{
  "best_global_step": 625,
  "best_metric": 0.18495811522006989,
  "best_model_checkpoint": "./results/checkpoint-625",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 625,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.016,
      "grad_norm": 19.218093872070312,
      "learning_rate": 4.9640000000000006e-05,
      "loss": 0.09028505682945251,
      "step": 10
    },
    {
      "epoch": 0.032,
      "grad_norm": 1.0261529684066772,
      "learning_rate": 4.924e-05,
      "loss": 0.15324625968933106,
      "step": 20
    },
    {
      "epoch": 0.048,
      "grad_norm": 21.003023147583008,
      "learning_rate": 4.884e-05,
      "loss": 0.22774670124053956,
      "step": 30
    },
    {
      "epoch": 0.064,
      "grad_norm": 7.388162612915039,
      "learning_rate": 4.8440000000000004e-05,
      "loss": 0.4121945858001709,
      "step": 40
    },
    {
      "epoch": 0.08,
      "grad_norm": 4.979572296142578,
      "learning_rate": 4.804e-05,
      "loss": 0.38861570358276365,
      "step": 50
    },
    {
      "epoch": 0.096,
      "grad_norm": 5.862935543060303,
      "learning_rate": 4.7640000000000005e-05,
      "loss": 0.29872808456420896,
      "step": 60
    },
    {
      "epoch": 0.112,
      "grad_norm": 8.852452278137207,
      "learning_rate": 4.724e-05,
      "loss": 0.3256639242172241,
      "step": 70
    },
    {
      "epoch": 0.128,
      "grad_norm": 3.3186402320861816,
      "learning_rate": 4.684e-05,
      "loss": 0.3397534847259521,
      "step": 80
    },
    {
      "epoch": 0.144,
      "grad_norm": 5.926950931549072,
      "learning_rate": 4.644e-05,
      "loss": 0.19672555923461915,
      "step": 90
    },
    {
      "epoch": 0.16,
      "grad_norm": 9.196661949157715,
      "learning_rate": 4.604e-05,
      "loss": 0.2907862663269043,
      "step": 100
    },
    {
      "epoch": 0.176,
      "grad_norm": 5.412224292755127,
      "learning_rate": 4.564e-05,
      "loss": 0.2230736255645752,
      "step": 110
    },
    {
      "epoch": 0.192,
      "grad_norm": 2.8200976848602295,
      "learning_rate": 4.524000000000001e-05,
      "loss": 0.3943183422088623,
      "step": 120
    },
    {
      "epoch": 0.208,
      "grad_norm": 11.510780334472656,
      "learning_rate": 4.4840000000000004e-05,
      "loss": 0.28646397590637207,
      "step": 130
    },
    {
      "epoch": 0.224,
      "grad_norm": 3.909830093383789,
      "learning_rate": 4.444e-05,
      "loss": 0.346493124961853,
      "step": 140
    },
    {
      "epoch": 0.24,
      "grad_norm": 3.446835517883301,
      "learning_rate": 4.4040000000000005e-05,
      "loss": 0.2555964946746826,
      "step": 150
    },
    {
      "epoch": 0.256,
      "grad_norm": 8.182538032531738,
      "learning_rate": 4.364e-05,
      "loss": 0.24913170337677001,
      "step": 160
    },
    {
      "epoch": 0.272,
      "grad_norm": 4.328517913818359,
      "learning_rate": 4.324e-05,
      "loss": 0.3257677316665649,
      "step": 170
    },
    {
      "epoch": 0.288,
      "grad_norm": 4.964771270751953,
      "learning_rate": 4.284e-05,
      "loss": 0.28899221420288085,
      "step": 180
    },
    {
      "epoch": 0.304,
      "grad_norm": 9.758742332458496,
      "learning_rate": 4.244e-05,
      "loss": 0.2279355764389038,
      "step": 190
    },
    {
      "epoch": 0.32,
      "grad_norm": 4.366827964782715,
      "learning_rate": 4.2040000000000004e-05,
      "loss": 0.31453232765197753,
      "step": 200
    },
    {
      "epoch": 0.336,
      "grad_norm": 2.277212381362915,
      "learning_rate": 4.164e-05,
      "loss": 0.20993876457214355,
      "step": 210
    },
    {
      "epoch": 0.352,
      "grad_norm": 4.816099166870117,
      "learning_rate": 4.124e-05,
      "loss": 0.27517788410186766,
      "step": 220
    },
    {
      "epoch": 0.368,
      "grad_norm": 3.51198673248291,
      "learning_rate": 4.084e-05,
      "loss": 0.22087533473968507,
      "step": 230
    },
    {
      "epoch": 0.384,
      "grad_norm": 5.840693950653076,
      "learning_rate": 4.044e-05,
      "loss": 0.20846953392028808,
      "step": 240
    },
    {
      "epoch": 0.4,
      "grad_norm": 3.9098050594329834,
      "learning_rate": 4.004e-05,
      "loss": 0.26031317710876467,
      "step": 250
    },
    {
      "epoch": 0.416,
      "grad_norm": 3.918344020843506,
      "learning_rate": 3.964e-05,
      "loss": 0.2516783714294434,
      "step": 260
    },
    {
      "epoch": 0.432,
      "grad_norm": 8.892339706420898,
      "learning_rate": 3.9240000000000004e-05,
      "loss": 0.2795307159423828,
      "step": 270
    },
    {
      "epoch": 0.448,
      "grad_norm": 4.103593826293945,
      "learning_rate": 3.884e-05,
      "loss": 0.23137011528015136,
      "step": 280
    },
    {
      "epoch": 0.464,
      "grad_norm": 6.328890800476074,
      "learning_rate": 3.8440000000000005e-05,
      "loss": 0.22461700439453125,
      "step": 290
    },
    {
      "epoch": 0.48,
      "grad_norm": 6.5414719581604,
      "learning_rate": 3.804e-05,
      "loss": 0.21610186100006104,
      "step": 300
    },
    {
      "epoch": 0.496,
      "grad_norm": 3.691993474960327,
      "learning_rate": 3.7640000000000006e-05,
      "loss": 0.24925684928894043,
      "step": 310
    },
    {
      "epoch": 0.512,
      "grad_norm": 4.344432353973389,
      "learning_rate": 3.724e-05,
      "loss": 0.21005148887634278,
      "step": 320
    },
    {
      "epoch": 0.528,
      "grad_norm": 7.790218353271484,
      "learning_rate": 3.684e-05,
      "loss": 0.17650561332702636,
      "step": 330
    },
    {
      "epoch": 0.544,
      "grad_norm": 7.356423854827881,
      "learning_rate": 3.6440000000000003e-05,
      "loss": 0.2985139131546021,
      "step": 340
    },
    {
      "epoch": 0.56,
      "grad_norm": 2.8463327884674072,
      "learning_rate": 3.604e-05,
      "loss": 0.20631999969482423,
      "step": 350
    },
    {
      "epoch": 0.576,
      "grad_norm": 7.239101409912109,
      "learning_rate": 3.5640000000000004e-05,
      "loss": 0.2260190486907959,
      "step": 360
    },
    {
      "epoch": 0.592,
      "grad_norm": 6.864079475402832,
      "learning_rate": 3.524e-05,
      "loss": 0.29787819385528563,
      "step": 370
    },
    {
      "epoch": 0.608,
      "grad_norm": 4.634511947631836,
      "learning_rate": 3.484e-05,
      "loss": 0.2093559741973877,
      "step": 380
    },
    {
      "epoch": 0.624,
      "grad_norm": 8.057502746582031,
      "learning_rate": 3.444e-05,
      "loss": 0.23704848289489747,
      "step": 390
    },
    {
      "epoch": 0.64,
      "grad_norm": 2.670377731323242,
      "learning_rate": 3.404e-05,
      "loss": 0.20256345272064208,
      "step": 400
    },
    {
      "epoch": 0.656,
      "grad_norm": 5.436578273773193,
      "learning_rate": 3.3639999999999996e-05,
      "loss": 0.2178948402404785,
      "step": 410
    },
    {
      "epoch": 0.672,
      "grad_norm": 2.7397665977478027,
      "learning_rate": 3.324e-05,
      "loss": 0.28787732124328613,
      "step": 420
    },
    {
      "epoch": 0.688,
      "grad_norm": 7.691206455230713,
      "learning_rate": 3.2840000000000004e-05,
      "loss": 0.2569857358932495,
      "step": 430
    },
    {
      "epoch": 0.704,
      "grad_norm": 2.859588623046875,
      "learning_rate": 3.244e-05,
      "loss": 0.21177470684051514,
      "step": 440
    },
    {
      "epoch": 0.72,
      "grad_norm": 8.864638328552246,
      "learning_rate": 3.2040000000000005e-05,
      "loss": 0.21835825443267823,
      "step": 450
    },
    {
      "epoch": 0.736,
      "grad_norm": 3.5713469982147217,
      "learning_rate": 3.164e-05,
      "loss": 0.18327864408493041,
      "step": 460
    },
    {
      "epoch": 0.752,
      "grad_norm": 4.1505351066589355,
      "learning_rate": 3.1240000000000006e-05,
      "loss": 0.23397378921508788,
      "step": 470
    },
    {
      "epoch": 0.768,
      "grad_norm": 7.102250099182129,
      "learning_rate": 3.084e-05,
      "loss": 0.2387765645980835,
      "step": 480
    },
    {
      "epoch": 0.784,
      "grad_norm": 2.268003225326538,
      "learning_rate": 3.0440000000000003e-05,
      "loss": 0.24410586357116698,
      "step": 490
    },
    {
      "epoch": 0.8,
      "grad_norm": 7.200525760650635,
      "learning_rate": 3.004e-05,
      "loss": 0.22940239906311036,
      "step": 500
    },
    {
      "epoch": 0.816,
      "grad_norm": 6.109457015991211,
      "learning_rate": 2.964e-05,
      "loss": 0.23941683769226074,
      "step": 510
    },
    {
      "epoch": 0.832,
      "grad_norm": 2.041025400161743,
      "learning_rate": 2.924e-05,
      "loss": 0.2272693157196045,
      "step": 520
    },
    {
      "epoch": 0.848,
      "grad_norm": 3.117744207382202,
      "learning_rate": 2.8840000000000002e-05,
      "loss": 0.3034891843795776,
      "step": 530
    },
    {
      "epoch": 0.864,
      "grad_norm": 3.5636343955993652,
      "learning_rate": 2.844e-05,
      "loss": 0.22543411254882811,
      "step": 540
    },
    {
      "epoch": 0.88,
      "grad_norm": 5.813530921936035,
      "learning_rate": 2.804e-05,
      "loss": 0.15515211820602418,
      "step": 550
    },
    {
      "epoch": 0.896,
      "grad_norm": 3.961332082748413,
      "learning_rate": 2.764e-05,
      "loss": 0.18014708757400513,
      "step": 560
    },
    {
      "epoch": 0.912,
      "grad_norm": 4.513957500457764,
      "learning_rate": 2.724e-05,
      "loss": 0.15350849628448487,
      "step": 570
    },
    {
      "epoch": 0.928,
      "grad_norm": 4.664239406585693,
      "learning_rate": 2.6840000000000004e-05,
      "loss": 0.17080495357513428,
      "step": 580
    },
    {
      "epoch": 0.944,
      "grad_norm": 4.640005588531494,
      "learning_rate": 2.6440000000000004e-05,
      "loss": 0.2014240026473999,
      "step": 590
    },
    {
      "epoch": 0.96,
      "grad_norm": 4.601800441741943,
      "learning_rate": 2.6040000000000005e-05,
      "loss": 0.14860270023345948,
      "step": 600
    },
    {
      "epoch": 0.976,
      "grad_norm": 3.3365046977996826,
      "learning_rate": 2.5640000000000002e-05,
      "loss": 0.16999433040618897,
      "step": 610
    },
    {
      "epoch": 0.992,
      "grad_norm": 11.081926345825195,
      "learning_rate": 2.5240000000000002e-05,
      "loss": 0.2594302177429199,
      "step": 620
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.18495811522006989,
      "eval_runtime": 154.2281,
      "eval_samples_per_second": 32.42,
      "eval_steps_per_second": 1.018,
      "step": 625
    }
  ],
  "logging_steps": 10,
  "max_steps": 1250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 5262221107200000.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}