{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9850141757796679,
  "eval_steps": 500,
  "global_step": 38,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.025921425678412314,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.802,
      "step": 1
    },
    {
      "epoch": 0.05184285135682463,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.8269,
      "step": 2
    },
    {
      "epoch": 0.07776427703523693,
      "learning_rate": 1e-05,
      "loss": 0.7809,
      "step": 3
    },
    {
      "epoch": 0.10368570271364926,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.7301,
      "step": 4
    },
    {
      "epoch": 0.12960712839206157,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.6587,
      "step": 5
    },
    {
      "epoch": 0.15552855407047386,
      "learning_rate": 2e-05,
      "loss": 0.696,
      "step": 6
    },
    {
      "epoch": 0.1814499797488862,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 0.6169,
      "step": 7
    },
    {
      "epoch": 0.2073714054272985,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 0.6169,
      "step": 8
    },
    {
      "epoch": 0.2332928311057108,
      "learning_rate": 3e-05,
      "loss": 0.6303,
      "step": 9
    },
    {
      "epoch": 0.25921425678412313,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.6913,
      "step": 10
    },
    {
      "epoch": 0.28513568246253546,
      "learning_rate": 3.6666666666666666e-05,
      "loss": 0.6918,
      "step": 11
    },
    {
      "epoch": 0.3110571081409477,
      "learning_rate": 4e-05,
      "loss": 0.6765,
      "step": 12
    },
    {
      "epoch": 0.33697853381936005,
      "learning_rate": 4.3333333333333334e-05,
      "loss": 0.6562,
      "step": 13
    },
    {
      "epoch": 0.3628999594977724,
      "learning_rate": 4.666666666666667e-05,
      "loss": 0.6849,
      "step": 14
    },
    {
      "epoch": 0.3888213851761847,
      "learning_rate": 5e-05,
      "loss": 0.7527,
      "step": 15
    },
    {
      "epoch": 0.414742810854597,
      "learning_rate": 4.782608695652174e-05,
      "loss": 0.8151,
      "step": 16
    },
    {
      "epoch": 0.4406642365330093,
      "learning_rate": 4.565217391304348e-05,
      "loss": 0.8005,
      "step": 17
    },
    {
      "epoch": 0.4665856622114216,
      "learning_rate": 4.347826086956522e-05,
      "loss": 0.8159,
      "step": 18
    },
    {
      "epoch": 0.49250708788983394,
      "learning_rate": 4.130434782608696e-05,
      "loss": 0.7787,
      "step": 19
    },
    {
      "epoch": 0.5184285135682463,
      "learning_rate": 3.91304347826087e-05,
      "loss": 0.6932,
      "step": 20
    },
    {
      "epoch": 0.5443499392466585,
      "learning_rate": 3.695652173913043e-05,
      "loss": 0.6447,
      "step": 21
    },
    {
      "epoch": 0.5702713649250709,
      "learning_rate": 3.478260869565218e-05,
      "loss": 0.6396,
      "step": 22
    },
    {
      "epoch": 0.5961927906034832,
      "learning_rate": 3.260869565217392e-05,
      "loss": 0.6011,
      "step": 23
    },
    {
      "epoch": 0.6221142162818954,
      "learning_rate": 3.0434782608695656e-05,
      "loss": 0.6038,
      "step": 24
    },
    {
      "epoch": 0.6480356419603078,
      "learning_rate": 2.826086956521739e-05,
      "loss": 0.5989,
      "step": 25
    },
    {
      "epoch": 0.6739570676387201,
      "learning_rate": 2.608695652173913e-05,
      "loss": 0.5854,
      "step": 26
    },
    {
      "epoch": 0.6998784933171325,
      "learning_rate": 2.391304347826087e-05,
      "loss": 0.5819,
      "step": 27
    },
    {
      "epoch": 0.7257999189955447,
      "learning_rate": 2.173913043478261e-05,
      "loss": 0.5735,
      "step": 28
    },
    {
      "epoch": 0.751721344673957,
      "learning_rate": 1.956521739130435e-05,
      "loss": 0.5977,
      "step": 29
    },
    {
      "epoch": 0.7776427703523694,
      "learning_rate": 1.739130434782609e-05,
      "loss": 0.5811,
      "step": 30
    },
    {
      "epoch": 0.8035641960307817,
      "learning_rate": 1.5217391304347828e-05,
      "loss": 0.59,
      "step": 31
    },
    {
      "epoch": 0.829485621709194,
      "learning_rate": 1.3043478260869566e-05,
      "loss": 0.5842,
      "step": 32
    },
    {
      "epoch": 0.8554070473876063,
      "learning_rate": 1.0869565217391305e-05,
      "loss": 0.5792,
      "step": 33
    },
    {
      "epoch": 0.8813284730660186,
      "learning_rate": 8.695652173913044e-06,
      "loss": 0.596,
      "step": 34
    },
    {
      "epoch": 0.907249898744431,
      "learning_rate": 6.521739130434783e-06,
      "loss": 0.5816,
      "step": 35
    },
    {
      "epoch": 0.9331713244228432,
      "learning_rate": 4.347826086956522e-06,
      "loss": 0.5835,
      "step": 36
    },
    {
      "epoch": 0.9590927501012556,
      "learning_rate": 2.173913043478261e-06,
      "loss": 0.5792,
      "step": 37
    },
    {
      "epoch": 0.9850141757796679,
      "learning_rate": 0.0,
      "loss": 0.5852,
      "step": 38
    },
    {
      "epoch": 0.9850141757796679,
      "step": 38,
      "total_flos": 9.55604026206978e+17,
      "train_loss": 0.6605736519161024,
      "train_runtime": 3366.0824,
      "train_samples_per_second": 5.867,
      "train_steps_per_second": 0.011
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 38,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.55604026206978e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}