trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.05318588730911,
  "eval_steps": 50,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "eval_loss": 1.8554456233978271,
      "eval_runtime": 2143.5349,
      "eval_samples_per_second": 2.363,
      "eval_steps_per_second": 0.074,
      "step": 50
    },
    {
      "epoch": 0.11,
      "eval_loss": 1.8419370651245117,
      "eval_runtime": 2143.6574,
      "eval_samples_per_second": 2.363,
      "eval_steps_per_second": 0.074,
      "step": 100
    },
    {
      "epoch": 0.16,
      "eval_loss": 1.832232117652893,
      "eval_runtime": 2143.9117,
      "eval_samples_per_second": 2.363,
      "eval_steps_per_second": 0.074,
      "step": 150
    },
    {
      "epoch": 0.21,
      "eval_loss": 1.8266302347183228,
      "eval_runtime": 2144.0794,
      "eval_samples_per_second": 2.363,
      "eval_steps_per_second": 0.074,
      "step": 200
    },
    {
      "epoch": 0.26,
      "eval_loss": 1.8243311643600464,
      "eval_runtime": 2144.1306,
      "eval_samples_per_second": 2.363,
      "eval_steps_per_second": 0.074,
      "step": 250
    },
    {
      "epoch": 0.32,
      "eval_loss": 1.8222966194152832,
      "eval_runtime": 2144.2111,
      "eval_samples_per_second": 2.363,
      "eval_steps_per_second": 0.074,
      "step": 300
    },
    {
      "epoch": 0.37,
      "eval_loss": 1.8207086324691772,
      "eval_runtime": 2143.8422,
      "eval_samples_per_second": 2.363,
      "eval_steps_per_second": 0.074,
      "step": 350
    },
    {
      "epoch": 0.42,
      "eval_loss": 1.8194689750671387,
      "eval_runtime": 2143.9601,
      "eval_samples_per_second": 2.363,
      "eval_steps_per_second": 0.074,
      "step": 400
    },
    {
      "epoch": 0.47,
      "eval_loss": 1.818217158317566,
      "eval_runtime": 2142.9482,
      "eval_samples_per_second": 2.364,
      "eval_steps_per_second": 0.074,
      "step": 450
    },
    {
      "epoch": 0.53,
      "learning_rate": 1.0050251256281408e-05,
      "loss": 1.8371,
      "step": 500
    },
    {
      "epoch": 0.53,
      "eval_loss": 1.8166958093643188,
      "eval_runtime": 2143.0693,
      "eval_samples_per_second": 2.364,
      "eval_steps_per_second": 0.074,
      "step": 500
    },
    {
      "epoch": 0.58,
      "eval_loss": 1.8156176805496216,
      "eval_runtime": 2143.2912,
      "eval_samples_per_second": 2.364,
      "eval_steps_per_second": 0.074,
      "step": 550
    },
    {
      "epoch": 0.63,
      "eval_loss": 1.8143000602722168,
      "eval_runtime": 2143.0457,
      "eval_samples_per_second": 2.364,
      "eval_steps_per_second": 0.074,
      "step": 600
    },
    {
      "epoch": 0.68,
      "eval_loss": 1.813321590423584,
      "eval_runtime": 2142.6086,
      "eval_samples_per_second": 2.364,
      "eval_steps_per_second": 0.074,
      "step": 650
    },
    {
      "epoch": 0.74,
      "eval_loss": 1.8123859167099,
      "eval_runtime": 2142.7684,
      "eval_samples_per_second": 2.364,
      "eval_steps_per_second": 0.074,
      "step": 700
    },
    {
      "epoch": 0.79,
      "eval_loss": 1.81136155128479,
      "eval_runtime": 2143.3216,
      "eval_samples_per_second": 2.364,
      "eval_steps_per_second": 0.074,
      "step": 750
    },
    {
      "epoch": 0.84,
      "eval_loss": 1.8105697631835938,
      "eval_runtime": 2142.989,
      "eval_samples_per_second": 2.364,
      "eval_steps_per_second": 0.074,
      "step": 800
    },
    {
      "epoch": 0.9,
      "eval_loss": 1.8099677562713623,
      "eval_runtime": 2142.6436,
      "eval_samples_per_second": 2.364,
      "eval_steps_per_second": 0.074,
      "step": 850
    },
    {
      "epoch": 0.95,
      "eval_loss": 1.809475302696228,
      "eval_runtime": 2142.6825,
      "eval_samples_per_second": 2.364,
      "eval_steps_per_second": 0.074,
      "step": 900
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.8091450929641724,
      "eval_runtime": 2142.5605,
      "eval_samples_per_second": 2.364,
      "eval_steps_per_second": 0.074,
      "step": 950
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0,
      "loss": 1.8001,
      "step": 1000
    },
    {
      "epoch": 1.05,
      "eval_loss": 1.809110403060913,
      "eval_runtime": 2142.8135,
      "eval_samples_per_second": 2.364,
      "eval_steps_per_second": 0.074,
      "step": 1000
    }
  ],
  "logging_steps": 500,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "total_flos": 7.15390604279808e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}