{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 334,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06010518407212622,
      "grad_norm": 2.776237700093034,
      "learning_rate": 2.647058823529412e-06,
      "loss": 1.2284340858459473,
      "step": 10
    },
    {
      "epoch": 0.12021036814425244,
      "grad_norm": 1.1013368513651545,
      "learning_rate": 4.999508937232514e-06,
      "loss": 0.953094482421875,
      "step": 20
    },
    {
      "epoch": 0.18031555221637866,
      "grad_norm": 0.7678503876226538,
      "learning_rate": 4.982341987865914e-06,
      "loss": 0.7880845069885254,
      "step": 30
    },
    {
      "epoch": 0.24042073628850488,
      "grad_norm": 0.4960089758415,
      "learning_rate": 4.940814473856278e-06,
      "loss": 0.7320358276367187,
      "step": 40
    },
    {
      "epoch": 0.3005259203606311,
      "grad_norm": 0.4611853514743128,
      "learning_rate": 4.875333927161104e-06,
      "loss": 0.7054203033447266,
      "step": 50
    },
    {
      "epoch": 0.3606311044327573,
      "grad_norm": 0.45095741292705066,
      "learning_rate": 4.7865429438039955e-06,
      "loss": 0.687248706817627,
      "step": 60
    },
    {
      "epoch": 0.42073628850488354,
      "grad_norm": 0.445510626195826,
      "learning_rate": 4.6753128777323e-06,
      "loss": 0.6785623550415039,
      "step": 70
    },
    {
      "epoch": 0.48084147257700977,
      "grad_norm": 0.4218098042597313,
      "learning_rate": 4.542735289749498e-06,
      "loss": 0.66799898147583,
      "step": 80
    },
    {
      "epoch": 0.540946656649136,
      "grad_norm": 0.42965824692515564,
      "learning_rate": 4.390111235438606e-06,
      "loss": 0.6619597434997558,
      "step": 90
    },
    {
      "epoch": 0.6010518407212622,
      "grad_norm": 0.43461658184031327,
      "learning_rate": 4.218938497199996e-06,
      "loss": 0.6566213130950928,
      "step": 100
    },
    {
      "epoch": 0.6611570247933884,
      "grad_norm": 0.4516606558101725,
      "learning_rate": 4.03089688570253e-06,
      "loss": 0.649503517150879,
      "step": 110
    },
    {
      "epoch": 0.7212622088655146,
      "grad_norm": 0.44000894914700206,
      "learning_rate": 3.827831754992854e-06,
      "loss": 0.6441732883453369,
      "step": 120
    },
    {
      "epoch": 0.7813673929376409,
      "grad_norm": 0.46937207230196937,
      "learning_rate": 3.611735893037967e-06,
      "loss": 0.6436738491058349,
      "step": 130
    },
    {
      "epoch": 0.8414725770097671,
      "grad_norm": 0.43338172376594786,
      "learning_rate": 3.3847299654189947e-06,
      "loss": 0.638824462890625,
      "step": 140
    },
    {
      "epoch": 0.9015777610818934,
      "grad_norm": 0.41244075171530503,
      "learning_rate": 3.1490417040927513e-06,
      "loss": 0.6347045421600341,
      "step": 150
    },
    {
      "epoch": 0.9616829451540195,
      "grad_norm": 0.4435736854495128,
      "learning_rate": 2.9069840454530583e-06,
      "loss": 0.6339764595031738,
      "step": 160
    },
    {
      "epoch": 1.018031555221638,
      "grad_norm": 0.43042109834301273,
      "learning_rate": 2.660932432234823e-06,
      "loss": 0.6272397994995117,
      "step": 170
    },
    {
      "epoch": 1.0781367392937642,
      "grad_norm": 0.4130061435691091,
      "learning_rate": 2.413301502009591e-06,
      "loss": 0.6114815235137939,
      "step": 180
    },
    {
      "epoch": 1.1382419233658903,
      "grad_norm": 0.4038777948776202,
      "learning_rate": 2.166521391040963e-06,
      "loss": 0.6114835739135742,
      "step": 190
    },
    {
      "epoch": 1.1983471074380165,
      "grad_norm": 0.40817003614353453,
      "learning_rate": 1.923013886042956e-06,
      "loss": 0.6095846176147461,
      "step": 200
    },
    {
      "epoch": 1.2584522915101428,
      "grad_norm": 0.40324569219607864,
      "learning_rate": 1.6851686578770263e-06,
      "loss": 0.6101284980773926,
      "step": 210
    },
    {
      "epoch": 1.3185574755822689,
      "grad_norm": 0.40166556982490487,
      "learning_rate": 1.4553198104193094e-06,
      "loss": 0.6100864410400391,
      "step": 220
    },
    {
      "epoch": 1.3786626596543952,
      "grad_norm": 0.3809282869819938,
      "learning_rate": 1.235722974736756e-06,
      "loss": 0.6077391147613526,
      "step": 230
    },
    {
      "epoch": 1.4387678437265214,
      "grad_norm": 0.38079334134428333,
      "learning_rate": 1.0285331733593778e-06,
      "loss": 0.6076976776123046,
      "step": 240
    },
    {
      "epoch": 1.4988730277986475,
      "grad_norm": 0.38514315862275184,
      "learning_rate": 8.357836718785018e-07,
      "loss": 0.6098727226257324,
      "step": 250
    },
    {
      "epoch": 1.558978211870774,
      "grad_norm": 1.080984219484949,
      "learning_rate": 6.593660254117104e-07,
      "loss": 0.6043878555297851,
      "step": 260
    },
    {
      "epoch": 1.6190833959429,
      "grad_norm": 0.3893836987691287,
      "learning_rate": 5.010115157493198e-07,
      "loss": 0.6059476375579834,
      "step": 270
    },
    {
      "epoch": 1.6791885800150261,
      "grad_norm": 0.37390375440579593,
      "learning_rate": 3.622741613497047e-07,
      "loss": 0.6050002098083496,
      "step": 280
    },
    {
      "epoch": 1.7392937640871526,
      "grad_norm": 0.3823417162941356,
      "learning_rate": 2.4451546691559305e-07,
      "loss": 0.6037191867828369,
      "step": 290
    },
    {
      "epoch": 1.7993989481592787,
      "grad_norm": 0.39472217562650863,
      "learning_rate": 1.4889106221196686e-07,
      "loss": 0.5994118213653564,
      "step": 300
    },
    {
      "epoch": 1.859504132231405,
      "grad_norm": 0.4433640201370672,
      "learning_rate": 7.633936124608998e-08,
      "loss": 0.6043890953063965,
      "step": 310
    },
    {
      "epoch": 1.9196093163035313,
      "grad_norm": 0.3775912358838846,
      "learning_rate": 2.7572353103262617e-08,
      "loss": 0.6042394638061523,
      "step": 320
    },
    {
      "epoch": 1.9797145003756573,
      "grad_norm": 0.36394036662336054,
      "learning_rate": 3.0686148128050707e-09,
      "loss": 0.6040500640869141,
      "step": 330
    }
  ],
  "logging_steps": 10,
  "max_steps": 334,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.0054478564622336e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}