{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.06252014179826,
  "eval_steps": 100,
  "global_step": 800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.12890750886239125,
      "grad_norm": 5.428058115945689,
      "learning_rate": 0.0001,
      "loss": 3.7217,
      "step": 50
    },
    {
      "epoch": 0.2578150177247825,
      "grad_norm": 3.6736343068699004,
      "learning_rate": 9.999743504733682e-05,
      "loss": 2.6957,
      "step": 100
    },
    {
      "epoch": 0.2578150177247825,
      "eval_loss": 2.472891092300415,
      "eval_runtime": 13.3767,
      "eval_samples_per_second": 74.757,
      "eval_steps_per_second": 2.392,
      "step": 100
    },
    {
      "epoch": 0.3867225265871737,
      "grad_norm": 3.9566460988411976,
      "learning_rate": 9.998974045516476e-05,
      "loss": 2.3982,
      "step": 150
    },
    {
      "epoch": 0.515630035449565,
      "grad_norm": 1.91000275173515,
      "learning_rate": 9.997691702090861e-05,
      "loss": 2.188,
      "step": 200
    },
    {
      "epoch": 0.515630035449565,
      "eval_loss": 2.072312593460083,
      "eval_runtime": 13.1385,
      "eval_samples_per_second": 76.112,
      "eval_steps_per_second": 2.436,
      "step": 200
    },
    {
      "epoch": 0.6445375443119562,
      "grad_norm": 3.7326458687273494,
      "learning_rate": 9.9958966073518e-05,
      "loss": 2.058,
      "step": 250
    },
    {
      "epoch": 0.7734450531743474,
      "grad_norm": 1.1877292780347308,
      "learning_rate": 9.993588947332947e-05,
      "loss": 2.0499,
      "step": 300
    },
    {
      "epoch": 0.7734450531743474,
      "eval_loss": 1.9889113903045654,
      "eval_runtime": 13.0859,
      "eval_samples_per_second": 76.418,
      "eval_steps_per_second": 2.445,
      "step": 300
    },
    {
      "epoch": 0.9023525620367386,
      "grad_norm": 2.896903582467451,
      "learning_rate": 9.990768961187381e-05,
      "loss": 1.9975,
      "step": 350
    },
    {
      "epoch": 1.03126007089913,
      "grad_norm": 1.1169559646807505,
      "learning_rate": 9.98743694116282e-05,
      "loss": 1.9593,
      "step": 400
    },
    {
      "epoch": 1.03126007089913,
      "eval_loss": 1.9284899234771729,
      "eval_runtime": 13.1076,
      "eval_samples_per_second": 76.292,
      "eval_steps_per_second": 2.441,
      "step": 400
    },
    {
      "epoch": 1.1601675797615212,
      "grad_norm": 0.9849310297267434,
      "learning_rate": 9.983593232571328e-05,
      "loss": 1.9186,
      "step": 450
    },
    {
      "epoch": 1.2890750886239124,
      "grad_norm": 0.9560509903560709,
      "learning_rate": 9.979238233753537e-05,
      "loss": 1.921,
      "step": 500
    },
    {
      "epoch": 1.2890750886239124,
      "eval_loss": 1.899874210357666,
      "eval_runtime": 13.1392,
      "eval_samples_per_second": 76.108,
      "eval_steps_per_second": 2.435,
      "step": 500
    },
    {
      "epoch": 1.4179825974863036,
      "grad_norm": 1.3741796182310861,
      "learning_rate": 9.974372396037357e-05,
      "loss": 1.9246,
      "step": 550
    },
    {
      "epoch": 1.5468901063486948,
      "grad_norm": 1.718108772048462,
      "learning_rate": 9.96899622369121e-05,
      "loss": 1.8882,
      "step": 600
    },
    {
      "epoch": 1.5468901063486948,
      "eval_loss": 1.8836181163787842,
      "eval_runtime": 13.1533,
      "eval_samples_per_second": 76.026,
      "eval_steps_per_second": 2.433,
      "step": 600
    },
    {
      "epoch": 1.675797615211086,
      "grad_norm": 1.3793562879868584,
      "learning_rate": 9.963110273871768e-05,
      "loss": 1.8823,
      "step": 650
    },
    {
      "epoch": 1.8047051240734773,
      "grad_norm": 1.7941360700066475,
      "learning_rate": 9.956715156566203e-05,
      "loss": 1.8786,
      "step": 700
    },
    {
      "epoch": 1.8047051240734773,
      "eval_loss": 1.874005913734436,
      "eval_runtime": 13.1279,
      "eval_samples_per_second": 76.174,
      "eval_steps_per_second": 2.438,
      "step": 700
    },
    {
      "epoch": 1.9336126329358685,
      "grad_norm": 1.2268118375629977,
      "learning_rate": 9.94981153452899e-05,
      "loss": 1.8764,
      "step": 750
    },
    {
      "epoch": 2.06252014179826,
      "grad_norm": 0.8694323872512157,
      "learning_rate": 9.94240012321321e-05,
      "loss": 1.8327,
      "step": 800
    },
    {
      "epoch": 2.06252014179826,
      "eval_loss": 1.8573421239852905,
      "eval_runtime": 13.1123,
      "eval_samples_per_second": 76.264,
      "eval_steps_per_second": 2.44,
      "step": 800
    }
  ],
  "logging_steps": 50,
  "max_steps": 15480,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 40,
  "save_steps": 800,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 711303530283008.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}