{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 750,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4,
      "grad_norm": 0.48472875356674194,
      "learning_rate": 0.0003,
      "loss": 2.3219,
      "step": 100
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.4583953619003296,
      "learning_rate": 0.0003,
      "loss": 2.2487,
      "step": 200
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5168253968253969,
      "eval_loss": 2.311781167984009,
      "eval_runtime": 5.4425,
      "eval_samples_per_second": 91.87,
      "eval_steps_per_second": 11.576,
      "step": 250
    },
    {
      "epoch": 1.0,
      "eval_exact_match": 18.6,
      "eval_f1": 26.999121042356347,
      "step": 250
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.6610094904899597,
      "learning_rate": 0.0003,
      "loss": 2.083,
      "step": 300
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.7361629605293274,
      "learning_rate": 0.0003,
      "loss": 1.9274,
      "step": 400
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.6793610453605652,
      "learning_rate": 0.0003,
      "loss": 1.9113,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5153650793650794,
      "eval_loss": 2.3749232292175293,
      "eval_runtime": 5.2167,
      "eval_samples_per_second": 95.846,
      "eval_steps_per_second": 12.077,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_exact_match": 18.2,
      "eval_f1": 26.209704184704197,
      "step": 500
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.8843489289283752,
      "learning_rate": 0.0003,
      "loss": 1.4602,
      "step": 600
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.8380613923072815,
      "learning_rate": 0.0003,
      "loss": 1.4924,
      "step": 700
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.5098730158730159,
      "eval_loss": 2.5289740562438965,
      "eval_runtime": 5.3631,
      "eval_samples_per_second": 93.23,
      "eval_steps_per_second": 11.747,
      "step": 750
    },
    {
      "epoch": 3.0,
      "eval_exact_match": 16.6,
      "eval_f1": 24.526153291153296,
      "step": 750
    }
  ],
  "logging_steps": 100,
  "max_steps": 12500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.940307860835533e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}