{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 25.0,
  "eval_steps": 20,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.125,
      "eval_loss": 2.5584230422973633,
      "eval_runtime": 4.8815,
      "eval_samples_per_second": 307.488,
      "eval_steps_per_second": 3.483,
      "step": 1
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.53125,
      "learning_rate": 0.0002,
      "loss": 2.3584,
      "step": 10
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.185546875,
      "learning_rate": 0.00019863613034027224,
      "loss": 2.2406,
      "step": 20
    },
    {
      "epoch": 2.5,
      "eval_loss": 2.1561896800994873,
      "eval_runtime": 4.8534,
      "eval_samples_per_second": 309.27,
      "eval_steps_per_second": 3.503,
      "step": 20
    },
    {
      "epoch": 3.75,
      "grad_norm": 0.162109375,
      "learning_rate": 0.00019458172417006347,
      "loss": 2.1785,
      "step": 30
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.1376953125,
      "learning_rate": 0.0001879473751206489,
      "loss": 2.136,
      "step": 40
    },
    {
      "epoch": 5.0,
      "eval_loss": 2.082921028137207,
      "eval_runtime": 4.8453,
      "eval_samples_per_second": 309.785,
      "eval_steps_per_second": 3.509,
      "step": 40
    },
    {
      "epoch": 6.25,
      "grad_norm": 0.138671875,
      "learning_rate": 0.00017891405093963938,
      "loss": 2.1125,
      "step": 50
    },
    {
      "epoch": 7.5,
      "grad_norm": 0.126953125,
      "learning_rate": 0.00016772815716257412,
      "loss": 2.0938,
      "step": 60
    },
    {
      "epoch": 7.5,
      "eval_loss": 2.0711307525634766,
      "eval_runtime": 5.3765,
      "eval_samples_per_second": 279.177,
      "eval_steps_per_second": 3.162,
      "step": 60
    },
    {
      "epoch": 8.75,
      "grad_norm": 0.138671875,
      "learning_rate": 0.00015469481581224272,
      "loss": 2.0638,
      "step": 70
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.140625,
      "learning_rate": 0.00014016954246529696,
      "loss": 2.0632,
      "step": 80
    },
    {
      "epoch": 10.0,
      "eval_loss": 2.067866325378418,
      "eval_runtime": 4.9082,
      "eval_samples_per_second": 305.813,
      "eval_steps_per_second": 3.464,
      "step": 80
    },
    {
      "epoch": 11.25,
      "grad_norm": 0.1337890625,
      "learning_rate": 0.00012454854871407994,
      "loss": 2.0551,
      "step": 90
    },
    {
      "epoch": 12.5,
      "grad_norm": 0.14453125,
      "learning_rate": 0.00010825793454723325,
      "loss": 2.0298,
      "step": 100
    },
    {
      "epoch": 12.5,
      "eval_loss": 2.0621085166931152,
      "eval_runtime": 5.0999,
      "eval_samples_per_second": 294.32,
      "eval_steps_per_second": 3.333,
      "step": 100
    },
    {
      "epoch": 13.75,
      "grad_norm": 0.1416015625,
      "learning_rate": 9.174206545276677e-05,
      "loss": 2.0272,
      "step": 110
    },
    {
      "epoch": 15.0,
      "grad_norm": 0.134765625,
      "learning_rate": 7.54514512859201e-05,
      "loss": 2.0168,
      "step": 120
    },
    {
      "epoch": 15.0,
      "eval_loss": 2.056727647781372,
      "eval_runtime": 5.1364,
      "eval_samples_per_second": 292.227,
      "eval_steps_per_second": 3.31,
      "step": 120
    },
    {
      "epoch": 16.25,
      "grad_norm": 0.130859375,
      "learning_rate": 5.983045753470308e-05,
      "loss": 2.0127,
      "step": 130
    },
    {
      "epoch": 17.5,
      "grad_norm": 0.1376953125,
      "learning_rate": 4.530518418775733e-05,
      "loss": 2.0188,
      "step": 140
    },
    {
      "epoch": 17.5,
      "eval_loss": 2.0686135292053223,
      "eval_runtime": 5.3391,
      "eval_samples_per_second": 281.135,
      "eval_steps_per_second": 3.184,
      "step": 140
    },
    {
      "epoch": 18.75,
      "grad_norm": 0.1337890625,
      "learning_rate": 3.227184283742591e-05,
      "loss": 2.009,
      "step": 150
    },
    {
      "epoch": 20.0,
      "grad_norm": 0.1357421875,
      "learning_rate": 2.1085949060360654e-05,
      "loss": 2.0108,
      "step": 160
    },
    {
      "epoch": 20.0,
      "eval_loss": 2.0700676441192627,
      "eval_runtime": 4.9064,
      "eval_samples_per_second": 305.926,
      "eval_steps_per_second": 3.465,
      "step": 160
    },
    {
      "epoch": 21.25,
      "grad_norm": 0.12890625,
      "learning_rate": 1.2052624879351104e-05,
      "loss": 2.0101,
      "step": 170
    },
    {
      "epoch": 22.5,
      "grad_norm": 0.1455078125,
      "learning_rate": 5.418275829936537e-06,
      "loss": 2.0169,
      "step": 180
    },
    {
      "epoch": 22.5,
      "eval_loss": 2.0683298110961914,
      "eval_runtime": 4.9925,
      "eval_samples_per_second": 300.65,
      "eval_steps_per_second": 3.405,
      "step": 180
    },
    {
      "epoch": 23.75,
      "grad_norm": 0.146484375,
      "learning_rate": 1.3638696597277679e-06,
      "loss": 2.0059,
      "step": 190
    },
    {
      "epoch": 25.0,
      "grad_norm": 0.1318359375,
      "learning_rate": 0.0,
      "loss": 2.0109,
      "step": 200
    },
    {
      "epoch": 25.0,
      "eval_loss": 2.0673062801361084,
      "eval_runtime": 4.8758,
      "eval_samples_per_second": 307.844,
      "eval_steps_per_second": 3.487,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 25,
  "save_steps": 20,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.113876738932736e+16,
  "train_batch_size": 23,
  "trial_name": null,
  "trial_params": null
}