{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "grad_norm": 1.15625,
      "learning_rate": 1.0523107840665401e-05,
      "loss": 0.3756,
      "step": 5
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.70703125,
      "learning_rate": 2.367699264149715e-05,
      "loss": 0.3539,
      "step": 10
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.640625,
      "learning_rate": 3.68308774423289e-05,
      "loss": 0.3366,
      "step": 15
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.6171875,
      "learning_rate": 4.998476224316065e-05,
      "loss": 0.3259,
      "step": 20
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.63671875,
      "learning_rate": 6.31386470439924e-05,
      "loss": 0.3272,
      "step": 25
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.65625,
      "learning_rate": 7.629253184482416e-05,
      "loss": 0.3224,
      "step": 30
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.58203125,
      "learning_rate": 8.944641664565591e-05,
      "loss": 0.3081,
      "step": 35
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.57421875,
      "learning_rate": 9.203837857438074e-05,
      "loss": 0.3035,
      "step": 40
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.59375,
      "learning_rate": 9.188084206007837e-05,
      "loss": 0.3082,
      "step": 45
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.64453125,
      "learning_rate": 9.160271104997139e-05,
      "loss": 0.3045,
      "step": 50
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.609375,
      "learning_rate": 9.12049624893766e-05,
      "loss": 0.3016,
      "step": 55
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.64453125,
      "learning_rate": 9.068899348461955e-05,
      "loss": 0.2997,
      "step": 60
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.640625,
      "learning_rate": 9.005661639564749e-05,
      "loss": 0.2978,
      "step": 65
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.640625,
      "learning_rate": 8.931005247004914e-05,
      "loss": 0.2928,
      "step": 70
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.625,
      "learning_rate": 8.845192404084132e-05,
      "loss": 0.2901,
      "step": 75
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.5625,
      "learning_rate": 8.748524531542874e-05,
      "loss": 0.2881,
      "step": 80
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.5546875,
      "learning_rate": 8.641341178809052e-05,
      "loss": 0.2843,
      "step": 85
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.59765625,
      "learning_rate": 8.524018831318264e-05,
      "loss": 0.2838,
      "step": 90
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.58203125,
      "learning_rate": 8.396969588094976e-05,
      "loss": 0.2849,
      "step": 95
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.625,
      "learning_rate": 8.260639714239669e-05,
      "loss": 0.2801,
      "step": 100
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.29965952038764954,
      "eval_runtime": 2.9151,
      "eval_samples_per_second": 18.524,
      "eval_steps_per_second": 18.524,
      "step": 100
    },
    {
      "epoch": 1.05,
      "grad_norm": 0.69921875,
      "learning_rate": 8.115508073406396e-05,
      "loss": 0.2354,
      "step": 105
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.6796875,
      "learning_rate": 7.96208444577673e-05,
      "loss": 0.2383,
      "step": 110
    },
    {
      "epoch": 1.15,
      "grad_norm": 0.6171875,
      "learning_rate": 7.80090773743829e-05,
      "loss": 0.2338,
      "step": 115
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.58984375,
      "learning_rate": 7.632544087457448e-05,
      "loss": 0.2323,
      "step": 120
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.578125,
      "learning_rate": 7.457584879295211e-05,
      "loss": 0.2343,
      "step": 125
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.6640625,
      "learning_rate": 7.27664466355125e-05,
      "loss": 0.2385,
      "step": 130
    },
    {
      "epoch": 1.35,
      "grad_norm": 0.62890625,
      "learning_rate": 7.0903589993325e-05,
      "loss": 0.2312,
      "step": 135
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.609375,
      "learning_rate": 6.89938222182862e-05,
      "loss": 0.2326,
      "step": 140
    },
    {
      "epoch": 1.45,
      "grad_norm": 0.5859375,
      "learning_rate": 6.704385143935775e-05,
      "loss": 0.2358,
      "step": 145
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.53125,
      "learning_rate": 6.506052700001874e-05,
      "loss": 0.2329,
      "step": 150
    },
    {
      "epoch": 1.55,
      "grad_norm": 0.55859375,
      "learning_rate": 6.305081539969685e-05,
      "loss": 0.2325,
      "step": 155
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.52734375,
      "learning_rate": 6.1021775823685125e-05,
      "loss": 0.2297,
      "step": 160
    },
    {
      "epoch": 1.65,
      "grad_norm": 0.51953125,
      "learning_rate": 5.8980535347496145e-05,
      "loss": 0.2267,
      "step": 165
    },
    {
      "epoch": 1.7,
      "grad_norm": 0.53515625,
      "learning_rate": 5.6934263902749345e-05,
      "loss": 0.2311,
      "step": 170
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.5234375,
      "learning_rate": 5.4890149092524674e-05,
      "loss": 0.2266,
      "step": 175
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.53125,
      "learning_rate": 5.2855370944644685e-05,
      "loss": 0.2313,
      "step": 180
    },
    {
      "epoch": 1.85,
      "grad_norm": 0.53125,
      "learning_rate": 5.083707669156495e-05,
      "loss": 0.2275,
      "step": 185
    },
    {
      "epoch": 1.9,
      "grad_norm": 0.51171875,
      "learning_rate": 4.884235566545931e-05,
      "loss": 0.2273,
      "step": 190
    },
    {
      "epoch": 1.95,
      "grad_norm": 0.5,
      "learning_rate": 4.687821439668218e-05,
      "loss": 0.2248,
      "step": 195
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.51953125,
      "learning_rate": 4.4951552003075e-05,
      "loss": 0.225,
      "step": 200
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.2855764925479889,
      "eval_runtime": 2.8036,
      "eval_samples_per_second": 19.261,
      "eval_steps_per_second": 19.261,
      "step": 200
    }
  ],
  "logging_steps": 5,
  "max_steps": 300,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 1.51548994781184e+17,
  "train_batch_size": 140,
  "trial_name": null,
  "trial_params": null
}