trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "global_step": 9475,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "learning_rate": 4.736147757255937e-05,
      "loss": 0.5473,
      "step": 500
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.4722955145118735e-05,
      "loss": 0.5618,
      "step": 1000
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.2094986807387866e-05,
      "loss": 0.5662,
      "step": 1500
    },
    {
      "epoch": 0.21,
      "learning_rate": 3.945646437994723e-05,
      "loss": 0.5662,
      "step": 2000
    },
    {
      "epoch": 0.26,
      "learning_rate": 3.68179419525066e-05,
      "loss": 0.5654,
      "step": 2500
    },
    {
      "epoch": 0.32,
      "learning_rate": 3.4179419525065965e-05,
      "loss": 0.5466,
      "step": 3000
    },
    {
      "epoch": 0.37,
      "learning_rate": 3.154089709762533e-05,
      "loss": 0.5468,
      "step": 3500
    },
    {
      "epoch": 0.42,
      "learning_rate": 2.8902374670184694e-05,
      "loss": 0.5387,
      "step": 4000
    },
    {
      "epoch": 0.47,
      "learning_rate": 2.6263852242744064e-05,
      "loss": 0.5383,
      "step": 4500
    },
    {
      "epoch": 0.53,
      "learning_rate": 2.3625329815303433e-05,
      "loss": 0.5215,
      "step": 5000
    },
    {
      "epoch": 0.58,
      "learning_rate": 2.0986807387862796e-05,
      "loss": 0.5299,
      "step": 5500
    },
    {
      "epoch": 0.63,
      "learning_rate": 1.8348284960422166e-05,
      "loss": 0.541,
      "step": 6000
    },
    {
      "epoch": 0.69,
      "learning_rate": 1.571503957783641e-05,
      "loss": 0.5235,
      "step": 6500
    },
    {
      "epoch": 0.74,
      "learning_rate": 1.3076517150395778e-05,
      "loss": 0.5041,
      "step": 7000
    },
    {
      "epoch": 0.79,
      "learning_rate": 1.0437994722955146e-05,
      "loss": 0.5135,
      "step": 7500
    },
    {
      "epoch": 0.84,
      "learning_rate": 7.804749340369394e-06,
      "loss": 0.5302,
      "step": 8000
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.16622691292876e-06,
      "loss": 0.5206,
      "step": 8500
    },
    {
      "epoch": 0.95,
      "learning_rate": 2.5277044854881265e-06,
      "loss": 0.5454,
      "step": 9000
    },
    {
      "epoch": 1.0,
      "eval_gen_len": 229.9856,
      "eval_loss": 1.0093897581100464,
      "eval_rouge1": 0.5781,
      "eval_rouge2": 0.3786,
      "eval_rougeL": 0.4342,
      "eval_rougeLsum": 0.4342,
      "eval_runtime": 7098.2277,
      "eval_samples_per_second": 0.461,
      "eval_steps_per_second": 0.23,
      "step": 9475
    }
  ],
  "max_steps": 9475,
  "num_train_epochs": 1,
  "total_flos": 5.116618141492838e+16,
  "trial_name": null,
  "trial_params": null
}