{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.8363636363636364,
  "eval_steps": 500,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 1e-05,
      "loss": 2.669,
      "step": 1
    },
    {
      "epoch": 0.15,
      "learning_rate": 2e-05,
      "loss": 2.6355,
      "step": 2
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.9963974885425267e-05,
      "loss": 1.5978,
      "step": 3
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.9856159103477085e-05,
      "loss": 1.1824,
      "step": 4
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.967732946933499e-05,
      "loss": 1.1361,
      "step": 5
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.9428774454610845e-05,
      "loss": 0.9867,
      "step": 6
    },
    {
      "epoch": 0.51,
      "learning_rate": 1.911228490388136e-05,
      "loss": 0.9334,
      "step": 7
    },
    {
      "epoch": 0.58,
      "learning_rate": 1.8730141131611882e-05,
      "loss": 0.8648,
      "step": 8
    },
    {
      "epoch": 0.65,
      "learning_rate": 1.8285096492438424e-05,
      "loss": 0.8256,
      "step": 9
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.7780357543184396e-05,
      "loss": 0.8355,
      "step": 10
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.7219560939545246e-05,
      "loss": 0.8219,
      "step": 11
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.6606747233900816e-05,
      "loss": 0.7471,
      "step": 12
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.594633176304287e-05,
      "loss": 0.7533,
      "step": 13
    },
    {
      "epoch": 1.02,
      "learning_rate": 1.5243072835572319e-05,
      "loss": 0.7302,
      "step": 14
    },
    {
      "epoch": 1.09,
      "learning_rate": 1.4502037448176734e-05,
      "loss": 0.6829,
      "step": 15
    },
    {
      "epoch": 1.16,
      "learning_rate": 1.3728564777803089e-05,
      "loss": 0.6685,
      "step": 16
    },
    {
      "epoch": 1.24,
      "learning_rate": 1.2928227712765504e-05,
      "loss": 0.624,
      "step": 17
    },
    {
      "epoch": 1.31,
      "learning_rate": 1.2106792699957264e-05,
      "loss": 0.631,
      "step": 18
    },
    {
      "epoch": 1.38,
      "learning_rate": 1.1270178197468788e-05,
      "loss": 0.6069,
      "step": 19
    },
    {
      "epoch": 1.45,
      "learning_rate": 1.0424412031961485e-05,
      "loss": 0.5985,
      "step": 20
    },
    {
      "epoch": 1.53,
      "learning_rate": 9.57558796803852e-06,
      "loss": 0.5978,
      "step": 21
    },
    {
      "epoch": 1.6,
      "learning_rate": 8.729821802531213e-06,
      "loss": 0.5939,
      "step": 22
    },
    {
      "epoch": 1.67,
      "learning_rate": 7.89320730004274e-06,
      "loss": 0.5707,
      "step": 23
    },
    {
      "epoch": 1.75,
      "learning_rate": 7.071772287234497e-06,
      "loss": 0.5802,
      "step": 24
    },
    {
      "epoch": 1.82,
      "learning_rate": 6.2714352221969155e-06,
      "loss": 0.5831,
      "step": 25
    },
    {
      "epoch": 1.89,
      "learning_rate": 5.497962551823266e-06,
      "loss": 0.5776,
      "step": 26
    },
    {
      "epoch": 1.96,
      "learning_rate": 4.756927164427685e-06,
      "loss": 0.5565,
      "step": 27
    },
    {
      "epoch": 2.04,
      "learning_rate": 4.053668236957135e-06,
      "loss": 0.525,
      "step": 28
    },
    {
      "epoch": 2.11,
      "learning_rate": 3.3932527660991877e-06,
      "loss": 0.5286,
      "step": 29
    },
    {
      "epoch": 2.18,
      "learning_rate": 2.780439060454756e-06,
      "loss": 0.5217,
      "step": 30
    },
    {
      "epoch": 2.25,
      "learning_rate": 2.2196424568156073e-06,
      "loss": 0.5327,
      "step": 31
    },
    {
      "epoch": 2.33,
      "learning_rate": 1.7149035075615795e-06,
      "loss": 0.5034,
      "step": 32
    },
    {
      "epoch": 2.4,
      "learning_rate": 1.2698588683881185e-06,
      "loss": 0.5166,
      "step": 33
    },
    {
      "epoch": 2.47,
      "learning_rate": 8.87715096118642e-07,
      "loss": 0.519,
      "step": 34
    },
    {
      "epoch": 2.55,
      "learning_rate": 5.71225545389158e-07,
      "loss": 0.5159,
      "step": 35
    },
    {
      "epoch": 2.62,
      "learning_rate": 3.226705306650113e-07,
      "loss": 0.5046,
      "step": 36
    },
    {
      "epoch": 2.69,
      "learning_rate": 1.4384089652291544e-07,
      "loss": 0.535,
      "step": 37
    },
    {
      "epoch": 2.76,
      "learning_rate": 3.602511457473479e-08,
      "loss": 0.5082,
      "step": 38
    },
    {
      "epoch": 2.84,
      "learning_rate": 0.0,
      "loss": 0.5269,
      "step": 39
    },
    {
      "epoch": 2.84,
      "step": 39,
      "total_flos": 63342876557312.0,
      "train_loss": 0.7904764398550376,
      "train_runtime": 1995.6522,
      "train_samples_per_second": 2.637,
      "train_steps_per_second": 0.02
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 39,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "total_flos": 63342876557312.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}