{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.001069741817812271,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.139483635624542e-05,
      "eval_loss": 3.457625389099121,
      "eval_runtime": 1325.3882,
      "eval_samples_per_second": 14.849,
      "eval_steps_per_second": 7.425,
      "step": 1
    },
    {
      "epoch": 0.0001069741817812271,
      "grad_norm": 4.435446739196777,
      "learning_rate": 5e-05,
      "loss": 3.3958,
      "step": 5
    },
    {
      "epoch": 0.0002139483635624542,
      "grad_norm": 4.249910354614258,
      "learning_rate": 0.0001,
      "loss": 2.7027,
      "step": 10
    },
    {
      "epoch": 0.0002139483635624542,
      "eval_loss": 1.6180306673049927,
      "eval_runtime": 1327.1519,
      "eval_samples_per_second": 14.83,
      "eval_steps_per_second": 7.415,
      "step": 10
    },
    {
      "epoch": 0.0003209225453436813,
      "grad_norm": 4.166057586669922,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.0518,
      "step": 15
    },
    {
      "epoch": 0.0004278967271249084,
      "grad_norm": 5.492222785949707,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.2079,
      "step": 20
    },
    {
      "epoch": 0.0004278967271249084,
      "eval_loss": 0.10403858125209808,
      "eval_runtime": 1327.1095,
      "eval_samples_per_second": 14.83,
      "eval_steps_per_second": 7.415,
      "step": 20
    },
    {
      "epoch": 0.0005348709089061355,
      "grad_norm": 3.6413562297821045,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.122,
      "step": 25
    },
    {
      "epoch": 0.0006418450906873626,
      "grad_norm": 2.4354987144470215,
      "learning_rate": 5e-05,
      "loss": 0.1313,
      "step": 30
    },
    {
      "epoch": 0.0006418450906873626,
      "eval_loss": 0.10089851915836334,
      "eval_runtime": 1330.4675,
      "eval_samples_per_second": 14.793,
      "eval_steps_per_second": 7.397,
      "step": 30
    },
    {
      "epoch": 0.0007488192724685898,
      "grad_norm": 0.6122166514396667,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0806,
      "step": 35
    },
    {
      "epoch": 0.0008557934542498168,
      "grad_norm": 1.6655242443084717,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0817,
      "step": 40
    },
    {
      "epoch": 0.0008557934542498168,
      "eval_loss": 0.0756126344203949,
      "eval_runtime": 1328.4384,
      "eval_samples_per_second": 14.815,
      "eval_steps_per_second": 7.408,
      "step": 40
    },
    {
      "epoch": 0.0009627676360310439,
      "grad_norm": 3.3045506477355957,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.1229,
      "step": 45
    },
    {
      "epoch": 0.001069741817812271,
      "grad_norm": 1.370465636253357,
      "learning_rate": 0.0,
      "loss": 0.0739,
      "step": 50
    },
    {
      "epoch": 0.001069741817812271,
      "eval_loss": 0.07545288652181625,
      "eval_runtime": 1329.8786,
      "eval_samples_per_second": 14.799,
      "eval_steps_per_second": 7.4,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9247821240729600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}