{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.987452948557089,
  "eval_steps": 500,
  "global_step": 198,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "grad_norm": 0.13307033479213715,
      "learning_rate": 0.0002,
      "loss": 1.3135,
      "step": 10
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.25080665946006775,
      "learning_rate": 0.0002,
      "loss": 0.8903,
      "step": 20
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.22090280055999756,
      "learning_rate": 0.0002,
      "loss": 1.0646,
      "step": 30
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.14331598579883575,
      "learning_rate": 0.0002,
      "loss": 1.0373,
      "step": 40
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.4005136489868164,
      "learning_rate": 0.0002,
      "loss": 0.8402,
      "step": 50
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.14100393652915955,
      "learning_rate": 0.0002,
      "loss": 1.1971,
      "step": 60
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.17817306518554688,
      "learning_rate": 0.0002,
      "loss": 0.8422,
      "step": 70
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.15485863387584686,
      "learning_rate": 0.0002,
      "loss": 1.0806,
      "step": 80
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.13957808911800385,
      "learning_rate": 0.0002,
      "loss": 0.9923,
      "step": 90
    },
    {
      "epoch": 0.99,
      "eval_loss": 1.075861930847168,
      "eval_runtime": 15.627,
      "eval_samples_per_second": 6.399,
      "eval_steps_per_second": 0.256,
      "step": 99
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.17686176300048828,
      "learning_rate": 0.0002,
      "loss": 0.8183,
      "step": 100
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.13432720303535461,
      "learning_rate": 0.0002,
      "loss": 1.1495,
      "step": 110
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.16776545345783234,
      "learning_rate": 0.0002,
      "loss": 0.7245,
      "step": 120
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.12988704442977905,
      "learning_rate": 0.0002,
      "loss": 0.9554,
      "step": 130
    },
    {
      "epoch": 1.41,
      "grad_norm": 0.1477508395910263,
      "learning_rate": 0.0002,
      "loss": 0.9577,
      "step": 140
    },
    {
      "epoch": 1.51,
      "grad_norm": 0.2590917944908142,
      "learning_rate": 0.0002,
      "loss": 0.6792,
      "step": 150
    },
    {
      "epoch": 1.61,
      "grad_norm": 0.13945309817790985,
      "learning_rate": 0.0002,
      "loss": 1.121,
      "step": 160
    },
    {
      "epoch": 1.71,
      "grad_norm": 0.19059790670871735,
      "learning_rate": 0.0002,
      "loss": 0.6953,
      "step": 170
    },
    {
      "epoch": 1.81,
      "grad_norm": 0.09515325725078583,
      "learning_rate": 0.0002,
      "loss": 0.9976,
      "step": 180
    },
    {
      "epoch": 1.91,
      "grad_norm": 0.1453874409198761,
      "learning_rate": 0.0002,
      "loss": 0.8999,
      "step": 190
    },
    {
      "epoch": 1.99,
      "eval_loss": 1.0925697088241577,
      "eval_runtime": 4.0721,
      "eval_samples_per_second": 24.557,
      "eval_steps_per_second": 0.982,
      "step": 198
    },
    {
      "epoch": 1.99,
      "step": 198,
      "total_flos": 7.115900132922491e+17,
      "train_loss": 0.9474106412945371,
      "train_runtime": 6013.7693,
      "train_samples_per_second": 16.962,
      "train_steps_per_second": 0.033
    }
  ],
  "logging_steps": 10,
  "max_steps": 198,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 250,
  "total_flos": 7.115900132922491e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}