{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.849557522123893,
  "eval_steps": 30,
  "global_step": 140,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.17699115044247787,
      "grad_norm": 5.151245594024658,
      "learning_rate": 4.989935734988098e-05,
      "loss": 4.7686,
      "num_input_tokens_seen": 239360,
      "step": 5
    },
    {
      "epoch": 0.35398230088495575,
      "grad_norm": 11.76759147644043,
      "learning_rate": 4.9491884960580894e-05,
      "loss": 3.5672,
      "num_input_tokens_seen": 478720,
      "step": 10
    },
    {
      "epoch": 0.5309734513274337,
      "grad_norm": 7.127159118652344,
      "learning_rate": 4.877641290737884e-05,
      "loss": 3.3447,
      "num_input_tokens_seen": 718080,
      "step": 15
    },
    {
      "epoch": 0.7079646017699115,
      "grad_norm": 11.316607475280762,
      "learning_rate": 4.7761938666470403e-05,
      "loss": 2.9905,
      "num_input_tokens_seen": 957440,
      "step": 20
    },
    {
      "epoch": 0.8849557522123894,
      "grad_norm": 8.864629745483398,
      "learning_rate": 4.6461219840046654e-05,
      "loss": 2.4303,
      "num_input_tokens_seen": 1196800,
      "step": 25
    },
    {
      "epoch": 1.0353982300884956,
      "grad_norm": 10.300582885742188,
      "learning_rate": 4.489061372204453e-05,
      "loss": 1.6583,
      "num_input_tokens_seen": 1400256,
      "step": 30
    },
    {
      "epoch": 1.0353982300884956,
      "eval_loss": 0.22562175989151,
      "eval_runtime": 112.57,
      "eval_samples_per_second": 1.004,
      "eval_steps_per_second": 0.506,
      "num_input_tokens_seen": 1400256,
      "step": 30
    },
    {
      "epoch": 1.2123893805309733,
      "grad_norm": 10.661843299865723,
      "learning_rate": 4.306987159568479e-05,
      "loss": 1.4066,
      "num_input_tokens_seen": 1639616,
      "step": 35
    },
    {
      "epoch": 1.3893805309734513,
      "grad_norm": 19.031333923339844,
      "learning_rate": 4.144846814849282e-05,
      "loss": 2.0231,
      "num_input_tokens_seen": 1878976,
      "step": 40
    },
    {
      "epoch": 1.5663716814159292,
      "grad_norm": 3.0498855113983154,
      "learning_rate": 3.92371123292113e-05,
      "loss": 1.3326,
      "num_input_tokens_seen": 2118336,
      "step": 45
    },
    {
      "epoch": 1.7433628318584071,
      "grad_norm": 10.98171615600586,
      "learning_rate": 3.7337705451608674e-05,
      "loss": 1.3365,
      "num_input_tokens_seen": 2357696,
      "step": 50
    },
    {
      "epoch": 1.920353982300885,
      "grad_norm": 8.286742210388184,
      "learning_rate": 3.4825625791348096e-05,
      "loss": 1.0757,
      "num_input_tokens_seen": 2597056,
      "step": 55
    },
    {
      "epoch": 2.0707964601769913,
      "grad_norm": 9.307785987854004,
      "learning_rate": 3.218998318580043e-05,
      "loss": 0.6975,
      "num_input_tokens_seen": 2800512,
      "step": 60
    },
    {
      "epoch": 2.0707964601769913,
      "eval_loss": 0.122890904545784,
      "eval_runtime": 112.5005,
      "eval_samples_per_second": 1.004,
      "eval_steps_per_second": 0.507,
      "num_input_tokens_seen": 2800512,
      "step": 60
    },
    {
      "epoch": 2.247787610619469,
      "grad_norm": 15.803374290466309,
      "learning_rate": 2.9463922369965917e-05,
      "loss": 0.823,
      "num_input_tokens_seen": 3039872,
      "step": 65
    },
    {
      "epoch": 2.4247787610619467,
      "grad_norm": 21.673105239868164,
      "learning_rate": 2.6681725140300997e-05,
      "loss": 1.2483,
      "num_input_tokens_seen": 3279232,
      "step": 70
    },
    {
      "epoch": 2.601769911504425,
      "grad_norm": 12.51755428314209,
      "learning_rate": 2.3878379241237136e-05,
      "loss": 1.2269,
      "num_input_tokens_seen": 3518592,
      "step": 75
    },
    {
      "epoch": 2.7787610619469025,
      "grad_norm": 12.325953483581543,
      "learning_rate": 2.1089138373994223e-05,
      "loss": 0.8036,
      "num_input_tokens_seen": 3757952,
      "step": 80
    },
    {
      "epoch": 2.9557522123893807,
      "grad_norm": 13.16337776184082,
      "learning_rate": 1.8349078860833123e-05,
      "loss": 0.994,
      "num_input_tokens_seen": 3997312,
      "step": 85
    },
    {
      "epoch": 3.106194690265487,
      "grad_norm": 12.360128402709961,
      "learning_rate": 1.5692658539951372e-05,
      "loss": 0.72,
      "num_input_tokens_seen": 4200768,
      "step": 90
    },
    {
      "epoch": 3.106194690265487,
      "eval_loss": 0.1203799694776535,
      "eval_runtime": 112.2274,
      "eval_samples_per_second": 1.007,
      "eval_steps_per_second": 0.508,
      "num_input_tokens_seen": 4200768,
      "step": 90
    },
    {
      "epoch": 3.2831858407079646,
      "grad_norm": 2.5878424644470215,
      "learning_rate": 1.3153283438175034e-05,
      "loss": 0.4563,
      "num_input_tokens_seen": 4440128,
      "step": 95
    },
    {
      "epoch": 3.4601769911504423,
      "grad_norm": 5.434853553771973,
      "learning_rate": 1.0762887670788702e-05,
      "loss": 0.7728,
      "num_input_tokens_seen": 4679488,
      "step": 100
    },
    {
      "epoch": 3.6371681415929205,
      "grad_norm": 28.99522590637207,
      "learning_rate": 8.551531851507186e-06,
      "loss": 0.799,
      "num_input_tokens_seen": 4918848,
      "step": 105
    },
    {
      "epoch": 3.814159292035398,
      "grad_norm": 8.98515510559082,
      "learning_rate": 6.547025062816486e-06,
      "loss": 0.5341,
      "num_input_tokens_seen": 5158208,
      "step": 110
    },
    {
      "epoch": 3.991150442477876,
      "grad_norm": 19.345624923706055,
      "learning_rate": 4.7745751406263165e-06,
      "loss": 0.7853,
      "num_input_tokens_seen": 5397568,
      "step": 115
    },
    {
      "epoch": 4.1415929203539825,
      "grad_norm": 12.641897201538086,
      "learning_rate": 3.2564716711076167e-06,
      "loss": 0.1667,
      "num_input_tokens_seen": 5601024,
      "step": 120
    },
    {
      "epoch": 4.1415929203539825,
      "eval_loss": 0.11977627128362656,
      "eval_runtime": 112.3249,
      "eval_samples_per_second": 1.006,
      "eval_steps_per_second": 0.507,
      "num_input_tokens_seen": 5601024,
      "step": 120
    },
    {
      "epoch": 4.31858407079646,
      "grad_norm": 27.25510597229004,
      "learning_rate": 2.0118056862137357e-06,
      "loss": 0.862,
      "num_input_tokens_seen": 5840384,
      "step": 125
    },
    {
      "epoch": 4.495575221238938,
      "grad_norm": 8.840839385986328,
      "learning_rate": 1.0562295828767387e-06,
      "loss": 0.6083,
      "num_input_tokens_seen": 6079744,
      "step": 130
    },
    {
      "epoch": 4.672566371681416,
      "grad_norm": 3.672297954559326,
      "learning_rate": 4.0176028503425835e-07,
      "loss": 0.3353,
      "num_input_tokens_seen": 6319104,
      "step": 135
    },
    {
      "epoch": 4.849557522123893,
      "grad_norm": 50.150081634521484,
      "learning_rate": 5.662812383859795e-08,
      "loss": 0.6499,
      "num_input_tokens_seen": 6558464,
      "step": 140
    },
    {
      "epoch": 4.849557522123893,
      "num_input_tokens_seen": 6558464,
      "step": 140,
      "total_flos": 2.735467646854103e+17,
      "train_loss": 1.3720276079007558,
      "train_runtime": 8129.8997,
      "train_samples_per_second": 0.278,
      "train_steps_per_second": 0.017
    }
  ],
  "logging_steps": 5,
  "max_steps": 140,
  "num_input_tokens_seen": 6558464,
  "num_train_epochs": 5,
  "save_steps": 30,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.735467646854103e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}