{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.016,
      "grad_norm": 2.7287635803222656,
      "learning_rate": 2.3936170212765957e-06,
      "loss": 1.8321,
      "step": 10
    },
    {
      "epoch": 0.032,
      "grad_norm": 2.5078585147857666,
      "learning_rate": 5.053191489361702e-06,
      "loss": 1.7408,
      "step": 20
    },
    {
      "epoch": 0.048,
      "grad_norm": 2.1067042350769043,
      "learning_rate": 7.712765957446808e-06,
      "loss": 1.5053,
      "step": 30
    },
    {
      "epoch": 0.064,
      "grad_norm": 1.6803735494613647,
      "learning_rate": 1.0372340425531916e-05,
      "loss": 1.176,
      "step": 40
    },
    {
      "epoch": 0.08,
      "grad_norm": 1.358530044555664,
      "learning_rate": 1.3031914893617023e-05,
      "loss": 0.7815,
      "step": 50
    },
    {
      "epoch": 0.096,
      "grad_norm": 0.7375353574752808,
      "learning_rate": 1.5691489361702127e-05,
      "loss": 0.4287,
      "step": 60
    },
    {
      "epoch": 0.112,
      "grad_norm": 0.5832469463348389,
      "learning_rate": 1.8351063829787234e-05,
      "loss": 0.3052,
      "step": 70
    },
    {
      "epoch": 0.128,
      "grad_norm": 0.41397199034690857,
      "learning_rate": 2.1010638297872342e-05,
      "loss": 0.1874,
      "step": 80
    },
    {
      "epoch": 0.144,
      "grad_norm": 0.4094902575016022,
      "learning_rate": 2.3670212765957446e-05,
      "loss": 0.1135,
      "step": 90
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.2328539937734604,
      "learning_rate": 2.6329787234042553e-05,
      "loss": 0.047,
      "step": 100
    },
    {
      "epoch": 0.176,
      "grad_norm": 0.1451612263917923,
      "learning_rate": 2.898936170212766e-05,
      "loss": 0.0175,
      "step": 110
    },
    {
      "epoch": 0.192,
      "grad_norm": 0.02662522904574871,
      "learning_rate": 3.164893617021277e-05,
      "loss": 0.0036,
      "step": 120
    },
    {
      "epoch": 0.208,
      "grad_norm": 0.01232597604393959,
      "learning_rate": 3.430851063829787e-05,
      "loss": 0.0014,
      "step": 130
    },
    {
      "epoch": 0.224,
      "grad_norm": 0.0077546993270516396,
      "learning_rate": 3.696808510638298e-05,
      "loss": 0.0007,
      "step": 140
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.005459086503833532,
      "learning_rate": 3.962765957446809e-05,
      "loss": 0.0006,
      "step": 150
    },
    {
      "epoch": 0.256,
      "grad_norm": 0.005705484189093113,
      "learning_rate": 4.228723404255319e-05,
      "loss": 0.0005,
      "step": 160
    },
    {
      "epoch": 0.272,
      "grad_norm": 0.0035389093682169914,
      "learning_rate": 4.49468085106383e-05,
      "loss": 0.0004,
      "step": 170
    },
    {
      "epoch": 0.288,
      "grad_norm": 0.003010712331160903,
      "learning_rate": 4.7606382978723405e-05,
      "loss": 0.0003,
      "step": 180
    },
    {
      "epoch": 0.304,
      "grad_norm": 0.002946693217381835,
      "learning_rate": 4.999995665096164e-05,
      "loss": 0.0003,
      "step": 190
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.002301169792190194,
      "learning_rate": 4.9994754948256304e-05,
      "loss": 0.0002,
      "step": 200
    },
    {
      "epoch": 0.336,
      "grad_norm": 0.002140331780537963,
      "learning_rate": 4.998088550481357e-05,
      "loss": 0.0002,
      "step": 210
    },
    {
      "epoch": 0.352,
      "grad_norm": 0.0022257098462432623,
      "learning_rate": 4.9958353130312106e-05,
      "loss": 0.0002,
      "step": 220
    },
    {
      "epoch": 0.368,
      "grad_norm": 0.001662266324274242,
      "learning_rate": 4.99271656385825e-05,
      "loss": 0.0002,
      "step": 230
    },
    {
      "epoch": 0.384,
      "grad_norm": 0.002042123582214117,
      "learning_rate": 4.9887333844897506e-05,
      "loss": 0.0002,
      "step": 240
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.0013473546132445335,
      "learning_rate": 4.983887156222155e-05,
      "loss": 0.0002,
      "step": 250
    },
    {
      "epoch": 0.416,
      "grad_norm": 0.0018928167410194874,
      "learning_rate": 4.978179559642061e-05,
      "loss": 0.0002,
      "step": 260
    },
    {
      "epoch": 0.432,
      "grad_norm": 0.0016440442996099591,
      "learning_rate": 4.9716125740434235e-05,
      "loss": 0.0002,
      "step": 270
    },
    {
      "epoch": 0.448,
      "grad_norm": 0.001509015099145472,
      "learning_rate": 4.9641884767411714e-05,
      "loss": 0.0002,
      "step": 280
    },
    {
      "epoch": 0.464,
      "grad_norm": 0.002279238309711218,
      "learning_rate": 4.955909842281477e-05,
      "loss": 0.0001,
      "step": 290
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.0011063262354582548,
      "learning_rate": 4.946779541548942e-05,
      "loss": 0.0001,
      "step": 300
    },
    {
      "epoch": 0.496,
      "grad_norm": 0.0013478458859026432,
      "learning_rate": 4.936800740771033e-05,
      "loss": 0.0001,
      "step": 310
    },
    {
      "epoch": 0.512,
      "grad_norm": 0.0010506451362743974,
      "learning_rate": 4.925976900420083e-05,
      "loss": 0.0001,
      "step": 320
    },
    {
      "epoch": 0.528,
      "grad_norm": 0.0013516925973817706,
      "learning_rate": 4.9143117740132667e-05,
      "loss": 0.0001,
      "step": 330
    },
    {
      "epoch": 0.544,
      "grad_norm": 0.001162629690952599,
      "learning_rate": 4.901809406810942e-05,
      "loss": 0.0001,
      "step": 340
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.0008260276517830789,
      "learning_rate": 4.8884741344138294e-05,
      "loss": 0.0001,
      "step": 350
    },
    {
      "epoch": 0.576,
      "grad_norm": 0.0009220085921697319,
      "learning_rate": 4.8743105812594944e-05,
      "loss": 0.0001,
      "step": 360
    },
    {
      "epoch": 0.592,
      "grad_norm": 0.0009574664290994406,
      "learning_rate": 4.8593236590186855e-05,
      "loss": 0.0001,
      "step": 370
    },
    {
      "epoch": 0.608,
      "grad_norm": 0.0009008324705064297,
      "learning_rate": 4.8435185648920403e-05,
      "loss": 0.0001,
      "step": 380
    },
    {
      "epoch": 0.624,
      "grad_norm": 0.0007590301102027297,
      "learning_rate": 4.8269007798077994e-05,
      "loss": 0.0001,
      "step": 390
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.0007175425416789949,
      "learning_rate": 4.809476066521111e-05,
      "loss": 0.0001,
      "step": 400
    },
    {
      "epoch": 0.656,
      "grad_norm": 0.0008309377590194345,
      "learning_rate": 4.791250467615608e-05,
      "loss": 0.0001,
      "step": 410
    },
    {
      "epoch": 0.672,
      "grad_norm": 0.0006082377512939274,
      "learning_rate": 4.77223030340795e-05,
      "loss": 0.0001,
      "step": 420
    },
    {
      "epoch": 0.688,
      "grad_norm": 0.0007051264983601868,
      "learning_rate": 4.752422169756048e-05,
      "loss": 0.0001,
      "step": 430
    },
    {
      "epoch": 0.704,
      "grad_norm": 0.000669407716486603,
      "learning_rate": 4.7318329357717345e-05,
      "loss": 0.0001,
      "step": 440
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.0006657831836491823,
      "learning_rate": 4.710469741438679e-05,
      "loss": 0.0001,
      "step": 450
    },
    {
      "epoch": 0.736,
      "grad_norm": 0.0005902393022552133,
      "learning_rate": 4.688339995136368e-05,
      "loss": 0.0001,
      "step": 460
    },
    {
      "epoch": 0.752,
      "grad_norm": 0.0006702489918097854,
      "learning_rate": 4.6654513710710056e-05,
      "loss": 0.0001,
      "step": 470
    },
    {
      "epoch": 0.768,
      "grad_norm": 0.0005900064134038985,
      "learning_rate": 4.6418118066142395e-05,
      "loss": 0.0001,
      "step": 480
    },
    {
      "epoch": 0.784,
      "grad_norm": 0.0005075543303973973,
      "learning_rate": 4.6174294995506154e-05,
      "loss": 0.0001,
      "step": 490
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.0005521568236872554,
      "learning_rate": 4.5923129052347334e-05,
      "loss": 0.0001,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 1875,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 1.9952307416334336e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}