{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9968337730870713,
  "eval_steps": 500,
  "global_step": 473,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04221635883905013,
      "grad_norm": 0.50788813829422,
      "learning_rate": 2.5e-05,
      "loss": 4.0916,
      "step": 10
    },
    {
      "epoch": 0.08443271767810026,
      "grad_norm": 0.31596097350120544,
      "learning_rate": 2.9996874776728528e-05,
      "loss": 3.8989,
      "step": 20
    },
    {
      "epoch": 0.1266490765171504,
      "grad_norm": 0.28351184725761414,
      "learning_rate": 2.998418103705505e-05,
      "loss": 3.6225,
      "step": 30
    },
    {
      "epoch": 0.16886543535620052,
      "grad_norm": 0.2747008502483368,
      "learning_rate": 2.996173263030885e-05,
      "loss": 3.3931,
      "step": 40
    },
    {
      "epoch": 0.21108179419525067,
      "grad_norm": 0.27435237169265747,
      "learning_rate": 2.9929545796017835e-05,
      "loss": 3.1614,
      "step": 50
    },
    {
      "epoch": 0.2532981530343008,
      "grad_norm": 0.31030479073524475,
      "learning_rate": 2.9887643818640412e-05,
      "loss": 2.882,
      "step": 60
    },
    {
      "epoch": 0.2955145118733509,
      "grad_norm": 0.3085922598838806,
      "learning_rate": 2.983605701072119e-05,
      "loss": 2.6283,
      "step": 70
    },
    {
      "epoch": 0.33773087071240104,
      "grad_norm": 0.230041041970253,
      "learning_rate": 2.9774822690962358e-05,
      "loss": 2.3723,
      "step": 80
    },
    {
      "epoch": 0.37994722955145116,
      "grad_norm": 0.19185876846313477,
      "learning_rate": 2.9703985157226802e-05,
      "loss": 2.1931,
      "step": 90
    },
    {
      "epoch": 0.42216358839050133,
      "grad_norm": 0.17534567415714264,
      "learning_rate": 2.9623595654492328e-05,
      "loss": 2.1193,
      "step": 100
    },
    {
      "epoch": 0.46437994722955145,
      "grad_norm": 0.15833114087581635,
      "learning_rate": 2.953371233778022e-05,
      "loss": 2.0044,
      "step": 110
    },
    {
      "epoch": 0.5065963060686016,
      "grad_norm": 0.152941033244133,
      "learning_rate": 2.943440023008502e-05,
      "loss": 2.0208,
      "step": 120
    },
    {
      "epoch": 0.5488126649076517,
      "grad_norm": 0.14308719336986542,
      "learning_rate": 2.932573117533585e-05,
      "loss": 2.0013,
      "step": 130
    },
    {
      "epoch": 0.5910290237467019,
      "grad_norm": 0.12415236979722977,
      "learning_rate": 2.9207783786423436e-05,
      "loss": 1.9719,
      "step": 140
    },
    {
      "epoch": 0.633245382585752,
      "grad_norm": 0.14564257860183716,
      "learning_rate": 2.9080643388330266e-05,
      "loss": 1.9659,
      "step": 150
    },
    {
      "epoch": 0.6754617414248021,
      "grad_norm": 0.14092124998569489,
      "learning_rate": 2.8944401956405192e-05,
      "loss": 1.9645,
      "step": 160
    },
    {
      "epoch": 0.7176781002638523,
      "grad_norm": 0.14931683242321014,
      "learning_rate": 2.8799158049827027e-05,
      "loss": 1.902,
      "step": 170
    },
    {
      "epoch": 0.7598944591029023,
      "grad_norm": 0.13305355608463287,
      "learning_rate": 2.8645016740305286e-05,
      "loss": 2.0203,
      "step": 180
    },
    {
      "epoch": 0.8021108179419525,
      "grad_norm": 0.13253405690193176,
      "learning_rate": 2.8482089536069683e-05,
      "loss": 1.92,
      "step": 190
    },
    {
      "epoch": 0.8443271767810027,
      "grad_norm": 0.15814724564552307,
      "learning_rate": 2.8310494301203323e-05,
      "loss": 1.9354,
      "step": 200
    },
    {
      "epoch": 0.8865435356200527,
      "grad_norm": 0.12858152389526367,
      "learning_rate": 2.8130355170378002e-05,
      "loss": 1.8576,
      "step": 210
    },
    {
      "epoch": 0.9287598944591029,
      "grad_norm": 0.15734779834747314,
      "learning_rate": 2.7941802459053222e-05,
      "loss": 1.8994,
      "step": 220
    },
    {
      "epoch": 0.9709762532981531,
      "grad_norm": 0.13302397727966309,
      "learning_rate": 2.7744972569203985e-05,
      "loss": 1.9127,
      "step": 230
    },
    {
      "epoch": 1.0131926121372032,
      "grad_norm": 0.14125587046146393,
      "learning_rate": 2.754000789064544e-05,
      "loss": 1.856,
      "step": 240
    },
    {
      "epoch": 1.0554089709762533,
      "grad_norm": 0.1589905321598053,
      "learning_rate": 2.7327056698025907e-05,
      "loss": 1.8638,
      "step": 250
    },
    {
      "epoch": 1.0976253298153034,
      "grad_norm": 0.15254752337932587,
      "learning_rate": 2.710627304356264e-05,
      "loss": 1.8925,
      "step": 260
    },
    {
      "epoch": 1.1398416886543536,
      "grad_norm": 0.1510193943977356,
      "learning_rate": 2.6877816645598093e-05,
      "loss": 1.8423,
      "step": 270
    },
    {
      "epoch": 1.1820580474934037,
      "grad_norm": 0.15128286182880402,
      "learning_rate": 2.664185277305712e-05,
      "loss": 1.8433,
      "step": 280
    },
    {
      "epoch": 1.2242744063324538,
      "grad_norm": 0.16148072481155396,
      "learning_rate": 2.639855212588892e-05,
      "loss": 1.8482,
      "step": 290
    },
    {
      "epoch": 1.266490765171504,
      "grad_norm": 0.1490674763917923,
      "learning_rate": 2.6148090711579976e-05,
      "loss": 1.8667,
      "step": 300
    },
    {
      "epoch": 1.3087071240105541,
      "grad_norm": 0.141664519906044,
      "learning_rate": 2.5890649717827517e-05,
      "loss": 1.8034,
      "step": 310
    },
    {
      "epoch": 1.3509234828496042,
      "grad_norm": 0.13706474006175995,
      "learning_rate": 2.5626415381465506e-05,
      "loss": 1.8521,
      "step": 320
    },
    {
      "epoch": 1.3931398416886545,
      "grad_norm": 0.1380421221256256,
      "learning_rate": 2.535557885373801e-05,
      "loss": 1.8737,
      "step": 330
    },
    {
      "epoch": 1.4353562005277045,
      "grad_norm": 0.16114376485347748,
      "learning_rate": 2.5078336062017396e-05,
      "loss": 1.8536,
      "step": 340
    },
    {
      "epoch": 1.4775725593667546,
      "grad_norm": 0.14424873888492584,
      "learning_rate": 2.4794887568067413e-05,
      "loss": 1.8225,
      "step": 350
    },
    {
      "epoch": 1.5197889182058049,
      "grad_norm": 0.15957856178283691,
      "learning_rate": 2.4505438422953686e-05,
      "loss": 1.8637,
      "step": 360
    },
    {
      "epoch": 1.562005277044855,
      "grad_norm": 0.16451793909072876,
      "learning_rate": 2.421019801870658e-05,
      "loss": 1.8643,
      "step": 370
    },
    {
      "epoch": 1.604221635883905,
      "grad_norm": 0.1663391888141632,
      "learning_rate": 2.390937993684371e-05,
      "loss": 1.8301,
      "step": 380
    },
    {
      "epoch": 1.6464379947229553,
      "grad_norm": 0.15829075872898102,
      "learning_rate": 2.3603201793861776e-05,
      "loss": 1.8388,
      "step": 390
    },
    {
      "epoch": 1.6886543535620053,
      "grad_norm": 0.14315567910671234,
      "learning_rate": 2.329188508380936e-05,
      "loss": 1.8571,
      "step": 400
    },
    {
      "epoch": 1.7308707124010554,
      "grad_norm": 0.16106358170509338,
      "learning_rate": 2.2975655018054685e-05,
      "loss": 1.8783,
      "step": 410
    },
    {
      "epoch": 1.7730870712401057,
      "grad_norm": 0.14807620644569397,
      "learning_rate": 2.2654740362364196e-05,
      "loss": 1.8006,
      "step": 420
    },
    {
      "epoch": 1.8153034300791555,
      "grad_norm": 0.1798703372478485,
      "learning_rate": 2.232937327140983e-05,
      "loss": 1.7707,
      "step": 430
    },
    {
      "epoch": 1.8575197889182058,
      "grad_norm": 0.15553659200668335,
      "learning_rate": 2.1999789120824702e-05,
      "loss": 1.8307,
      "step": 440
    },
    {
      "epoch": 1.899736147757256,
      "grad_norm": 0.14261312782764435,
      "learning_rate": 2.166622633692871e-05,
      "loss": 1.7768,
      "step": 450
    },
    {
      "epoch": 1.941952506596306,
      "grad_norm": 0.18098565936088562,
      "learning_rate": 2.13289262242472e-05,
      "loss": 1.7687,
      "step": 460
    },
    {
      "epoch": 1.9841688654353562,
      "grad_norm": 0.15806493163108826,
      "learning_rate": 2.0988132790947478e-05,
      "loss": 1.8417,
      "step": 470
    }
  ],
  "logging_steps": 10,
  "max_steps": 1180,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.1390125387913216e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}