{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9876543209876543,
  "eval_steps": 500,
  "global_step": 363,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0823045267489712,
      "grad_norm": 2.3707054376650794,
      "learning_rate": 5e-06,
      "loss": 0.8018,
      "step": 10
    },
    {
      "epoch": 0.1646090534979424,
      "grad_norm": 0.9189518749553744,
      "learning_rate": 5e-06,
      "loss": 0.6615,
      "step": 20
    },
    {
      "epoch": 0.24691358024691357,
      "grad_norm": 0.7181231203254296,
      "learning_rate": 5e-06,
      "loss": 0.6226,
      "step": 30
    },
    {
      "epoch": 0.3292181069958848,
      "grad_norm": 0.8098373994551952,
      "learning_rate": 5e-06,
      "loss": 0.5947,
      "step": 40
    },
    {
      "epoch": 0.411522633744856,
      "grad_norm": 0.6752478716308398,
      "learning_rate": 5e-06,
      "loss": 0.5731,
      "step": 50
    },
    {
      "epoch": 0.49382716049382713,
      "grad_norm": 0.6563536956259921,
      "learning_rate": 5e-06,
      "loss": 0.5748,
      "step": 60
    },
    {
      "epoch": 0.5761316872427984,
      "grad_norm": 0.7032292694552905,
      "learning_rate": 5e-06,
      "loss": 0.5696,
      "step": 70
    },
    {
      "epoch": 0.6584362139917695,
      "grad_norm": 0.7003547749235107,
      "learning_rate": 5e-06,
      "loss": 0.5579,
      "step": 80
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 0.6613096075940125,
      "learning_rate": 5e-06,
      "loss": 0.563,
      "step": 90
    },
    {
      "epoch": 0.823045267489712,
      "grad_norm": 0.5810433314696346,
      "learning_rate": 5e-06,
      "loss": 0.5506,
      "step": 100
    },
    {
      "epoch": 0.9053497942386831,
      "grad_norm": 0.6666365832464547,
      "learning_rate": 5e-06,
      "loss": 0.5526,
      "step": 110
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.7058806830798787,
      "learning_rate": 5e-06,
      "loss": 0.5415,
      "step": 120
    },
    {
      "epoch": 0.9958847736625515,
      "eval_loss": 0.5658594369888306,
      "eval_runtime": 31.1396,
      "eval_samples_per_second": 26.205,
      "eval_steps_per_second": 0.417,
      "step": 121
    },
    {
      "epoch": 1.0699588477366255,
      "grad_norm": 0.6935479068001943,
      "learning_rate": 5e-06,
      "loss": 0.5334,
      "step": 130
    },
    {
      "epoch": 1.1522633744855968,
      "grad_norm": 0.760550165297717,
      "learning_rate": 5e-06,
      "loss": 0.5067,
      "step": 140
    },
    {
      "epoch": 1.2345679012345678,
      "grad_norm": 0.643311514826356,
      "learning_rate": 5e-06,
      "loss": 0.4975,
      "step": 150
    },
    {
      "epoch": 1.316872427983539,
      "grad_norm": 0.7180631408695722,
      "learning_rate": 5e-06,
      "loss": 0.4907,
      "step": 160
    },
    {
      "epoch": 1.3991769547325104,
      "grad_norm": 0.6268855948646844,
      "learning_rate": 5e-06,
      "loss": 0.4846,
      "step": 170
    },
    {
      "epoch": 1.4814814814814814,
      "grad_norm": 0.6205279314065159,
      "learning_rate": 5e-06,
      "loss": 0.4857,
      "step": 180
    },
    {
      "epoch": 1.5637860082304527,
      "grad_norm": 0.6432594466375224,
      "learning_rate": 5e-06,
      "loss": 0.4922,
      "step": 190
    },
    {
      "epoch": 1.646090534979424,
      "grad_norm": 0.5837924660934569,
      "learning_rate": 5e-06,
      "loss": 0.485,
      "step": 200
    },
    {
      "epoch": 1.7283950617283952,
      "grad_norm": 0.5800173415658518,
      "learning_rate": 5e-06,
      "loss": 0.4899,
      "step": 210
    },
    {
      "epoch": 1.8106995884773662,
      "grad_norm": 0.5452696697421119,
      "learning_rate": 5e-06,
      "loss": 0.4794,
      "step": 220
    },
    {
      "epoch": 1.8930041152263375,
      "grad_norm": 0.6589276092411267,
      "learning_rate": 5e-06,
      "loss": 0.4925,
      "step": 230
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.7099238180212905,
      "learning_rate": 5e-06,
      "loss": 0.486,
      "step": 240
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.552381157875061,
      "eval_runtime": 31.0974,
      "eval_samples_per_second": 26.24,
      "eval_steps_per_second": 0.418,
      "step": 243
    },
    {
      "epoch": 2.05761316872428,
      "grad_norm": 0.6173968011853433,
      "learning_rate": 5e-06,
      "loss": 0.4643,
      "step": 250
    },
    {
      "epoch": 2.139917695473251,
      "grad_norm": 0.6515589754644828,
      "learning_rate": 5e-06,
      "loss": 0.4264,
      "step": 260
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 0.6329003562540839,
      "learning_rate": 5e-06,
      "loss": 0.427,
      "step": 270
    },
    {
      "epoch": 2.3045267489711936,
      "grad_norm": 0.61321586370113,
      "learning_rate": 5e-06,
      "loss": 0.4284,
      "step": 280
    },
    {
      "epoch": 2.386831275720165,
      "grad_norm": 0.5986219957694312,
      "learning_rate": 5e-06,
      "loss": 0.4298,
      "step": 290
    },
    {
      "epoch": 2.4691358024691357,
      "grad_norm": 0.5797625936229965,
      "learning_rate": 5e-06,
      "loss": 0.4332,
      "step": 300
    },
    {
      "epoch": 2.551440329218107,
      "grad_norm": 0.6606165599990808,
      "learning_rate": 5e-06,
      "loss": 0.432,
      "step": 310
    },
    {
      "epoch": 2.633744855967078,
      "grad_norm": 0.6055776178246806,
      "learning_rate": 5e-06,
      "loss": 0.4297,
      "step": 320
    },
    {
      "epoch": 2.7160493827160495,
      "grad_norm": 0.5792227650214353,
      "learning_rate": 5e-06,
      "loss": 0.4301,
      "step": 330
    },
    {
      "epoch": 2.7983539094650207,
      "grad_norm": 0.5678659977310005,
      "learning_rate": 5e-06,
      "loss": 0.4256,
      "step": 340
    },
    {
      "epoch": 2.8806584362139915,
      "grad_norm": 0.5959535146183862,
      "learning_rate": 5e-06,
      "loss": 0.4252,
      "step": 350
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.624214333713647,
      "learning_rate": 5e-06,
      "loss": 0.4216,
      "step": 360
    },
    {
      "epoch": 2.9876543209876543,
      "eval_loss": 0.55907142162323,
      "eval_runtime": 30.0336,
      "eval_samples_per_second": 27.17,
      "eval_steps_per_second": 0.433,
      "step": 363
    },
    {
      "epoch": 2.9876543209876543,
      "step": 363,
      "total_flos": 190042236518400.0,
      "train_loss": 0.506568502460301,
      "train_runtime": 5156.7482,
      "train_samples_per_second": 9.019,
      "train_steps_per_second": 0.07
    }
  ],
  "logging_steps": 10,
  "max_steps": 363,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 190042236518400.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}