{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07692307692307693,
      "grad_norm": 0.01362229132281847,
      "learning_rate": 2e-05,
      "loss": 0.214,
      "step": 1
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 0.015491360693982626,
      "learning_rate": 4e-05,
      "loss": 0.1883,
      "step": 2
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.013092231354423438,
      "learning_rate": 6.000000000000001e-05,
      "loss": 0.2559,
      "step": 3
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 0.011865468733559145,
      "learning_rate": 8e-05,
      "loss": 0.2318,
      "step": 4
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 0.01445707101996402,
      "learning_rate": 7.983897175980957e-05,
      "loss": 0.2356,
      "step": 5
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.022082670925174443,
      "learning_rate": 7.93571835439452e-05,
      "loss": 0.1849,
      "step": 6
    },
    {
      "epoch": 0.5384615384615384,
      "grad_norm": 0.016571143681459406,
      "learning_rate": 7.855851442783414e-05,
      "loss": 0.2368,
      "step": 7
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.013032821444579379,
      "learning_rate": 7.74493948255895e-05,
      "loss": 0.2375,
      "step": 8
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.00951504921068226,
      "learning_rate": 7.603875471609677e-05,
      "loss": 0.1866,
      "step": 9
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.013412897451087466,
      "learning_rate": 7.433795174407465e-05,
      "loss": 0.1767,
      "step": 10
    },
    {
      "epoch": 0.8461538461538461,
      "grad_norm": 0.015303084580261235,
      "learning_rate": 7.236067977499791e-05,
      "loss": 0.1619,
      "step": 11
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.02245685317077549,
      "learning_rate": 7.012285864014445e-05,
      "loss": 0.2166,
      "step": 12
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.020885068977789367,
      "learning_rate": 6.76425059594746e-05,
      "loss": 0.1882,
      "step": 13
    },
    {
      "epoch": 1.0769230769230769,
      "grad_norm": 0.013390527346974263,
      "learning_rate": 6.493959207434934e-05,
      "loss": 0.1718,
      "step": 14
    },
    {
      "epoch": 1.1538461538461537,
      "grad_norm": 0.008606296416287816,
      "learning_rate": 6.20358792580841e-05,
      "loss": 0.1861,
      "step": 15
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.007326851444871209,
      "learning_rate": 5.895474649891995e-05,
      "loss": 0.2026,
      "step": 16
    },
    {
      "epoch": 1.3076923076923077,
      "grad_norm": 0.007635686241940803,
      "learning_rate": 5.572100126615695e-05,
      "loss": 0.2013,
      "step": 17
    },
    {
      "epoch": 1.3846153846153846,
      "grad_norm": 0.008869623285318975,
      "learning_rate": 5.23606797749979e-05,
      "loss": 0.165,
      "step": 18
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 0.00788271564927161,
      "learning_rate": 4.890083735825258e-05,
      "loss": 0.1787,
      "step": 19
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 0.00870116469993209,
      "learning_rate": 4.5369330632706223e-05,
      "loss": 0.206,
      "step": 20
    },
    {
      "epoch": 1.6153846153846154,
      "grad_norm": 0.008346588642191923,
      "learning_rate": 4.17945932140206e-05,
      "loss": 0.1671,
      "step": 21
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 0.009658075777869769,
      "learning_rate": 3.820540678597942e-05,
      "loss": 0.1543,
      "step": 22
    },
    {
      "epoch": 1.7692307692307692,
      "grad_norm": 0.009152433347331993,
      "learning_rate": 3.4630669367293797e-05,
      "loss": 0.1792,
      "step": 23
    },
    {
      "epoch": 1.8461538461538463,
      "grad_norm": 0.007938383638920925,
      "learning_rate": 3.109916264174743e-05,
      "loss": 0.1727,
      "step": 24
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 0.01060506500300255,
      "learning_rate": 2.7639320225002108e-05,
      "loss": 0.1388,
      "step": 25
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.0086968658862576,
      "learning_rate": 2.427899873384306e-05,
      "loss": 0.1332,
      "step": 26
    },
    {
      "epoch": 2.076923076923077,
      "grad_norm": 0.007920756244716599,
      "learning_rate": 2.1045253501080058e-05,
      "loss": 0.1602,
      "step": 27
    },
    {
      "epoch": 2.1538461538461537,
      "grad_norm": 0.007030121363460224,
      "learning_rate": 1.7964120741915905e-05,
      "loss": 0.1589,
      "step": 28
    },
    {
      "epoch": 2.230769230769231,
      "grad_norm": 0.006685402907818994,
      "learning_rate": 1.5060407925650662e-05,
      "loss": 0.17,
      "step": 29
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 0.00769942388133665,
      "learning_rate": 1.2357494040525416e-05,
      "loss": 0.1375,
      "step": 30
    },
    {
      "epoch": 2.3846153846153846,
      "grad_norm": 0.0069255157912131325,
      "learning_rate": 9.877141359855567e-06,
      "loss": 0.151,
      "step": 31
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 0.007528440807236487,
      "learning_rate": 7.639320225002106e-06,
      "loss": 0.174,
      "step": 32
    },
    {
      "epoch": 2.5384615384615383,
      "grad_norm": 0.0068365831505659,
      "learning_rate": 5.662048255925357e-06,
      "loss": 0.1893,
      "step": 33
    },
    {
      "epoch": 2.6153846153846154,
      "grad_norm": 0.007259620939406601,
      "learning_rate": 3.961245283903239e-06,
      "loss": 0.1394,
      "step": 34
    },
    {
      "epoch": 2.6923076923076925,
      "grad_norm": 0.007387131018832008,
      "learning_rate": 2.550605174410512e-06,
      "loss": 0.171,
      "step": 35
    },
    {
      "epoch": 2.769230769230769,
      "grad_norm": 0.006999784513200382,
      "learning_rate": 1.4414855721658705e-06,
      "loss": 0.169,
      "step": 36
    },
    {
      "epoch": 2.8461538461538463,
      "grad_norm": 0.0070987738461534035,
      "learning_rate": 6.428164560548134e-07,
      "loss": 0.1483,
      "step": 37
    },
    {
      "epoch": 2.9230769230769234,
      "grad_norm": 0.007128694543877027,
      "learning_rate": 1.6102824019043728e-07,
      "loss": 0.1311,
      "step": 38
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.007308301272398886,
      "learning_rate": 0.0,
      "loss": 0.166,
      "step": 39
    },
    {
      "epoch": 3.0,
      "step": 39,
      "total_flos": 88512452100096.0,
      "train_loss": 0.18044410951626608,
      "train_runtime": 1311.1394,
      "train_samples_per_second": 0.458,
      "train_steps_per_second": 0.03
    }
  ],
  "logging_steps": 1,
  "max_steps": 39,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 88512452100096.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}