{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.007653061224489796,
  "eval_steps": 500,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00025510204081632655,
      "grad_norm": 2.689539670944214,
      "learning_rate": 1.9995e-05,
      "loss": 8.2037,
      "step": 50
    },
    {
      "epoch": 0.0005102040816326531,
      "grad_norm": 2.3293910026550293,
      "learning_rate": 1.9989897959183675e-05,
      "loss": 6.9309,
      "step": 100
    },
    {
      "epoch": 0.0007653061224489796,
      "grad_norm": 2.9805541038513184,
      "learning_rate": 1.9984795918367347e-05,
      "loss": 6.6153,
      "step": 150
    },
    {
      "epoch": 0.0010204081632653062,
      "grad_norm": 2.419286012649536,
      "learning_rate": 1.9979693877551025e-05,
      "loss": 6.3907,
      "step": 200
    },
    {
      "epoch": 0.0012755102040816326,
      "grad_norm": 2.8373420238494873,
      "learning_rate": 1.9974591836734696e-05,
      "loss": 6.2331,
      "step": 250
    },
    {
      "epoch": 0.001530612244897959,
      "grad_norm": 3.41703462600708,
      "learning_rate": 1.9969489795918367e-05,
      "loss": 6.0079,
      "step": 300
    },
    {
      "epoch": 0.0017857142857142857,
      "grad_norm": 1.9326502084732056,
      "learning_rate": 1.996438775510204e-05,
      "loss": 6.8421,
      "step": 350
    },
    {
      "epoch": 0.0020408163265306124,
      "grad_norm": 1.9628627300262451,
      "learning_rate": 1.9959285714285716e-05,
      "loss": 6.7932,
      "step": 400
    },
    {
      "epoch": 0.002295918367346939,
      "grad_norm": 1.8839755058288574,
      "learning_rate": 1.995418367346939e-05,
      "loss": 6.6473,
      "step": 450
    },
    {
      "epoch": 0.002551020408163265,
      "grad_norm": 2.1319727897644043,
      "learning_rate": 1.9949081632653062e-05,
      "loss": 6.5281,
      "step": 500
    },
    {
      "epoch": 0.0028061224489795917,
      "grad_norm": 2.1496269702911377,
      "learning_rate": 1.9943979591836737e-05,
      "loss": 6.417,
      "step": 550
    },
    {
      "epoch": 0.003061224489795918,
      "grad_norm": 1.9443697929382324,
      "learning_rate": 1.993887755102041e-05,
      "loss": 6.3274,
      "step": 600
    },
    {
      "epoch": 0.0033163265306122448,
      "grad_norm": 2.0376827716827393,
      "learning_rate": 1.9933775510204082e-05,
      "loss": 6.2191,
      "step": 650
    },
    {
      "epoch": 0.0035714285714285713,
      "grad_norm": 2.2743828296661377,
      "learning_rate": 1.9928673469387757e-05,
      "loss": 6.1371,
      "step": 700
    },
    {
      "epoch": 0.003826530612244898,
      "grad_norm": 1.8305890560150146,
      "learning_rate": 1.992357142857143e-05,
      "loss": 6.0537,
      "step": 750
    },
    {
      "epoch": 0.004081632653061225,
      "grad_norm": 2.600226402282715,
      "learning_rate": 1.9918469387755103e-05,
      "loss": 6.0223,
      "step": 800
    },
    {
      "epoch": 0.004336734693877551,
      "grad_norm": 2.161254644393921,
      "learning_rate": 1.9913367346938777e-05,
      "loss": 6.0193,
      "step": 850
    },
    {
      "epoch": 0.004591836734693878,
      "grad_norm": 2.131312131881714,
      "learning_rate": 1.990826530612245e-05,
      "loss": 5.9072,
      "step": 900
    },
    {
      "epoch": 0.004846938775510204,
      "grad_norm": 2.2562108039855957,
      "learning_rate": 1.9903163265306123e-05,
      "loss": 5.8881,
      "step": 950
    },
    {
      "epoch": 0.00510204081632653,
      "grad_norm": 2.4200196266174316,
      "learning_rate": 1.9898061224489798e-05,
      "loss": 5.7981,
      "step": 1000
    },
    {
      "epoch": 0.005357142857142857,
      "grad_norm": 2.1939544677734375,
      "learning_rate": 1.989295918367347e-05,
      "loss": 5.776,
      "step": 1050
    },
    {
      "epoch": 0.005612244897959183,
      "grad_norm": 2.1955156326293945,
      "learning_rate": 1.9887857142857147e-05,
      "loss": 5.7542,
      "step": 1100
    },
    {
      "epoch": 0.00586734693877551,
      "grad_norm": 2.50158953666687,
      "learning_rate": 1.9882755102040818e-05,
      "loss": 5.6729,
      "step": 1150
    },
    {
      "epoch": 0.006122448979591836,
      "grad_norm": 2.2941956520080566,
      "learning_rate": 1.9877653061224493e-05,
      "loss": 5.5944,
      "step": 1200
    },
    {
      "epoch": 0.006377551020408163,
      "grad_norm": 2.183966875076294,
      "learning_rate": 1.9872551020408164e-05,
      "loss": 5.634,
      "step": 1250
    },
    {
      "epoch": 0.0066326530612244895,
      "grad_norm": 2.238250732421875,
      "learning_rate": 1.986744897959184e-05,
      "loss": 5.5691,
      "step": 1300
    },
    {
      "epoch": 0.0068877551020408165,
      "grad_norm": 2.298186779022217,
      "learning_rate": 1.9862346938775513e-05,
      "loss": 5.5623,
      "step": 1350
    },
    {
      "epoch": 0.007142857142857143,
      "grad_norm": 2.208320379257202,
      "learning_rate": 1.9857244897959184e-05,
      "loss": 5.4931,
      "step": 1400
    },
    {
      "epoch": 0.00739795918367347,
      "grad_norm": 2.469818353652954,
      "learning_rate": 1.985214285714286e-05,
      "loss": 5.4935,
      "step": 1450
    },
    {
      "epoch": 0.007653061224489796,
      "grad_norm": 2.56227445602417,
      "learning_rate": 1.9847040816326533e-05,
      "loss": 5.4278,
      "step": 1500
    }
  ],
  "logging_steps": 50,
  "max_steps": 196000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "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": 1.24857511575552e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}