{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.980039920159681,
  "eval_steps": 500,
  "global_step": 20000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.249500998003992,
      "grad_norm": 2.452378511428833,
      "learning_rate": 4.876746506986028e-05,
      "loss": 2.1274,
      "step": 500
    },
    {
      "epoch": 0.499001996007984,
      "grad_norm": 10.962518692016602,
      "learning_rate": 4.751996007984032e-05,
      "loss": 1.3207,
      "step": 1000
    },
    {
      "epoch": 0.7485029940119761,
      "grad_norm": 2.4429094791412354,
      "learning_rate": 4.627245508982036e-05,
      "loss": 1.138,
      "step": 1500
    },
    {
      "epoch": 0.998003992015968,
      "grad_norm": 2.2755186557769775,
      "learning_rate": 4.50249500998004e-05,
      "loss": 1.0141,
      "step": 2000
    },
    {
      "epoch": 1.24750499001996,
      "grad_norm": 1.8802367448806763,
      "learning_rate": 4.377744510978044e-05,
      "loss": 0.8877,
      "step": 2500
    },
    {
      "epoch": 1.4970059880239521,
      "grad_norm": 3.98767352104187,
      "learning_rate": 4.252994011976048e-05,
      "loss": 0.8705,
      "step": 3000
    },
    {
      "epoch": 1.746506986027944,
      "grad_norm": 1.9973433017730713,
      "learning_rate": 4.128243512974052e-05,
      "loss": 0.826,
      "step": 3500
    },
    {
      "epoch": 1.996007984031936,
      "grad_norm": 2.2026467323303223,
      "learning_rate": 4.003493013972056e-05,
      "loss": 0.8115,
      "step": 4000
    },
    {
      "epoch": 2.245508982035928,
      "grad_norm": 2.212198257446289,
      "learning_rate": 3.87874251497006e-05,
      "loss": 0.6751,
      "step": 4500
    },
    {
      "epoch": 2.49500998003992,
      "grad_norm": 1.5753542184829712,
      "learning_rate": 3.754241516966068e-05,
      "loss": 0.6747,
      "step": 5000
    },
    {
      "epoch": 2.744510978043912,
      "grad_norm": 2.395479202270508,
      "learning_rate": 3.629491017964072e-05,
      "loss": 0.6646,
      "step": 5500
    },
    {
      "epoch": 2.9940119760479043,
      "grad_norm": 2.577756643295288,
      "learning_rate": 3.504740518962076e-05,
      "loss": 0.66,
      "step": 6000
    },
    {
      "epoch": 3.243512974051896,
      "grad_norm": 2.7224512100219727,
      "learning_rate": 3.3799900199600795e-05,
      "loss": 0.5135,
      "step": 6500
    },
    {
      "epoch": 3.493013972055888,
      "grad_norm": 2.3300223350524902,
      "learning_rate": 3.255239520958084e-05,
      "loss": 0.5112,
      "step": 7000
    },
    {
      "epoch": 3.7425149700598803,
      "grad_norm": 2.3015055656433105,
      "learning_rate": 3.130489021956088e-05,
      "loss": 0.5119,
      "step": 7500
    },
    {
      "epoch": 3.992015968063872,
      "grad_norm": 2.4661030769348145,
      "learning_rate": 3.0057385229540918e-05,
      "loss": 0.5107,
      "step": 8000
    },
    {
      "epoch": 4.241516966067865,
      "grad_norm": 2.5810928344726562,
      "learning_rate": 2.880988023952096e-05,
      "loss": 0.3741,
      "step": 8500
    },
    {
      "epoch": 4.491017964071856,
      "grad_norm": 1.8933159112930298,
      "learning_rate": 2.7562375249501e-05,
      "loss": 0.3756,
      "step": 9000
    },
    {
      "epoch": 4.740518962075848,
      "grad_norm": 2.711456775665283,
      "learning_rate": 2.6314870259481038e-05,
      "loss": 0.3745,
      "step": 9500
    },
    {
      "epoch": 4.99001996007984,
      "grad_norm": 2.8451802730560303,
      "learning_rate": 2.506736526946108e-05,
      "loss": 0.3743,
      "step": 10000
    },
    {
      "epoch": 5.2395209580838324,
      "grad_norm": 2.1212046146392822,
      "learning_rate": 2.381986027944112e-05,
      "loss": 0.2603,
      "step": 10500
    },
    {
      "epoch": 5.489021956087824,
      "grad_norm": 2.1375863552093506,
      "learning_rate": 2.257235528942116e-05,
      "loss": 0.2567,
      "step": 11000
    },
    {
      "epoch": 5.738522954091817,
      "grad_norm": 3.2050704956054688,
      "learning_rate": 2.1324850299401196e-05,
      "loss": 0.2596,
      "step": 11500
    },
    {
      "epoch": 5.9880239520958085,
      "grad_norm": 1.9162492752075195,
      "learning_rate": 2.007734530938124e-05,
      "loss": 0.2692,
      "step": 12000
    },
    {
      "epoch": 6.2375249500998,
      "grad_norm": 1.6697739362716675,
      "learning_rate": 1.8829840319361277e-05,
      "loss": 0.1711,
      "step": 12500
    },
    {
      "epoch": 6.487025948103792,
      "grad_norm": 2.253767728805542,
      "learning_rate": 1.758233532934132e-05,
      "loss": 0.1705,
      "step": 13000
    },
    {
      "epoch": 6.736526946107785,
      "grad_norm": 1.5864336490631104,
      "learning_rate": 1.6337325349301397e-05,
      "loss": 0.1735,
      "step": 13500
    },
    {
      "epoch": 6.986027944111776,
      "grad_norm": 2.6011617183685303,
      "learning_rate": 1.5089820359281437e-05,
      "loss": 0.1785,
      "step": 14000
    },
    {
      "epoch": 7.235528942115769,
      "grad_norm": 1.8357607126235962,
      "learning_rate": 1.3842315369261476e-05,
      "loss": 0.1101,
      "step": 14500
    },
    {
      "epoch": 7.485029940119761,
      "grad_norm": 2.048788547515869,
      "learning_rate": 1.2594810379241517e-05,
      "loss": 0.1152,
      "step": 15000
    },
    {
      "epoch": 7.734530938123752,
      "grad_norm": 2.7625575065612793,
      "learning_rate": 1.1347305389221557e-05,
      "loss": 0.1126,
      "step": 15500
    },
    {
      "epoch": 7.984031936127744,
      "grad_norm": 2.9754233360290527,
      "learning_rate": 1.0099800399201598e-05,
      "loss": 0.1116,
      "step": 16000
    },
    {
      "epoch": 8.233532934131736,
      "grad_norm": 2.279146909713745,
      "learning_rate": 8.852295409181637e-06,
      "loss": 0.0743,
      "step": 16500
    },
    {
      "epoch": 8.48303393213573,
      "grad_norm": 2.4354634284973145,
      "learning_rate": 7.604790419161677e-06,
      "loss": 0.074,
      "step": 17000
    },
    {
      "epoch": 8.732534930139721,
      "grad_norm": 2.9256038665771484,
      "learning_rate": 6.357285429141717e-06,
      "loss": 0.0722,
      "step": 17500
    },
    {
      "epoch": 8.982035928143713,
      "grad_norm": 1.8734424114227295,
      "learning_rate": 5.109780439121756e-06,
      "loss": 0.0703,
      "step": 18000
    },
    {
      "epoch": 9.231536926147704,
      "grad_norm": 2.1415419578552246,
      "learning_rate": 3.862275449101797e-06,
      "loss": 0.0503,
      "step": 18500
    },
    {
      "epoch": 9.481037924151696,
      "grad_norm": 2.486562490463257,
      "learning_rate": 2.6172654690618765e-06,
      "loss": 0.0497,
      "step": 19000
    },
    {
      "epoch": 9.730538922155688,
      "grad_norm": 1.6438294649124146,
      "learning_rate": 1.3697604790419162e-06,
      "loss": 0.0467,
      "step": 19500
    },
    {
      "epoch": 9.980039920159681,
      "grad_norm": 2.3399159908294678,
      "learning_rate": 1.222554890219561e-07,
      "loss": 0.0457,
      "step": 20000
    }
  ],
  "logging_steps": 500,
  "max_steps": 20040,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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": 2.167129767936e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}