{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 11.0,
  "eval_steps": 500,
  "global_step": 1485,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 9.024576187133789,
      "learning_rate": 4.758024691358025e-05,
      "loss": 5.6879,
      "step": 100
    },
    {
      "epoch": 1.0,
      "eval_loss": 3.6306915283203125,
      "eval_runtime": 51.3095,
      "eval_samples_per_second": 4.366,
      "eval_steps_per_second": 1.091,
      "step": 135
    },
    {
      "epoch": 1.4814814814814814,
      "grad_norm": 5.388796329498291,
      "learning_rate": 4.511111111111112e-05,
      "loss": 3.394,
      "step": 200
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.354670286178589,
      "eval_runtime": 55.5839,
      "eval_samples_per_second": 4.03,
      "eval_steps_per_second": 1.007,
      "step": 270
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 2.522367477416992,
      "learning_rate": 4.264197530864198e-05,
      "loss": 2.2705,
      "step": 300
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 2.4746665954589844,
      "learning_rate": 4.0172839506172845e-05,
      "loss": 1.9791,
      "step": 400
    },
    {
      "epoch": 3.0,
      "eval_loss": 2.1306421756744385,
      "eval_runtime": 52.1249,
      "eval_samples_per_second": 4.297,
      "eval_steps_per_second": 1.074,
      "step": 405
    },
    {
      "epoch": 3.7037037037037037,
      "grad_norm": 2.1820168495178223,
      "learning_rate": 3.770370370370371e-05,
      "loss": 1.769,
      "step": 500
    },
    {
      "epoch": 4.0,
      "eval_loss": 2.044142961502075,
      "eval_runtime": 53.0307,
      "eval_samples_per_second": 4.224,
      "eval_steps_per_second": 1.056,
      "step": 540
    },
    {
      "epoch": 4.444444444444445,
      "grad_norm": 2.130756139755249,
      "learning_rate": 3.523456790123457e-05,
      "loss": 1.6324,
      "step": 600
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.9857765436172485,
      "eval_runtime": 9.8322,
      "eval_samples_per_second": 22.782,
      "eval_steps_per_second": 5.696,
      "step": 675
    },
    {
      "epoch": 5.185185185185185,
      "grad_norm": 2.337979555130005,
      "learning_rate": 3.2765432098765435e-05,
      "loss": 1.57,
      "step": 700
    },
    {
      "epoch": 5.925925925925926,
      "grad_norm": 2.2854785919189453,
      "learning_rate": 3.02962962962963e-05,
      "loss": 1.5001,
      "step": 800
    },
    {
      "epoch": 6.0,
      "eval_loss": 1.9689041376113892,
      "eval_runtime": 22.8388,
      "eval_samples_per_second": 9.808,
      "eval_steps_per_second": 2.452,
      "step": 810
    },
    {
      "epoch": 6.666666666666667,
      "grad_norm": 2.746314525604248,
      "learning_rate": 2.7827160493827158e-05,
      "loss": 1.3906,
      "step": 900
    },
    {
      "epoch": 7.0,
      "eval_loss": 1.9692579507827759,
      "eval_runtime": 28.0368,
      "eval_samples_per_second": 7.989,
      "eval_steps_per_second": 1.997,
      "step": 945
    },
    {
      "epoch": 7.407407407407407,
      "grad_norm": 2.559098720550537,
      "learning_rate": 2.5358024691358025e-05,
      "loss": 1.299,
      "step": 1000
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.9595974683761597,
      "eval_runtime": 11.2298,
      "eval_samples_per_second": 19.947,
      "eval_steps_per_second": 4.987,
      "step": 1080
    },
    {
      "epoch": 8.148148148148149,
      "grad_norm": 2.383742094039917,
      "learning_rate": 2.288888888888889e-05,
      "loss": 1.2395,
      "step": 1100
    },
    {
      "epoch": 8.88888888888889,
      "grad_norm": 2.732578754425049,
      "learning_rate": 2.0419753086419755e-05,
      "loss": 1.1885,
      "step": 1200
    },
    {
      "epoch": 9.0,
      "eval_loss": 1.972147822380066,
      "eval_runtime": 35.0043,
      "eval_samples_per_second": 6.399,
      "eval_steps_per_second": 1.6,
      "step": 1215
    },
    {
      "epoch": 9.62962962962963,
      "grad_norm": 2.3015191555023193,
      "learning_rate": 1.7950617283950618e-05,
      "loss": 1.0952,
      "step": 1300
    },
    {
      "epoch": 10.0,
      "eval_loss": 1.9826620817184448,
      "eval_runtime": 28.3051,
      "eval_samples_per_second": 7.914,
      "eval_steps_per_second": 1.978,
      "step": 1350
    },
    {
      "epoch": 10.37037037037037,
      "grad_norm": 2.642057180404663,
      "learning_rate": 1.548148148148148e-05,
      "loss": 1.0285,
      "step": 1400
    },
    {
      "epoch": 11.0,
      "eval_loss": 1.9937878847122192,
      "eval_runtime": 11.3644,
      "eval_samples_per_second": 19.711,
      "eval_steps_per_second": 4.928,
      "step": 1485
    }
  ],
  "logging_steps": 100,
  "max_steps": 2025,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 15,
  "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": 2.1628187800547328e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}