{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0013505209634616553,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.7010419269233105e-05,
      "eval_loss": 3.10772442817688,
      "eval_runtime": 1187.1961,
      "eval_samples_per_second": 13.131,
      "eval_steps_per_second": 6.566,
      "step": 1
    },
    {
      "epoch": 0.00013505209634616554,
      "grad_norm": 3.13470721244812,
      "learning_rate": 5e-05,
      "loss": 2.9975,
      "step": 5
    },
    {
      "epoch": 0.0002701041926923311,
      "grad_norm": 3.5096006393432617,
      "learning_rate": 0.0001,
      "loss": 2.8866,
      "step": 10
    },
    {
      "epoch": 0.0002701041926923311,
      "eval_loss": 2.533891201019287,
      "eval_runtime": 1192.6144,
      "eval_samples_per_second": 13.071,
      "eval_steps_per_second": 6.536,
      "step": 10
    },
    {
      "epoch": 0.0004051562890384966,
      "grad_norm": 2.7829275131225586,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.4226,
      "step": 15
    },
    {
      "epoch": 0.0005402083853846621,
      "grad_norm": 2.209815502166748,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.3744,
      "step": 20
    },
    {
      "epoch": 0.0005402083853846621,
      "eval_loss": 2.0983729362487793,
      "eval_runtime": 1192.9184,
      "eval_samples_per_second": 13.068,
      "eval_steps_per_second": 6.534,
      "step": 20
    },
    {
      "epoch": 0.0006752604817308277,
      "grad_norm": 2.978599786758423,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.0518,
      "step": 25
    },
    {
      "epoch": 0.0008103125780769932,
      "grad_norm": 2.711549997329712,
      "learning_rate": 5e-05,
      "loss": 2.0796,
      "step": 30
    },
    {
      "epoch": 0.0008103125780769932,
      "eval_loss": 2.007845401763916,
      "eval_runtime": 1193.4448,
      "eval_samples_per_second": 13.062,
      "eval_steps_per_second": 6.532,
      "step": 30
    },
    {
      "epoch": 0.0009453646744231588,
      "grad_norm": 2.468726873397827,
      "learning_rate": 3.086582838174551e-05,
      "loss": 2.106,
      "step": 35
    },
    {
      "epoch": 0.0010804167707693243,
      "grad_norm": 2.1198647022247314,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.9398,
      "step": 40
    },
    {
      "epoch": 0.0010804167707693243,
      "eval_loss": 1.9728028774261475,
      "eval_runtime": 1193.5239,
      "eval_samples_per_second": 13.061,
      "eval_steps_per_second": 6.531,
      "step": 40
    },
    {
      "epoch": 0.0012154688671154898,
      "grad_norm": 2.1173436641693115,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.9808,
      "step": 45
    },
    {
      "epoch": 0.0013505209634616553,
      "grad_norm": 2.887991428375244,
      "learning_rate": 0.0,
      "loss": 2.0277,
      "step": 50
    },
    {
      "epoch": 0.0013505209634616553,
      "eval_loss": 1.966479778289795,
      "eval_runtime": 1192.3329,
      "eval_samples_per_second": 13.074,
      "eval_steps_per_second": 6.538,
      "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": 4809119319982080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}