{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3827751196172249,
  "eval_steps": 200,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.019138755980861243,
      "grad_norm": 0.6331622004508972,
      "learning_rate": 6.25e-05,
      "loss": 1.2934,
      "step": 25
    },
    {
      "epoch": 0.03827751196172249,
      "grad_norm": 0.4265715181827545,
      "learning_rate": 9.921011058451817e-05,
      "loss": 0.646,
      "step": 50
    },
    {
      "epoch": 0.05741626794258373,
      "grad_norm": 0.058480992913246155,
      "learning_rate": 9.723538704581358e-05,
      "loss": 0.526,
      "step": 75
    },
    {
      "epoch": 0.07655502392344497,
      "grad_norm": 0.03429209440946579,
      "learning_rate": 9.5260663507109e-05,
      "loss": 0.5069,
      "step": 100
    },
    {
      "epoch": 0.09569377990430622,
      "grad_norm": 0.11788608133792877,
      "learning_rate": 9.328593996840442e-05,
      "loss": 0.4748,
      "step": 125
    },
    {
      "epoch": 0.11483253588516747,
      "grad_norm": 0.06252221018075943,
      "learning_rate": 9.131121642969984e-05,
      "loss": 0.4838,
      "step": 150
    },
    {
      "epoch": 0.1339712918660287,
      "grad_norm": 0.020096125081181526,
      "learning_rate": 8.933649289099526e-05,
      "loss": 0.4918,
      "step": 175
    },
    {
      "epoch": 0.15311004784688995,
      "grad_norm": 0.12325792759656906,
      "learning_rate": 8.736176935229068e-05,
      "loss": 0.5104,
      "step": 200
    },
    {
      "epoch": 0.15311004784688995,
      "eval_loss": 0.49960193037986755,
      "eval_runtime": 113.968,
      "eval_samples_per_second": 4.826,
      "eval_steps_per_second": 0.605,
      "step": 200
    },
    {
      "epoch": 0.1722488038277512,
      "grad_norm": 0.10687647014856339,
      "learning_rate": 8.53870458135861e-05,
      "loss": 0.5015,
      "step": 225
    },
    {
      "epoch": 0.19138755980861244,
      "grad_norm": 0.08051887899637222,
      "learning_rate": 8.341232227488151e-05,
      "loss": 0.4976,
      "step": 250
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 0.03358834236860275,
      "learning_rate": 8.143759873617693e-05,
      "loss": 0.4916,
      "step": 275
    },
    {
      "epoch": 0.22966507177033493,
      "grad_norm": 0.0065140132792294025,
      "learning_rate": 7.946287519747235e-05,
      "loss": 0.489,
      "step": 300
    },
    {
      "epoch": 0.24880382775119617,
      "grad_norm": 0.06022901087999344,
      "learning_rate": 7.748815165876777e-05,
      "loss": 0.5067,
      "step": 325
    },
    {
      "epoch": 0.2679425837320574,
      "grad_norm": 0.10035768896341324,
      "learning_rate": 7.551342812006318e-05,
      "loss": 0.4672,
      "step": 350
    },
    {
      "epoch": 0.28708133971291866,
      "grad_norm": 0.12114957720041275,
      "learning_rate": 7.35387045813586e-05,
      "loss": 0.4941,
      "step": 375
    },
    {
      "epoch": 0.3062200956937799,
      "grad_norm": 0.008501251228153706,
      "learning_rate": 7.156398104265402e-05,
      "loss": 0.5059,
      "step": 400
    },
    {
      "epoch": 0.3062200956937799,
      "eval_loss": 0.49782803654670715,
      "eval_runtime": 112.8287,
      "eval_samples_per_second": 4.875,
      "eval_steps_per_second": 0.612,
      "step": 400
    },
    {
      "epoch": 0.3253588516746411,
      "grad_norm": 0.13349683582782745,
      "learning_rate": 6.958925750394945e-05,
      "loss": 0.4999,
      "step": 425
    },
    {
      "epoch": 0.3444976076555024,
      "grad_norm": 0.07800962775945663,
      "learning_rate": 6.761453396524487e-05,
      "loss": 0.5059,
      "step": 450
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.08217480778694153,
      "learning_rate": 6.563981042654029e-05,
      "loss": 0.5114,
      "step": 475
    },
    {
      "epoch": 0.3827751196172249,
      "grad_norm": 0.07217281311750412,
      "learning_rate": 6.36650868878357e-05,
      "loss": 0.4855,
      "step": 500
    }
  ],
  "logging_steps": 25,
  "max_steps": 1306,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 1.7646732515386368e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}