{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 285,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.017543859649122806,
      "grad_norm": 1.052474021911621,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 1.3678,
      "step": 5
    },
    {
      "epoch": 0.03508771929824561,
      "grad_norm": 0.8925581574440002,
      "learning_rate": 3.75e-06,
      "loss": 1.341,
      "step": 10
    },
    {
      "epoch": 0.05263157894736842,
      "grad_norm": 0.5862356424331665,
      "learning_rate": 5.833333333333334e-06,
      "loss": 1.3559,
      "step": 15
    },
    {
      "epoch": 0.07017543859649122,
      "grad_norm": 0.605962872505188,
      "learning_rate": 7.916666666666667e-06,
      "loss": 1.3164,
      "step": 20
    },
    {
      "epoch": 0.08771929824561403,
      "grad_norm": 0.719713568687439,
      "learning_rate": 9.999999999999999e-06,
      "loss": 1.2669,
      "step": 25
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 0.7025077939033508,
      "learning_rate": 1.2083333333333333e-05,
      "loss": 1.2975,
      "step": 30
    },
    {
      "epoch": 0.12280701754385964,
      "grad_norm": 0.6195961833000183,
      "learning_rate": 1.4166666666666666e-05,
      "loss": 1.2555,
      "step": 35
    },
    {
      "epoch": 0.14035087719298245,
      "grad_norm": 0.5059925317764282,
      "learning_rate": 1.625e-05,
      "loss": 1.2483,
      "step": 40
    },
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 0.44754377007484436,
      "learning_rate": 1.8333333333333336e-05,
      "loss": 1.1871,
      "step": 45
    },
    {
      "epoch": 0.17543859649122806,
      "grad_norm": 0.4830501675605774,
      "learning_rate": 2.0416666666666667e-05,
      "loss": 1.2557,
      "step": 50
    },
    {
      "epoch": 0.19298245614035087,
      "grad_norm": 0.5137682557106018,
      "learning_rate": 2.25e-05,
      "loss": 1.2327,
      "step": 55
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 0.6771454811096191,
      "learning_rate": 2.4583333333333332e-05,
      "loss": 1.163,
      "step": 60
    },
    {
      "epoch": 0.22807017543859648,
      "grad_norm": 0.47523486614227295,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 1.2184,
      "step": 65
    },
    {
      "epoch": 0.24561403508771928,
      "grad_norm": 0.5108222365379333,
      "learning_rate": 2.875e-05,
      "loss": 1.1653,
      "step": 70
    },
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 0.5787661075592041,
      "learning_rate": 2.9999838257323155e-05,
      "loss": 1.1365,
      "step": 75
    },
    {
      "epoch": 0.2807017543859649,
      "grad_norm": 0.5562297701835632,
      "learning_rate": 2.999801869226695e-05,
      "loss": 1.1322,
      "step": 80
    },
    {
      "epoch": 0.2982456140350877,
      "grad_norm": 0.49115923047065735,
      "learning_rate": 2.9994177629874796e-05,
      "loss": 1.1604,
      "step": 85
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 0.5512995719909668,
      "learning_rate": 2.998831558786157e-05,
      "loss": 1.1242,
      "step": 90
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.5950692892074585,
      "learning_rate": 2.9980433356338452e-05,
      "loss": 1.1483,
      "step": 95
    },
    {
      "epoch": 0.3508771929824561,
      "grad_norm": 0.5971149802207947,
      "learning_rate": 2.997053199770644e-05,
      "loss": 1.0541,
      "step": 100
    },
    {
      "epoch": 0.3684210526315789,
      "grad_norm": 0.6665179133415222,
      "learning_rate": 2.9958612846513155e-05,
      "loss": 1.0925,
      "step": 105
    },
    {
      "epoch": 0.38596491228070173,
      "grad_norm": 0.6457589864730835,
      "learning_rate": 2.994467750927295e-05,
      "loss": 1.0314,
      "step": 110
    },
    {
      "epoch": 0.40350877192982454,
      "grad_norm": 0.6131024956703186,
      "learning_rate": 2.99287278642504e-05,
      "loss": 1.0386,
      "step": 115
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 0.7078121900558472,
      "learning_rate": 2.991076606120712e-05,
      "loss": 1.0386,
      "step": 120
    },
    {
      "epoch": 0.43859649122807015,
      "grad_norm": 0.6109601259231567,
      "learning_rate": 2.989079452111202e-05,
      "loss": 1.0023,
      "step": 125
    },
    {
      "epoch": 0.45614035087719296,
      "grad_norm": 0.6941441297531128,
      "learning_rate": 2.9868815935815e-05,
      "loss": 0.9594,
      "step": 130
    },
    {
      "epoch": 0.47368421052631576,
      "grad_norm": 0.7532424330711365,
      "learning_rate": 2.9844833267684125e-05,
      "loss": 0.9634,
      "step": 135
    },
    {
      "epoch": 0.49122807017543857,
      "grad_norm": 0.6735473275184631,
      "learning_rate": 2.981884974920635e-05,
      "loss": 0.9899,
      "step": 140
    },
    {
      "epoch": 0.5087719298245614,
      "grad_norm": 0.6795721054077148,
      "learning_rate": 2.9790868882551826e-05,
      "loss": 0.9987,
      "step": 145
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 0.8002466559410095,
      "learning_rate": 2.9760894439101858e-05,
      "loss": 0.9458,
      "step": 150
    },
    {
      "epoch": 0.543859649122807,
      "grad_norm": 0.7615883946418762,
      "learning_rate": 2.97289304589406e-05,
      "loss": 0.9223,
      "step": 155
    },
    {
      "epoch": 0.5614035087719298,
      "grad_norm": 0.7222945094108582,
      "learning_rate": 2.96949812503105e-05,
      "loss": 0.9075,
      "step": 160
    },
    {
      "epoch": 0.5789473684210527,
      "grad_norm": 0.7469078302383423,
      "learning_rate": 2.9659051389031616e-05,
      "loss": 0.9037,
      "step": 165
    },
    {
      "epoch": 0.5964912280701754,
      "grad_norm": 0.7908621430397034,
      "learning_rate": 2.9621145717884875e-05,
      "loss": 0.8794,
      "step": 170
    },
    {
      "epoch": 0.6140350877192983,
      "grad_norm": 0.8037143349647522,
      "learning_rate": 2.9581269345959334e-05,
      "loss": 0.8801,
      "step": 175
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 0.8847508430480957,
      "learning_rate": 2.953942764796357e-05,
      "loss": 0.9097,
      "step": 180
    },
    {
      "epoch": 0.6491228070175439,
      "grad_norm": 0.8524879217147827,
      "learning_rate": 2.9495626263501234e-05,
      "loss": 0.858,
      "step": 185
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.7811633944511414,
      "learning_rate": 2.9449871096310937e-05,
      "loss": 0.8413,
      "step": 190
    },
    {
      "epoch": 0.6842105263157895,
      "grad_norm": 0.797070324420929,
      "learning_rate": 2.940216831347051e-05,
      "loss": 0.8822,
      "step": 195
    },
    {
      "epoch": 0.7017543859649122,
      "grad_norm": 0.8127879500389099,
      "learning_rate": 2.935252434456578e-05,
      "loss": 0.8048,
      "step": 200
    },
    {
      "epoch": 0.7192982456140351,
      "grad_norm": 0.8690300583839417,
      "learning_rate": 2.9300945880823957e-05,
      "loss": 0.8857,
      "step": 205
    },
    {
      "epoch": 0.7368421052631579,
      "grad_norm": 0.9427959322929382,
      "learning_rate": 2.9247439874211792e-05,
      "loss": 0.8438,
      "step": 210
    },
    {
      "epoch": 0.7543859649122807,
      "grad_norm": 0.9349603652954102,
      "learning_rate": 2.919201353649851e-05,
      "loss": 0.8569,
      "step": 215
    },
    {
      "epoch": 0.7719298245614035,
      "grad_norm": 1.0479152202606201,
      "learning_rate": 2.9134674338283824e-05,
      "loss": 0.8157,
      "step": 220
    },
    {
      "epoch": 0.7894736842105263,
      "grad_norm": 0.8828158974647522,
      "learning_rate": 2.9075430007990978e-05,
      "loss": 0.7808,
      "step": 225
    },
    {
      "epoch": 0.8070175438596491,
      "grad_norm": 1.0486538410186768,
      "learning_rate": 2.9014288530825118e-05,
      "loss": 0.7673,
      "step": 230
    },
    {
      "epoch": 0.8245614035087719,
      "grad_norm": 0.9675076603889465,
      "learning_rate": 2.8951258147696973e-05,
      "loss": 0.7512,
      "step": 235
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 0.9661276936531067,
      "learning_rate": 2.8886347354112122e-05,
      "loss": 0.7903,
      "step": 240
    },
    {
      "epoch": 0.8596491228070176,
      "grad_norm": 1.0554648637771606,
      "learning_rate": 2.8819564899025953e-05,
      "loss": 0.7277,
      "step": 245
    },
    {
      "epoch": 0.8771929824561403,
      "grad_norm": 0.8913574814796448,
      "learning_rate": 2.875091978366441e-05,
      "loss": 0.7391,
      "step": 250
    },
    {
      "epoch": 0.8947368421052632,
      "grad_norm": 0.9491333961486816,
      "learning_rate": 2.8680421260310794e-05,
      "loss": 0.7534,
      "step": 255
    },
    {
      "epoch": 0.9122807017543859,
      "grad_norm": 0.9836607575416565,
      "learning_rate": 2.8608078831058683e-05,
      "loss": 0.7263,
      "step": 260
    },
    {
      "epoch": 0.9298245614035088,
      "grad_norm": 0.9923145771026611,
      "learning_rate": 2.8533902246531206e-05,
      "loss": 0.7526,
      "step": 265
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": 1.0657049417495728,
      "learning_rate": 2.8457901504566824e-05,
      "loss": 0.6987,
      "step": 270
    },
    {
      "epoch": 0.9649122807017544,
      "grad_norm": 0.9763380289077759,
      "learning_rate": 2.838008684887176e-05,
      "loss": 0.672,
      "step": 275
    },
    {
      "epoch": 0.9824561403508771,
      "grad_norm": 1.1240227222442627,
      "learning_rate": 2.8300468767639306e-05,
      "loss": 0.7127,
      "step": 280
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.302412748336792,
      "learning_rate": 2.8219057992136215e-05,
      "loss": 0.7443,
      "step": 285
    }
  ],
  "logging_steps": 5,
  "max_steps": 1425,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 2000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.977535706711982e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}