{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.504,
  "eval_steps": 500,
  "global_step": 470,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.016,
      "grad_norm": 0.33984375,
      "learning_rate": 0.0001,
      "loss": 4.2845,
      "step": 5
    },
    {
      "epoch": 0.032,
      "grad_norm": 0.20703125,
      "learning_rate": 0.0001,
      "loss": 2.611,
      "step": 10
    },
    {
      "epoch": 0.048,
      "grad_norm": 2.8125,
      "learning_rate": 0.0001,
      "loss": 2.1007,
      "step": 15
    },
    {
      "epoch": 0.064,
      "grad_norm": 1.2890625,
      "learning_rate": 0.0001,
      "loss": 2.0667,
      "step": 20
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.3203125,
      "learning_rate": 0.0001,
      "loss": 1.6745,
      "step": 25
    },
    {
      "epoch": 0.096,
      "grad_norm": 0.33984375,
      "learning_rate": 0.0001,
      "loss": 1.4179,
      "step": 30
    },
    {
      "epoch": 0.112,
      "grad_norm": 0.369140625,
      "learning_rate": 0.0001,
      "loss": 1.256,
      "step": 35
    },
    {
      "epoch": 0.128,
      "grad_norm": 0.1767578125,
      "learning_rate": 0.0001,
      "loss": 1.1206,
      "step": 40
    },
    {
      "epoch": 0.144,
      "grad_norm": 0.1806640625,
      "learning_rate": 0.0001,
      "loss": 0.8113,
      "step": 45
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.31640625,
      "learning_rate": 0.0001,
      "loss": 0.5563,
      "step": 50
    },
    {
      "epoch": 0.176,
      "grad_norm": 0.47265625,
      "learning_rate": 0.0001,
      "loss": 1.2945,
      "step": 55
    },
    {
      "epoch": 0.192,
      "grad_norm": 0.30078125,
      "learning_rate": 0.0001,
      "loss": 1.1513,
      "step": 60
    },
    {
      "epoch": 0.208,
      "grad_norm": 0.87109375,
      "learning_rate": 0.0001,
      "loss": 1.0038,
      "step": 65
    },
    {
      "epoch": 0.224,
      "grad_norm": 0.11376953125,
      "learning_rate": 0.0001,
      "loss": 0.9775,
      "step": 70
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.1376953125,
      "learning_rate": 0.0001,
      "loss": 0.9107,
      "step": 75
    },
    {
      "epoch": 0.256,
      "grad_norm": 0.13671875,
      "learning_rate": 0.0001,
      "loss": 0.8357,
      "step": 80
    },
    {
      "epoch": 0.272,
      "grad_norm": 0.2734375,
      "learning_rate": 0.0001,
      "loss": 0.8438,
      "step": 85
    },
    {
      "epoch": 0.288,
      "grad_norm": 0.1318359375,
      "learning_rate": 0.0001,
      "loss": 0.8182,
      "step": 90
    },
    {
      "epoch": 0.304,
      "grad_norm": 0.1220703125,
      "learning_rate": 0.0001,
      "loss": 0.6811,
      "step": 95
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.1474609375,
      "learning_rate": 0.0001,
      "loss": 0.5087,
      "step": 100
    },
    {
      "epoch": 0.336,
      "grad_norm": 0.1767578125,
      "learning_rate": 0.0001,
      "loss": 0.9827,
      "step": 105
    },
    {
      "epoch": 0.352,
      "grad_norm": 0.1943359375,
      "learning_rate": 0.0001,
      "loss": 0.9673,
      "step": 110
    },
    {
      "epoch": 0.368,
      "grad_norm": 0.21484375,
      "learning_rate": 0.0001,
      "loss": 0.9514,
      "step": 115
    },
    {
      "epoch": 0.384,
      "grad_norm": 0.1630859375,
      "learning_rate": 0.0001,
      "loss": 0.8378,
      "step": 120
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.1220703125,
      "learning_rate": 0.0001,
      "loss": 0.8721,
      "step": 125
    },
    {
      "epoch": 0.416,
      "grad_norm": 0.1328125,
      "learning_rate": 0.0001,
      "loss": 0.8317,
      "step": 130
    },
    {
      "epoch": 0.432,
      "grad_norm": 0.1328125,
      "learning_rate": 0.0001,
      "loss": 0.7948,
      "step": 135
    },
    {
      "epoch": 0.448,
      "grad_norm": 0.1328125,
      "learning_rate": 0.0001,
      "loss": 0.7682,
      "step": 140
    },
    {
      "epoch": 0.464,
      "grad_norm": 0.107421875,
      "learning_rate": 0.0001,
      "loss": 0.6472,
      "step": 145
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.1513671875,
      "learning_rate": 0.0001,
      "loss": 0.463,
      "step": 150
    },
    {
      "epoch": 0.496,
      "grad_norm": 0.16015625,
      "learning_rate": 0.0001,
      "loss": 0.8907,
      "step": 155
    },
    {
      "epoch": 0.512,
      "grad_norm": 0.1337890625,
      "learning_rate": 0.0001,
      "loss": 0.8254,
      "step": 160
    },
    {
      "epoch": 0.528,
      "grad_norm": 0.146484375,
      "learning_rate": 0.0001,
      "loss": 0.8455,
      "step": 165
    },
    {
      "epoch": 0.544,
      "grad_norm": 0.15625,
      "learning_rate": 0.0001,
      "loss": 0.8194,
      "step": 170
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.166015625,
      "learning_rate": 0.0001,
      "loss": 0.8291,
      "step": 175
    },
    {
      "epoch": 0.576,
      "grad_norm": 0.1787109375,
      "learning_rate": 0.0001,
      "loss": 0.7265,
      "step": 180
    },
    {
      "epoch": 0.592,
      "grad_norm": 0.208984375,
      "learning_rate": 0.0001,
      "loss": 0.7856,
      "step": 185
    },
    {
      "epoch": 0.608,
      "grad_norm": 0.2216796875,
      "learning_rate": 0.0001,
      "loss": 0.7599,
      "step": 190
    },
    {
      "epoch": 0.624,
      "grad_norm": 0.130859375,
      "learning_rate": 0.0001,
      "loss": 0.6127,
      "step": 195
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.1982421875,
      "learning_rate": 0.0001,
      "loss": 0.4152,
      "step": 200
    },
    {
      "epoch": 0.656,
      "grad_norm": 0.1943359375,
      "learning_rate": 0.0001,
      "loss": 0.8772,
      "step": 205
    },
    {
      "epoch": 0.672,
      "grad_norm": 0.197265625,
      "learning_rate": 0.0001,
      "loss": 0.7661,
      "step": 210
    },
    {
      "epoch": 0.688,
      "grad_norm": 0.173828125,
      "learning_rate": 0.0001,
      "loss": 0.8362,
      "step": 215
    },
    {
      "epoch": 0.704,
      "grad_norm": 0.18359375,
      "learning_rate": 0.0001,
      "loss": 0.6781,
      "step": 220
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.1708984375,
      "learning_rate": 0.0001,
      "loss": 0.7479,
      "step": 225
    },
    {
      "epoch": 0.736,
      "grad_norm": 0.177734375,
      "learning_rate": 0.0001,
      "loss": 0.6598,
      "step": 230
    },
    {
      "epoch": 0.752,
      "grad_norm": 0.177734375,
      "learning_rate": 0.0001,
      "loss": 0.7109,
      "step": 235
    },
    {
      "epoch": 0.768,
      "grad_norm": 0.1337890625,
      "learning_rate": 0.0001,
      "loss": 0.6603,
      "step": 240
    },
    {
      "epoch": 0.784,
      "grad_norm": 0.1494140625,
      "learning_rate": 0.0001,
      "loss": 0.5983,
      "step": 245
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.1630859375,
      "learning_rate": 0.0001,
      "loss": 0.3945,
      "step": 250
    },
    {
      "epoch": 0.816,
      "grad_norm": 0.173828125,
      "learning_rate": 0.0001,
      "loss": 0.7734,
      "step": 255
    },
    {
      "epoch": 0.832,
      "grad_norm": 0.2021484375,
      "learning_rate": 0.0001,
      "loss": 0.7553,
      "step": 260
    },
    {
      "epoch": 0.848,
      "grad_norm": 0.177734375,
      "learning_rate": 0.0001,
      "loss": 0.8062,
      "step": 265
    },
    {
      "epoch": 0.864,
      "grad_norm": 0.150390625,
      "learning_rate": 0.0001,
      "loss": 0.6815,
      "step": 270
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.1689453125,
      "learning_rate": 0.0001,
      "loss": 0.7524,
      "step": 275
    },
    {
      "epoch": 0.896,
      "grad_norm": 0.1572265625,
      "learning_rate": 0.0001,
      "loss": 0.6798,
      "step": 280
    },
    {
      "epoch": 0.912,
      "grad_norm": 0.177734375,
      "learning_rate": 0.0001,
      "loss": 0.7037,
      "step": 285
    },
    {
      "epoch": 0.928,
      "grad_norm": 0.1591796875,
      "learning_rate": 0.0001,
      "loss": 0.6274,
      "step": 290
    },
    {
      "epoch": 0.944,
      "grad_norm": 0.1630859375,
      "learning_rate": 0.0001,
      "loss": 0.6103,
      "step": 295
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.22265625,
      "learning_rate": 0.0001,
      "loss": 0.3983,
      "step": 300
    },
    {
      "epoch": 0.976,
      "grad_norm": 0.1611328125,
      "learning_rate": 0.0001,
      "loss": 0.6683,
      "step": 305
    },
    {
      "epoch": 0.992,
      "grad_norm": 0.1533203125,
      "learning_rate": 0.0001,
      "loss": 0.6045,
      "step": 310
    },
    {
      "epoch": 1.008,
      "grad_norm": 0.1630859375,
      "learning_rate": 0.0001,
      "loss": 0.5759,
      "step": 315
    },
    {
      "epoch": 1.024,
      "grad_norm": 0.1904296875,
      "learning_rate": 0.0001,
      "loss": 0.5826,
      "step": 320
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.2490234375,
      "learning_rate": 0.0001,
      "loss": 0.6502,
      "step": 325
    },
    {
      "epoch": 1.056,
      "grad_norm": 0.2353515625,
      "learning_rate": 0.0001,
      "loss": 0.6278,
      "step": 330
    },
    {
      "epoch": 1.072,
      "grad_norm": 0.1904296875,
      "learning_rate": 0.0001,
      "loss": 0.6155,
      "step": 335
    },
    {
      "epoch": 1.088,
      "grad_norm": 0.2265625,
      "learning_rate": 0.0001,
      "loss": 0.6104,
      "step": 340
    },
    {
      "epoch": 1.104,
      "grad_norm": 0.21875,
      "learning_rate": 0.0001,
      "loss": 0.5942,
      "step": 345
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.224609375,
      "learning_rate": 0.0001,
      "loss": 0.6177,
      "step": 350
    },
    {
      "epoch": 1.1360000000000001,
      "grad_norm": 0.1796875,
      "learning_rate": 0.0001,
      "loss": 0.5307,
      "step": 355
    },
    {
      "epoch": 1.152,
      "grad_norm": 0.1630859375,
      "learning_rate": 0.0001,
      "loss": 0.443,
      "step": 360
    },
    {
      "epoch": 1.168,
      "grad_norm": 0.2431640625,
      "learning_rate": 0.0001,
      "loss": 0.4582,
      "step": 365
    },
    {
      "epoch": 1.184,
      "grad_norm": 0.2138671875,
      "learning_rate": 0.0001,
      "loss": 0.6175,
      "step": 370
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.22265625,
      "learning_rate": 0.0001,
      "loss": 0.6191,
      "step": 375
    },
    {
      "epoch": 1.216,
      "grad_norm": 0.25,
      "learning_rate": 0.0001,
      "loss": 0.5887,
      "step": 380
    },
    {
      "epoch": 1.232,
      "grad_norm": 0.1962890625,
      "learning_rate": 0.0001,
      "loss": 0.5517,
      "step": 385
    },
    {
      "epoch": 1.248,
      "grad_norm": 0.2109375,
      "learning_rate": 0.0001,
      "loss": 0.5712,
      "step": 390
    },
    {
      "epoch": 1.264,
      "grad_norm": 0.1904296875,
      "learning_rate": 0.0001,
      "loss": 0.5526,
      "step": 395
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.2119140625,
      "learning_rate": 0.0001,
      "loss": 0.6027,
      "step": 400
    },
    {
      "epoch": 1.296,
      "grad_norm": 0.1865234375,
      "learning_rate": 0.0001,
      "loss": 0.5325,
      "step": 405
    },
    {
      "epoch": 1.312,
      "grad_norm": 0.212890625,
      "learning_rate": 0.0001,
      "loss": 0.4752,
      "step": 410
    },
    {
      "epoch": 1.328,
      "grad_norm": 0.25,
      "learning_rate": 0.0001,
      "loss": 0.4214,
      "step": 415
    },
    {
      "epoch": 1.3439999999999999,
      "grad_norm": 0.306640625,
      "learning_rate": 0.0001,
      "loss": 0.6299,
      "step": 420
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 0.361328125,
      "learning_rate": 0.0001,
      "loss": 0.6215,
      "step": 425
    },
    {
      "epoch": 1.376,
      "grad_norm": 0.310546875,
      "learning_rate": 0.0001,
      "loss": 0.5869,
      "step": 430
    },
    {
      "epoch": 1.392,
      "grad_norm": 0.2255859375,
      "learning_rate": 0.0001,
      "loss": 0.5448,
      "step": 435
    },
    {
      "epoch": 1.408,
      "grad_norm": 0.306640625,
      "learning_rate": 0.0001,
      "loss": 0.6038,
      "step": 440
    },
    {
      "epoch": 1.424,
      "grad_norm": 0.37890625,
      "learning_rate": 0.0001,
      "loss": 0.5647,
      "step": 445
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.26953125,
      "learning_rate": 0.0001,
      "loss": 0.5564,
      "step": 450
    },
    {
      "epoch": 1.456,
      "grad_norm": 0.1796875,
      "learning_rate": 0.0001,
      "loss": 0.4994,
      "step": 455
    },
    {
      "epoch": 1.472,
      "grad_norm": 0.25,
      "learning_rate": 0.0001,
      "loss": 0.4244,
      "step": 460
    },
    {
      "epoch": 1.488,
      "grad_norm": 0.2451171875,
      "learning_rate": 0.0001,
      "loss": 0.4652,
      "step": 465
    },
    {
      "epoch": 1.504,
      "grad_norm": 0.2578125,
      "learning_rate": 0.0001,
      "loss": 0.5929,
      "step": 470
    }
  ],
  "logging_steps": 5,
  "max_steps": 470,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 90,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.7094162776644813e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}