{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.08615045315138357,
  "eval_steps": 10000,
  "global_step": 5000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004307522657569179,
      "grad_norm": 0.4925552308559418,
      "learning_rate": 2.4998864565799097e-05,
      "loss": 0.9861,
      "step": 250
    },
    {
      "epoch": 0.008615045315138358,
      "grad_norm": 0.9346778988838196,
      "learning_rate": 2.4995440213189432e-05,
      "loss": 0.8053,
      "step": 500
    },
    {
      "epoch": 0.012922567972707537,
      "grad_norm": 0.9080485701560974,
      "learning_rate": 2.498972755096465e-05,
      "loss": 0.778,
      "step": 750
    },
    {
      "epoch": 0.017230090630276716,
      "grad_norm": 0.8981316685676575,
      "learning_rate": 2.498172762529356e-05,
      "loss": 0.7423,
      "step": 1000
    },
    {
      "epoch": 0.021537613287845894,
      "grad_norm": 0.8113252520561218,
      "learning_rate": 2.4971441901215136e-05,
      "loss": 0.7344,
      "step": 1250
    },
    {
      "epoch": 0.025845135945415074,
      "grad_norm": 0.7558934688568115,
      "learning_rate": 2.4958872262370206e-05,
      "loss": 0.7288,
      "step": 1500
    },
    {
      "epoch": 0.03015265860298425,
      "grad_norm": 0.9201549887657166,
      "learning_rate": 2.4944021010656492e-05,
      "loss": 0.725,
      "step": 1750
    },
    {
      "epoch": 0.03446018126055343,
      "grad_norm": 0.7769947648048401,
      "learning_rate": 2.4926890865807073e-05,
      "loss": 0.7205,
      "step": 2000
    },
    {
      "epoch": 0.038767703918122606,
      "grad_norm": 0.9018628597259521,
      "learning_rate": 2.4907484964892315e-05,
      "loss": 0.7156,
      "step": 2250
    },
    {
      "epoch": 0.04307522657569179,
      "grad_norm": 0.8375287055969238,
      "learning_rate": 2.4885806861745365e-05,
      "loss": 0.7137,
      "step": 2500
    },
    {
      "epoch": 0.04738274923326097,
      "grad_norm": 0.9508460760116577,
      "learning_rate": 2.4861860526311346e-05,
      "loss": 0.7101,
      "step": 2750
    },
    {
      "epoch": 0.05169027189083015,
      "grad_norm": 0.8501839637756348,
      "learning_rate": 2.4835650343920313e-05,
      "loss": 0.7105,
      "step": 3000
    },
    {
      "epoch": 0.05599779454839932,
      "grad_norm": 0.9571662545204163,
      "learning_rate": 2.480718111448419e-05,
      "loss": 0.7056,
      "step": 3250
    },
    {
      "epoch": 0.0603053172059685,
      "grad_norm": 0.9728882312774658,
      "learning_rate": 2.4776458051617728e-05,
      "loss": 0.7051,
      "step": 3500
    },
    {
      "epoch": 0.06461283986353768,
      "grad_norm": 0.8361214995384216,
      "learning_rate": 2.4743486781683745e-05,
      "loss": 0.7076,
      "step": 3750
    },
    {
      "epoch": 0.06892036252110686,
      "grad_norm": 0.8233757615089417,
      "learning_rate": 2.4708273342762746e-05,
      "loss": 0.7011,
      "step": 4000
    },
    {
      "epoch": 0.07322788517867604,
      "grad_norm": 0.883545994758606,
      "learning_rate": 2.467082418354717e-05,
      "loss": 0.6976,
      "step": 4250
    },
    {
      "epoch": 0.07753540783624521,
      "grad_norm": 0.7400261759757996,
      "learning_rate": 2.463114616216044e-05,
      "loss": 0.6992,
      "step": 4500
    },
    {
      "epoch": 0.0818429304938144,
      "grad_norm": 0.8324729204177856,
      "learning_rate": 2.4589246544901002e-05,
      "loss": 0.6964,
      "step": 4750
    },
    {
      "epoch": 0.08615045315138357,
      "grad_norm": 0.7931947112083435,
      "learning_rate": 2.4545133004911653e-05,
      "loss": 0.697,
      "step": 5000
    }
  ],
  "logging_steps": 250,
  "max_steps": 58038,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.4740249835134976e+17,
  "train_batch_size": 10,
  "trial_name": null,
  "trial_params": null
}