last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.814814814814815,
  "eval_steps": 100,
  "global_step": 1900,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15,
      "learning_rate": 0.0,
      "loss": 8.5238,
      "step": 100
    },
    {
      "epoch": 0.15,
      "eval_runtime": 788.2037,
      "eval_samples_per_second": 1.903,
      "eval_steps_per_second": 0.239,
      "step": 100
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0,
      "loss": 8.4542,
      "step": 200
    },
    {
      "epoch": 0.3,
      "eval_runtime": 788.181,
      "eval_samples_per_second": 1.903,
      "eval_steps_per_second": 0.239,
      "step": 200
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0,
      "loss": 8.4751,
      "step": 300
    },
    {
      "epoch": 0.44,
      "eval_runtime": 787.7273,
      "eval_samples_per_second": 1.904,
      "eval_steps_per_second": 0.239,
      "step": 300
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0,
      "loss": 8.6043,
      "step": 400
    },
    {
      "epoch": 0.59,
      "eval_runtime": 787.7907,
      "eval_samples_per_second": 1.904,
      "eval_steps_per_second": 0.239,
      "step": 400
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0,
      "loss": 8.2845,
      "step": 500
    },
    {
      "epoch": 0.74,
      "eval_runtime": 788.246,
      "eval_samples_per_second": 1.903,
      "eval_steps_per_second": 0.239,
      "step": 500
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0,
      "loss": 8.7866,
      "step": 600
    },
    {
      "epoch": 0.89,
      "eval_runtime": 787.5816,
      "eval_samples_per_second": 1.905,
      "eval_steps_per_second": 0.239,
      "step": 600
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0,
      "loss": 8.4979,
      "step": 700
    },
    {
      "epoch": 1.04,
      "eval_runtime": 788.4314,
      "eval_samples_per_second": 1.903,
      "eval_steps_per_second": 0.238,
      "step": 700
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0,
      "loss": 8.4584,
      "step": 800
    },
    {
      "epoch": 1.19,
      "eval_runtime": 787.875,
      "eval_samples_per_second": 1.904,
      "eval_steps_per_second": 0.239,
      "step": 800
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0,
      "loss": 8.3458,
      "step": 900
    },
    {
      "epoch": 1.33,
      "eval_runtime": 787.2391,
      "eval_samples_per_second": 1.905,
      "eval_steps_per_second": 0.239,
      "step": 900
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0,
      "loss": 8.5777,
      "step": 1000
    },
    {
      "epoch": 1.48,
      "eval_runtime": 787.2473,
      "eval_samples_per_second": 1.905,
      "eval_steps_per_second": 0.239,
      "step": 1000
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.0,
      "loss": 8.3661,
      "step": 1100
    },
    {
      "epoch": 1.63,
      "eval_runtime": 788.2154,
      "eval_samples_per_second": 1.903,
      "eval_steps_per_second": 0.239,
      "step": 1100
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.0,
      "loss": 8.781,
      "step": 1200
    },
    {
      "epoch": 1.78,
      "eval_runtime": 788.0952,
      "eval_samples_per_second": 1.903,
      "eval_steps_per_second": 0.239,
      "step": 1200
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.0,
      "loss": 8.6986,
      "step": 1300
    },
    {
      "epoch": 1.93,
      "eval_runtime": 787.9067,
      "eval_samples_per_second": 1.904,
      "eval_steps_per_second": 0.239,
      "step": 1300
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.0,
      "loss": 8.4373,
      "step": 1400
    },
    {
      "epoch": 2.07,
      "eval_runtime": 788.547,
      "eval_samples_per_second": 1.902,
      "eval_steps_per_second": 0.238,
      "step": 1400
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.0,
      "loss": 8.4733,
      "step": 1500
    },
    {
      "epoch": 2.22,
      "eval_runtime": 787.7569,
      "eval_samples_per_second": 1.904,
      "eval_steps_per_second": 0.239,
      "step": 1500
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.0,
      "loss": 8.3433,
      "step": 1600
    },
    {
      "epoch": 2.37,
      "eval_runtime": 788.3781,
      "eval_samples_per_second": 1.903,
      "eval_steps_per_second": 0.238,
      "step": 1600
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.0,
      "loss": 8.7091,
      "step": 1700
    },
    {
      "epoch": 2.52,
      "eval_runtime": 788.7408,
      "eval_samples_per_second": 1.902,
      "eval_steps_per_second": 0.238,
      "step": 1700
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.0,
      "loss": 8.4647,
      "step": 1800
    },
    {
      "epoch": 2.67,
      "eval_runtime": 788.0902,
      "eval_samples_per_second": 1.903,
      "eval_steps_per_second": 0.239,
      "step": 1800
    },
    {
      "epoch": 2.81,
      "learning_rate": 0.0,
      "loss": 8.657,
      "step": 1900
    },
    {
      "epoch": 2.81,
      "eval_runtime": 787.6516,
      "eval_samples_per_second": 1.904,
      "eval_steps_per_second": 0.239,
      "step": 1900
    }
  ],
  "logging_steps": 100,
  "max_steps": 2025,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 3.95656757772288e+17,
  "trial_name": null,
  "trial_params": null
}