{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 280,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03571428571428571,
      "grad_norm": 8.375,
      "learning_rate": 6.134975151822351e-06,
      "loss": 2.5166,
      "step": 5
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 7.03125,
      "learning_rate": 1.380369409160029e-05,
      "loss": 2.3664,
      "step": 10
    },
    {
      "epoch": 0.10714285714285714,
      "grad_norm": 4.46875,
      "learning_rate": 2.147241303137823e-05,
      "loss": 2.1894,
      "step": 15
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 2.75,
      "learning_rate": 2.9141131971156165e-05,
      "loss": 1.9071,
      "step": 20
    },
    {
      "epoch": 0.17857142857142858,
      "grad_norm": 2.578125,
      "learning_rate": 3.680985091093411e-05,
      "loss": 1.7995,
      "step": 25
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 2.4375,
      "learning_rate": 4.447856985071205e-05,
      "loss": 1.7517,
      "step": 30
    },
    {
      "epoch": 0.25,
      "grad_norm": 2.40625,
      "learning_rate": 5.214728879048998e-05,
      "loss": 1.674,
      "step": 35
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 2.375,
      "learning_rate": 5.366816599944071e-05,
      "loss": 1.7227,
      "step": 40
    },
    {
      "epoch": 0.32142857142857145,
      "grad_norm": 2.125,
      "learning_rate": 5.3615919012263934e-05,
      "loss": 1.6688,
      "step": 45
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 2.21875,
      "learning_rate": 5.3523574348746333e-05,
      "loss": 1.6506,
      "step": 50
    },
    {
      "epoch": 0.39285714285714285,
      "grad_norm": 1.9765625,
      "learning_rate": 5.339128570746694e-05,
      "loss": 1.6784,
      "step": 55
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 1.96875,
      "learning_rate": 5.321927326981367e-05,
      "loss": 1.6102,
      "step": 60
    },
    {
      "epoch": 0.4642857142857143,
      "grad_norm": 2.0625,
      "learning_rate": 5.3007823333513254e-05,
      "loss": 1.6463,
      "step": 65
    },
    {
      "epoch": 0.5,
      "grad_norm": 2.109375,
      "learning_rate": 5.275728783611684e-05,
      "loss": 1.6467,
      "step": 70
    },
    {
      "epoch": 0.5357142857142857,
      "grad_norm": 2.0625,
      "learning_rate": 5.246808376923472e-05,
      "loss": 1.6201,
      "step": 75
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 2.015625,
      "learning_rate": 5.2140692484494896e-05,
      "loss": 1.6123,
      "step": 80
    },
    {
      "epoch": 0.6071428571428571,
      "grad_norm": 2.125,
      "learning_rate": 5.1775658892380846e-05,
      "loss": 1.6038,
      "step": 85
    },
    {
      "epoch": 0.6428571428571429,
      "grad_norm": 2.046875,
      "learning_rate": 5.1373590555281784e-05,
      "loss": 1.5958,
      "step": 90
    },
    {
      "epoch": 0.6785714285714286,
      "grad_norm": 2.234375,
      "learning_rate": 5.093515667626503e-05,
      "loss": 1.5937,
      "step": 95
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 2.046875,
      "learning_rate": 5.0461086985253524e-05,
      "loss": 1.6396,
      "step": 100
    },
    {
      "epoch": 0.75,
      "grad_norm": 2.046875,
      "learning_rate": 4.995217052446242e-05,
      "loss": 1.5591,
      "step": 105
    },
    {
      "epoch": 0.7857142857142857,
      "grad_norm": 2.09375,
      "learning_rate": 4.940925433511616e-05,
      "loss": 1.5707,
      "step": 110
    },
    {
      "epoch": 0.8214285714285714,
      "grad_norm": 2.1875,
      "learning_rate": 4.883324204763196e-05,
      "loss": 1.5803,
      "step": 115
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 2.0625,
      "learning_rate": 4.822509237761618e-05,
      "loss": 1.5646,
      "step": 120
    },
    {
      "epoch": 0.8928571428571429,
      "grad_norm": 2.03125,
      "learning_rate": 4.758581753017676e-05,
      "loss": 1.5666,
      "step": 125
    },
    {
      "epoch": 0.9285714285714286,
      "grad_norm": 1.9609375,
      "learning_rate": 4.691648151520777e-05,
      "loss": 1.5521,
      "step": 130
    },
    {
      "epoch": 0.9642857142857143,
      "grad_norm": 1.96875,
      "learning_rate": 4.6218198376449914e-05,
      "loss": 1.5823,
      "step": 135
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.96875,
      "learning_rate": 4.5492130337274675e-05,
      "loss": 1.562,
      "step": 140
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.5592896938323975,
      "eval_runtime": 0.5806,
      "eval_samples_per_second": 8.611,
      "eval_steps_per_second": 8.611,
      "step": 140
    },
    {
      "epoch": 1.0357142857142858,
      "grad_norm": 2.4375,
      "learning_rate": 4.4739485866278206e-05,
      "loss": 1.2341,
      "step": 145
    },
    {
      "epoch": 1.0714285714285714,
      "grad_norm": 1.9765625,
      "learning_rate": 4.396151766590464e-05,
      "loss": 1.2236,
      "step": 150
    },
    {
      "epoch": 1.1071428571428572,
      "grad_norm": 2.109375,
      "learning_rate": 4.315952058744645e-05,
      "loss": 1.2273,
      "step": 155
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 2.46875,
      "learning_rate": 4.23348294758923e-05,
      "loss": 1.1896,
      "step": 160
    },
    {
      "epoch": 1.1785714285714286,
      "grad_norm": 2.296875,
      "learning_rate": 4.148881694820931e-05,
      "loss": 1.1565,
      "step": 165
    },
    {
      "epoch": 1.2142857142857142,
      "grad_norm": 2.390625,
      "learning_rate": 4.0622891108757535e-05,
      "loss": 1.217,
      "step": 170
    },
    {
      "epoch": 1.25,
      "grad_norm": 1.9375,
      "learning_rate": 3.9738493205639244e-05,
      "loss": 1.1793,
      "step": 175
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 2.109375,
      "learning_rate": 3.8837095231883686e-05,
      "loss": 1.1867,
      "step": 180
    },
    {
      "epoch": 1.3214285714285714,
      "grad_norm": 2.140625,
      "learning_rate": 3.7920197475459964e-05,
      "loss": 1.1728,
      "step": 185
    },
    {
      "epoch": 1.3571428571428572,
      "grad_norm": 2.046875,
      "learning_rate": 3.6989326022195766e-05,
      "loss": 1.1698,
      "step": 190
    },
    {
      "epoch": 1.3928571428571428,
      "grad_norm": 2.390625,
      "learning_rate": 3.604603021575812e-05,
      "loss": 1.1985,
      "step": 195
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 1.890625,
      "learning_rate": 3.509188007892378e-05,
      "loss": 1.2197,
      "step": 200
    },
    {
      "epoch": 1.4642857142857144,
      "grad_norm": 2.171875,
      "learning_rate": 3.412846370043121e-05,
      "loss": 1.1524,
      "step": 205
    },
    {
      "epoch": 1.5,
      "grad_norm": 1.96875,
      "learning_rate": 3.315738459176366e-05,
      "loss": 1.1829,
      "step": 210
    },
    {
      "epoch": 1.5357142857142856,
      "grad_norm": 2.09375,
      "learning_rate": 3.218025901826252e-05,
      "loss": 1.2213,
      "step": 215
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 2.1875,
      "learning_rate": 3.119871330901317e-05,
      "loss": 1.1901,
      "step": 220
    },
    {
      "epoch": 1.6071428571428572,
      "grad_norm": 2.0,
      "learning_rate": 3.021438114998073e-05,
      "loss": 1.1771,
      "step": 225
    },
    {
      "epoch": 1.6428571428571428,
      "grad_norm": 2.125,
      "learning_rate": 2.9228900864901006e-05,
      "loss": 1.1603,
      "step": 230
    },
    {
      "epoch": 1.6785714285714286,
      "grad_norm": 2.1875,
      "learning_rate": 2.8243912688452264e-05,
      "loss": 1.1664,
      "step": 235
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 1.8828125,
      "learning_rate": 2.7261056036246544e-05,
      "loss": 1.2189,
      "step": 240
    },
    {
      "epoch": 1.75,
      "grad_norm": 2.046875,
      "learning_rate": 2.6281966776184158e-05,
      "loss": 1.1748,
      "step": 245
    },
    {
      "epoch": 1.7857142857142856,
      "grad_norm": 1.9921875,
      "learning_rate": 2.530827450571295e-05,
      "loss": 1.1693,
      "step": 250
    },
    {
      "epoch": 1.8214285714285714,
      "grad_norm": 2.109375,
      "learning_rate": 2.4341599839524256e-05,
      "loss": 1.1425,
      "step": 255
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 1.96875,
      "learning_rate": 2.3383551712199637e-05,
      "loss": 1.1595,
      "step": 260
    },
    {
      "epoch": 1.8928571428571428,
      "grad_norm": 2.28125,
      "learning_rate": 2.2435724700298047e-05,
      "loss": 1.1774,
      "step": 265
    },
    {
      "epoch": 1.9285714285714286,
      "grad_norm": 2.28125,
      "learning_rate": 2.149969636834054e-05,
      "loss": 1.1536,
      "step": 270
    },
    {
      "epoch": 1.9642857142857144,
      "grad_norm": 2.109375,
      "learning_rate": 2.05770246431098e-05,
      "loss": 1.1708,
      "step": 275
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.296875,
      "learning_rate": 1.9669245220634777e-05,
      "loss": 1.1977,
      "step": 280
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.5587482452392578,
      "eval_runtime": 0.4527,
      "eval_samples_per_second": 11.045,
      "eval_steps_per_second": 11.045,
      "step": 280
    }
  ],
  "logging_steps": 5,
  "max_steps": 420,
  "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": 6.147865928584397e+17,
  "train_batch_size": 48,
  "trial_name": null,
  "trial_params": null
}