{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.46403712296983757,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02320185614849188,
      "grad_norm": 27.06661296487487,
      "learning_rate": 5e-07,
      "loss": 1.6534,
      "step": 5
    },
    {
      "epoch": 0.04640371229698376,
      "grad_norm": 14.570294011958959,
      "learning_rate": 1e-06,
      "loss": 1.5286,
      "step": 10
    },
    {
      "epoch": 0.06960556844547564,
      "grad_norm": 7.608713229824519,
      "learning_rate": 9.998470286265414e-07,
      "loss": 1.2854,
      "step": 15
    },
    {
      "epoch": 0.09280742459396751,
      "grad_norm": 6.212274190189952,
      "learning_rate": 9.993882081071305e-07,
      "loss": 1.2312,
      "step": 20
    },
    {
      "epoch": 0.11600928074245939,
      "grad_norm": 5.767015997797787,
      "learning_rate": 9.986238191873872e-07,
      "loss": 1.1896,
      "step": 25
    },
    {
      "epoch": 0.13921113689095127,
      "grad_norm": 5.073635902534103,
      "learning_rate": 9.975543295858033e-07,
      "loss": 1.1918,
      "step": 30
    },
    {
      "epoch": 0.16241299303944315,
      "grad_norm": 4.788195681953361,
      "learning_rate": 9.961803937075514e-07,
      "loss": 1.1547,
      "step": 35
    },
    {
      "epoch": 0.18561484918793503,
      "grad_norm": 4.642283394950232,
      "learning_rate": 9.945028522440653e-07,
      "loss": 1.1326,
      "step": 40
    },
    {
      "epoch": 0.2088167053364269,
      "grad_norm": 4.915483171626106,
      "learning_rate": 9.925227316586314e-07,
      "loss": 1.1409,
      "step": 45
    },
    {
      "epoch": 0.23201856148491878,
      "grad_norm": 4.785752094079727,
      "learning_rate": 9.902412435583125e-07,
      "loss": 1.1348,
      "step": 50
    },
    {
      "epoch": 0.23201856148491878,
      "eval_loss": 1.1267675161361694,
      "eval_runtime": 105.5696,
      "eval_samples_per_second": 58.056,
      "eval_steps_per_second": 0.909,
      "step": 50
    },
    {
      "epoch": 0.2552204176334107,
      "grad_norm": 4.914635335083288,
      "learning_rate": 9.876597839525813e-07,
      "loss": 1.1167,
      "step": 55
    },
    {
      "epoch": 0.27842227378190254,
      "grad_norm": 4.9477576848370095,
      "learning_rate": 9.847799323991233e-07,
      "loss": 1.1059,
      "step": 60
    },
    {
      "epoch": 0.30162412993039445,
      "grad_norm": 4.9360133375019295,
      "learning_rate": 9.816034510373285e-07,
      "loss": 1.1173,
      "step": 65
    },
    {
      "epoch": 0.3248259860788863,
      "grad_norm": 4.7405884580433675,
      "learning_rate": 9.781322835100637e-07,
      "loss": 1.1091,
      "step": 70
    },
    {
      "epoch": 0.3480278422273782,
      "grad_norm": 4.835669121473599,
      "learning_rate": 9.743685537743856e-07,
      "loss": 1.0967,
      "step": 75
    },
    {
      "epoch": 0.37122969837587005,
      "grad_norm": 4.6796771647856055,
      "learning_rate": 9.70314564801922e-07,
      "loss": 1.0758,
      "step": 80
    },
    {
      "epoch": 0.39443155452436196,
      "grad_norm": 4.984167856345103,
      "learning_rate": 9.659727971697173e-07,
      "loss": 1.0862,
      "step": 85
    },
    {
      "epoch": 0.4176334106728538,
      "grad_norm": 4.771046487158264,
      "learning_rate": 9.613459075424033e-07,
      "loss": 1.0795,
      "step": 90
    },
    {
      "epoch": 0.4408352668213457,
      "grad_norm": 4.605260375673115,
      "learning_rate": 9.564367270466245e-07,
      "loss": 1.0677,
      "step": 95
    },
    {
      "epoch": 0.46403712296983757,
      "grad_norm": 4.698279384122072,
      "learning_rate": 9.51248259538713e-07,
      "loss": 1.08,
      "step": 100
    },
    {
      "epoch": 0.46403712296983757,
      "eval_loss": 1.0813250541687012,
      "eval_runtime": 104.9985,
      "eval_samples_per_second": 58.372,
      "eval_steps_per_second": 0.914,
      "step": 100
    }
  ],
  "logging_steps": 5,
  "max_steps": 645,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 589411381149696.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}