-07,
+      "loss": 0.1819,
+      "step": 723
+    },
+    {
+      "epoch": 0.8960396039603961,
+      "grad_norm": 6.226649284362793,
+      "learning_rate": 6.516068405002441e-07,
+      "loss": 0.1995,
+      "step": 724
+    },
+    {
+      "epoch": 0.8972772277227723,
+      "grad_norm": 3.8088414669036865,
+      "learning_rate": 6.363504504263207e-07,
+      "loss": 0.1909,
+      "step": 725
+    },
+    {
+      "epoch": 0.8985148514851485,
+      "grad_norm": 3.8853421211242676,
+      "learning_rate": 6.212689142828232e-07,
+      "loss": 0.1821,
+      "step": 726
+    },
+    {
+      "epoch": 0.8997524752475248,
+      "grad_norm": 3.680631160736084,
+      "learning_rate": 6.063625136977447e-07,
+      "loss": 0.1419,
+      "step": 727
+    },
+    {
+      "epoch": 0.900990099009901,
+      "grad_norm": 4.0216217041015625,
+      "learning_rate": 5.916315270286588e-07,
+      "loss": 0.1715,
+      "step": 728
+    },
+    {
+      "epoch": 0.9022277227722773,
+      "grad_norm": 5.727372646331787,
+      "learning_rate": 5.770762293575083e-07,
+      "loss": 0.3295,
+      "step": 729
+    },
+    {
+      "epoch": 0.9034653465346535,
+      "grad_norm": 4.530044078826904,
+      "learning_rate": 5.626968924854714e-07,
+      "loss": 0.1704,
+      "step": 730
+    },
+    {
+      "epoch": 0.9047029702970297,
+      "grad_norm": 7.712387561798096,
+      "learning_rate": 5.484937849278937e-07,
+      "loss": 0.205,
+      "step": 731
+    },
+    {
+      "epoch": 0.905940594059406,
+      "grad_norm": 5.130886554718018,
+      "learning_rate": 5.344671719092664e-07,
+      "loss": 0.1432,
+      "step": 732
+    },
+    {
+      "epoch": 0.9071782178217822,
+      "grad_norm": 4.739104270935059,
+      "learning_rate": 5.206173153582705e-07,
+      "loss": 0.2583,
+      "step": 733
+    },
+    {
+      "epoch": 0.9084158415841584,
+      "grad_norm": 3.7045702934265137,
+      "learning_rate": 5.069444739029006e-07,
+      "loss": 0.1193,
+      "step": 734
+    },
+    {
+      "epoch": 0.9096534653465347,
+      "grad_norm": 3.3528637886047363,
+      "learning_rate": 4.934489028656164e-07,
+      "loss": 0.1153,
+      "step": 735
+    },
+    {
+      "epoch": 0.9108910891089109,
+      "grad_norm": 3.305149793624878,
+      "learning_rate": 4.801308542585892e-07,
+      "loss": 0.144,
+      "step": 736
+    },
+    {
+      "epoch": 0.9121287128712872,
+      "grad_norm": 4.803959369659424,
+      "learning_rate": 4.669905767789884e-07,
+      "loss": 0.1267,
+      "step": 737
+    },
+    {
+      "epoch": 0.9133663366336634,
+      "grad_norm": 5.374501705169678,
+      "learning_rate": 4.54028315804339e-07,
+      "loss": 0.1991,
+      "step": 738
+    },
+    {
+      "epoch": 0.9146039603960396,
+      "grad_norm": 5.532665729522705,
+      "learning_rate": 4.4124431338794403e-07,
+      "loss": 0.2528,
+      "step": 739
+    },
+    {
+      "epoch": 0.9158415841584159,
+      "grad_norm": 3.2962238788604736,
+      "learning_rate": 4.2863880825435687e-07,
+      "loss": 0.1608,
+      "step": 740
+    },
+    {
+      "epoch": 0.9158415841584159,
+      "eval_accuracy": 0.8603104212860311,
+      "eval_f1": 0.7096774193548387,
+      "eval_loss": 0.2995334267616272,
+      "eval_precision": 0.850828729281768,
+      "eval_recall": 0.6086956521739131,
+      "eval_runtime": 50.016,
+      "eval_samples_per_second": 5.518,
+      "eval_steps_per_second": 0.18,
+      "step": 740
+    },
+    {
+      "epoch": 0.9170792079207921,
+      "grad_norm": 3.7142422199249268,
+      "learning_rate": 4.162120357949284e-07,
+      "loss": 0.1256,
+      "step": 741
+    },
+    {
+      "epoch": 0.9183168316831684,
+      "grad_norm": 6.413259029388428,
+      "learning_rate": 4.039642280634104e-07,
+      "loss": 0.2582,
+      "step": 742
+    },
+    {
+      "epoch": 0.9195544554455446,
+      "grad_norm": 8.874350547790527,
+      "learning_rate": 3.9189561377162343e-07,
+      "loss": 0.3466,
+      "step": 743
+    },
+    {
+      "epoch": 0.9207920792079208,
+      "grad_norm": 3.888648271560669,
+      "learning_rate": 3.800064182851804e-07,
+      "loss": 0.1399,
+      "step": 744
+    },
+    {
+      "epoch": 0.9220297029702971,
+      "grad_norm": 3.599470615386963,
+      "learning_rate": 3.682968636192863e-07,
+      "loss": 0.1305,
+      "step": 745
+    },
+    {
+      "epoch": 0.9232673267326733,
+      "grad_norm": 5.102394104003906,
+      "learning_rate": 3.567671684345875e-07,
+      "loss": 0.2276,
+      "step": 746
+    },
+    {
+      "epoch": 0.9245049504950495,
+      "grad_norm": 3.962132453918457,
+      "learning_rate": 3.4541754803308567e-07,
+      "loss": 0.1582,
+      "step": 747
+    },
+    {
+      "epoch": 0.9257425742574258,
+      "grad_norm": 3.0672736167907715,
+      "learning_rate": 3.342482143541281e-07,
+      "loss": 0.1273,
+      "step": 748
+    },
+    {
+      "epoch": 0.926980198019802,
+      "grad_norm": 3.4861226081848145,
+      "learning_rate": 3.23259375970435e-07,
+      "loss": 0.1595,
+      "step": 749
+    },
+    {
+      "epoch": 0.9282178217821783,
+      "grad_norm": 4.98872184753418,
+      "learning_rate": 3.124512380842204e-07,
+      "loss": 0.1265,
+      "step": 750
+    },
+    {
+      "epoch": 0.9294554455445545,
+      "grad_norm": 3.516669988632202,
+      "learning_rate": 3.0182400252334656e-07,
+      "loss": 0.1916,
+      "step": 751
+    },
+    {
+      "epoch": 0.9306930693069307,
+      "grad_norm": 3.6074628829956055,
+      "learning_rate": 2.9137786773756114e-07,
+      "loss": 0.1395,
+      "step": 752
+    },
+    {
+      "epoch": 0.931930693069307,
+      "grad_norm": 4.940650463104248,
+      "learning_rate": 2.811130287947972e-07,
+      "loss": 0.2394,
+      "step": 753
+    },
+    {
+      "epoch": 0.9331683168316832,
+      "grad_norm": 6.3607072830200195,
+      "learning_rate": 2.710296773775167e-07,
+      "loss": 0.213,
+      "step": 754
+    },
+    {
+      "epoch": 0.9344059405940595,
+      "grad_norm": 4.352235317230225,
+      "learning_rate": 2.61128001779144e-07,
+      "loss": 0.1511,
+      "step": 755
+    },
+    {
+      "epoch": 0.9356435643564357,
+      "grad_norm": 4.3637495040893555,
+      "learning_rate": 2.514081869005458e-07,
+      "loss": 0.224,
+      "step": 756
+    },
+    {
+      "epoch": 0.9368811881188119,
+      "grad_norm": 3.1667957305908203,
+      "learning_rate": 2.418704142465722e-07,
+      "loss": 0.1993,
+      "step": 757
+    },
+    {
+      "epoch": 0.9381188118811881,
+      "grad_norm": 4.96242094039917,
+      "learning_rate": 2.325148619226758e-07,
+      "loss": 0.1221,
+      "step": 758
+    },
+    {
+      "epoch": 0.9393564356435643,
+      "grad_norm": 5.428174018859863,
+      "learning_rate": 2.2334170463158223e-07,
+      "loss": 0.2239,
+      "step": 759
+    },
+    {
+      "epoch": 0.9405940594059405,
+      "grad_norm": 5.158010005950928,
+      "learning_rate": 2.1435111367002826e-07,
+      "loss": 0.2056,
+      "step": 760
+    },
+    {
+      "epoch": 0.9405940594059405,
+      "eval_accuracy": 0.8592017738359202,
+      "eval_f1": 0.7093821510297483,
+      "eval_loss": 0.296718031167984,
+      "eval_precision": 0.842391304347826,
+      "eval_recall": 0.6126482213438735,
+      "eval_runtime": 50.2838,
+      "eval_samples_per_second": 5.489,
+      "eval_steps_per_second": 0.179,
+      "step": 760
+    },
+    {
+      "epoch": 0.9418316831683168,
+      "grad_norm": 3.6793015003204346,
+      "learning_rate": 2.055432569255622e-07,
+      "loss": 0.1978,
+      "step": 761
+    },
+    {
+      "epoch": 0.943069306930693,
+      "grad_norm": 4.697923183441162,
+      "learning_rate": 1.9691829887340864e-07,
+      "loss": 0.2068,
+      "step": 762
+    },
+    {
+      "epoch": 0.9443069306930693,
+      "grad_norm": 3.3791000843048096,
+      "learning_rate": 1.8847640057339966e-07,
+      "loss": 0.1953,
+      "step": 763
+    },
+    {
+      "epoch": 0.9455445544554455,
+      "grad_norm": 5.8897528648376465,
+      "learning_rate": 1.802177196669619e-07,
+      "loss": 0.2229,
+      "step": 764
+    },
+    {
+      "epoch": 0.9467821782178217,
+      "grad_norm": 5.087184906005859,
+      "learning_rate": 1.7214241037418312e-07,
+      "loss": 0.1672,
+      "step": 765
+    },
+    {
+      "epoch": 0.948019801980198,
+      "grad_norm": 7.06437873840332,
+      "learning_rate": 1.6425062349091914e-07,
+      "loss": 0.2658,
+      "step": 766
+    },
+    {
+      "epoch": 0.9492574257425742,
+      "grad_norm": 6.635834693908691,
+      "learning_rate": 1.5654250638598601e-07,
+      "loss": 0.1855,
+      "step": 767
+    },
+    {
+      "epoch": 0.9504950495049505,
+      "grad_norm": 4.292440414428711,
+      "learning_rate": 1.4901820299840997e-07,
+      "loss": 0.1832,
+      "step": 768
+    },
+    {
+      "epoch": 0.9517326732673267,
+      "grad_norm": 6.999221324920654,
+      "learning_rate": 1.4167785383472855e-07,
+      "loss": 0.2044,
+      "step": 769
+    },
+    {
+      "epoch": 0.9529702970297029,
+      "grad_norm": 3.0472869873046875,
+      "learning_rate": 1.345215959663837e-07,
+      "loss": 0.1321,
+      "step": 770
+    },
+    {
+      "epoch": 0.9542079207920792,
+      "grad_norm": 3.8832876682281494,
+      "learning_rate": 1.2754956302714617e-07,
+      "loss": 0.116,
+      "step": 771
+    },
+    {
+      "epoch": 0.9554455445544554,
+      "grad_norm": 2.6631460189819336,
+      "learning_rate": 1.207618852106285e-07,
+      "loss": 0.1369,
+      "step": 772
+    },
+    {
+      "epoch": 0.9566831683168316,
+      "grad_norm": 5.974620819091797,
+      "learning_rate": 1.1415868926785256e-07,
+      "loss": 0.2214,
+      "step": 773
+    },
+    {
+      "epoch": 0.9579207920792079,
+      "grad_norm": 4.9748616218566895,
+      "learning_rate": 1.0774009850488154e-07,
+      "loss": 0.1924,
+      "step": 774
+    },
+    {
+      "epoch": 0.9591584158415841,
+      "grad_norm": 3.96227765083313,
+      "learning_rate": 1.0150623278051719e-07,
+      "loss": 0.1976,
+      "step": 775
+    },
+    {
+      "epoch": 0.9603960396039604,
+      "grad_norm": 3.1740334033966064,
+      "learning_rate": 9.545720850406504e-08,
+      "loss": 0.1266,
+      "step": 776
+    },
+    {
+      "epoch": 0.9616336633663366,
+      "grad_norm": 7.497445583343506,
+      "learning_rate": 8.959313863315388e-08,
+      "loss": 0.231,
+      "step": 777
+    },
+    {
+      "epoch": 0.9628712871287128,
+      "grad_norm": 4.704877853393555,
+      "learning_rate": 8.391413267163418e-08,
+      "loss": 0.163,
+      "step": 778
+    },
+    {
+      "epoch": 0.9641089108910891,
+      "grad_norm": 4.273810386657715,
+      "learning_rate": 7.842029666752627e-08,
+      "loss": 0.1865,
+      "step": 779
+    },
+    {
+      "epoch": 0.9653465346534653,
+      "grad_norm": 4.104014873504639,
+      "learning_rate": 7.311173321104648e-08,
+      "loss": 0.2127,
+      "step": 780
+    },
+    {
+      "epoch": 0.9653465346534653,
+      "eval_accuracy": 0.8625277161862528,
+      "eval_f1": 0.7194570135746606,
+      "eval_loss": 0.2944088578224182,
+      "eval_precision": 0.8412698412698413,
+      "eval_recall": 0.6284584980237155,
+      "eval_runtime": 50.7955,
+      "eval_samples_per_second": 5.434,
+      "eval_steps_per_second": 0.177,
+      "step": 780
+    },
+    {
+      "epoch": 0.9665841584158416,
+      "grad_norm": 6.6444902420043945,
+      "learning_rate": 6.79885414326864e-08,
+      "loss": 0.251,
+      "step": 781
+    },
+    {
+      "epoch": 0.9678217821782178,
+      "grad_norm": 5.593561172485352,
+      "learning_rate": 6.305081700136328e-08,
+      "loss": 0.2616,
+      "step": 782
+    },
+    {
+      "epoch": 0.969059405940594,
+      "grad_norm": 3.74603009223938,
+      "learning_rate": 5.8298652122634747e-08,
+      "loss": 0.1636,
+      "step": 783
+    },
+    {
+      "epoch": 0.9702970297029703,
+      "grad_norm": 4.336615562438965,
+      "learning_rate": 5.373213553697576e-08,
+      "loss": 0.2196,
+      "step": 784
+    },
+    {
+      "epoch": 0.9715346534653465,
+      "grad_norm": 3.183893918991089,
+      "learning_rate": 4.935135251811995e-08,
+      "loss": 0.141,
+      "step": 785
+    },
+    {
+      "epoch": 0.9727722772277227,
+      "grad_norm": 5.894475936889648,
+      "learning_rate": 4.515638487147311e-08,
+      "loss": 0.2093,
+      "step": 786
+    },
+    {
+      "epoch": 0.974009900990099,
+      "grad_norm": 5.151168346405029,
+      "learning_rate": 4.1147310932578845e-08,
+      "loss": 0.2318,
+      "step": 787
+    },
+    {
+      "epoch": 0.9752475247524752,
+      "grad_norm": 3.7331173419952393,
+      "learning_rate": 3.732420556565752e-08,
+      "loss": 0.1696,
+      "step": 788
+    },
+    {
+      "epoch": 0.9764851485148515,
+      "grad_norm": 5.081837177276611,
+      "learning_rate": 3.368714016221186e-08,
+      "loss": 0.1864,
+      "step": 789
+    },
+    {
+      "epoch": 0.9777227722772277,
+      "grad_norm": 5.835230827331543,
+      "learning_rate": 3.023618263968797e-08,
+      "loss": 0.266,
+      "step": 790
+    },
+    {
+      "epoch": 0.9789603960396039,
+      "grad_norm": 4.534897327423096,
+      "learning_rate": 2.6971397440214154e-08,
+      "loss": 0.1775,
+      "step": 791
+    },
+    {
+      "epoch": 0.9801980198019802,
+      "grad_norm": 4.335183620452881,
+      "learning_rate": 2.3892845529390753e-08,
+      "loss": 0.2054,
+      "step": 792
+    },
+    {
+      "epoch": 0.9814356435643564,
+      "grad_norm": 4.6105451583862305,
+      "learning_rate": 2.100058439515551e-08,
+      "loss": 0.1936,
+      "step": 793
+    },
+    {
+      "epoch": 0.9826732673267327,
+      "grad_norm": 3.7368929386138916,
+      "learning_rate": 1.8294668046708874e-08,
+      "loss": 0.2007,
+      "step": 794
+    },
+    {
+      "epoch": 0.9839108910891089,
+      "grad_norm": 4.431072235107422,
+      "learning_rate": 1.577514701350591e-08,
+      "loss": 0.2273,
+      "step": 795
+    },
+    {
+      "epoch": 0.9851485148514851,
+      "grad_norm": 6.609121322631836,
+      "learning_rate": 1.3442068344312609e-08,
+      "loss": 0.238,
+      "step": 796
+    },
+    {
+      "epoch": 0.9863861386138614,
+      "grad_norm": 4.512663841247559,
+      "learning_rate": 1.129547560632771e-08,
+      "loss": 0.2116,
+      "step": 797
+    },
+    {
+      "epoch": 0.9876237623762376,
+      "grad_norm": 4.200558662414551,
+      "learning_rate": 9.335408884366682e-09,
+      "loss": 0.198,
+      "step": 798
+    },
+    {
+      "epoch": 0.9888613861386139,
+      "grad_norm": 6.579875469207764,
+      "learning_rate": 7.561904780116758e-09,
+      "loss": 0.212,
+      "step": 799
+    },
+    {
+      "epoch": 0.9900990099009901,
+      "grad_norm": 5.1703667640686035,
+      "learning_rate": 5.97499641145416e-09,
+      "loss": 0.2252,
+      "step": 800
+    },
+    {
+      "epoch": 0.9900990099009901,
+      "eval_accuracy": 0.8636363636363636,
+      "eval_f1": 0.7223476297968398,
+      "eval_loss": 0.2939181923866272,
+      "eval_precision": 0.8421052631578947,
+      "eval_recall": 0.6324110671936759,
+      "eval_runtime": 48.1373,
+      "eval_samples_per_second": 5.734,
+      "eval_steps_per_second": 0.187,
+      "step": 800
     }
   ],
   "logging_steps": 1,
@@ -5358,7 +6118,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.148551864918999e+17,
+  "total_flos": 2.4540790520807424e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null