{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.013036534889026497,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.518267444513249e-05,
      "eval_loss": 1.887902021408081,
      "eval_runtime": 333.4715,
      "eval_samples_per_second": 19.372,
      "eval_steps_per_second": 9.686,
      "step": 1
    },
    {
      "epoch": 0.0006518267444513248,
      "grad_norm": 0.9258672595024109,
      "learning_rate": 0.0002,
      "loss": 1.8293,
      "step": 10
    },
    {
      "epoch": 0.0013036534889026496,
      "grad_norm": 0.7830431461334229,
      "learning_rate": 0.0002,
      "loss": 1.7838,
      "step": 20
    },
    {
      "epoch": 0.0019554802333539745,
      "grad_norm": 0.9389762282371521,
      "learning_rate": 0.0002,
      "loss": 1.7733,
      "step": 30
    },
    {
      "epoch": 0.002607306977805299,
      "grad_norm": 0.9967517852783203,
      "learning_rate": 0.0002,
      "loss": 1.7201,
      "step": 40
    },
    {
      "epoch": 0.0032591337222566243,
      "grad_norm": 0.8355724215507507,
      "learning_rate": 0.0002,
      "loss": 1.5985,
      "step": 50
    },
    {
      "epoch": 0.0032591337222566243,
      "eval_loss": 1.7376784086227417,
      "eval_runtime": 333.6711,
      "eval_samples_per_second": 19.36,
      "eval_steps_per_second": 9.68,
      "step": 50
    },
    {
      "epoch": 0.003910960466707949,
      "grad_norm": 0.9053980708122253,
      "learning_rate": 0.0002,
      "loss": 1.7509,
      "step": 60
    },
    {
      "epoch": 0.004562787211159274,
      "grad_norm": 1.0709302425384521,
      "learning_rate": 0.0002,
      "loss": 1.7415,
      "step": 70
    },
    {
      "epoch": 0.005214613955610598,
      "grad_norm": 0.8847922682762146,
      "learning_rate": 0.0002,
      "loss": 1.8675,
      "step": 80
    },
    {
      "epoch": 0.005866440700061924,
      "grad_norm": 0.8659989237785339,
      "learning_rate": 0.0002,
      "loss": 1.7278,
      "step": 90
    },
    {
      "epoch": 0.006518267444513249,
      "grad_norm": 1.0513916015625,
      "learning_rate": 0.0002,
      "loss": 1.787,
      "step": 100
    },
    {
      "epoch": 0.006518267444513249,
      "eval_loss": 1.726641058921814,
      "eval_runtime": 333.7788,
      "eval_samples_per_second": 19.354,
      "eval_steps_per_second": 9.677,
      "step": 100
    },
    {
      "epoch": 0.007170094188964573,
      "grad_norm": 0.9510365128517151,
      "learning_rate": 0.0002,
      "loss": 1.6355,
      "step": 110
    },
    {
      "epoch": 0.007821920933415898,
      "grad_norm": 0.7684184312820435,
      "learning_rate": 0.0002,
      "loss": 1.6816,
      "step": 120
    },
    {
      "epoch": 0.008473747677867223,
      "grad_norm": 0.7511278390884399,
      "learning_rate": 0.0002,
      "loss": 1.7392,
      "step": 130
    },
    {
      "epoch": 0.009125574422318547,
      "grad_norm": 1.2092989683151245,
      "learning_rate": 0.0002,
      "loss": 1.5957,
      "step": 140
    },
    {
      "epoch": 0.009777401166769872,
      "grad_norm": 0.7998082041740417,
      "learning_rate": 0.0002,
      "loss": 1.5553,
      "step": 150
    },
    {
      "epoch": 0.009777401166769872,
      "eval_loss": 1.726781964302063,
      "eval_runtime": 333.6825,
      "eval_samples_per_second": 19.36,
      "eval_steps_per_second": 9.68,
      "step": 150
    },
    {
      "epoch": 0.010429227911221197,
      "grad_norm": 1.0430855751037598,
      "learning_rate": 0.0002,
      "loss": 1.7549,
      "step": 160
    },
    {
      "epoch": 0.011081054655672521,
      "grad_norm": 1.1361061334609985,
      "learning_rate": 0.0002,
      "loss": 1.6927,
      "step": 170
    },
    {
      "epoch": 0.011732881400123848,
      "grad_norm": 0.9144191741943359,
      "learning_rate": 0.0002,
      "loss": 1.7662,
      "step": 180
    },
    {
      "epoch": 0.012384708144575172,
      "grad_norm": 0.8297296762466431,
      "learning_rate": 0.0002,
      "loss": 1.7277,
      "step": 190
    },
    {
      "epoch": 0.013036534889026497,
      "grad_norm": 1.0495644807815552,
      "learning_rate": 0.0002,
      "loss": 1.7698,
      "step": 200
    },
    {
      "epoch": 0.013036534889026497,
      "eval_loss": 1.7259982824325562,
      "eval_runtime": 333.5702,
      "eval_samples_per_second": 19.366,
      "eval_steps_per_second": 9.683,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.386991357034496e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}