last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 7.926829268292683,
  "eval_steps": 100,
  "global_step": 1300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 0.9854,
      "step": 100
    },
    {
      "epoch": 0.61,
      "eval_runtime": 33.8919,
      "eval_samples_per_second": 2.036,
      "eval_steps_per_second": 0.266,
      "step": 100
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0002,
      "loss": 0.1264,
      "step": 200
    },
    {
      "epoch": 1.22,
      "eval_runtime": 33.8732,
      "eval_samples_per_second": 2.037,
      "eval_steps_per_second": 0.266,
      "step": 200
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.0002,
      "loss": 0.1122,
      "step": 300
    },
    {
      "epoch": 1.83,
      "eval_runtime": 33.8939,
      "eval_samples_per_second": 2.036,
      "eval_steps_per_second": 0.266,
      "step": 300
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.0002,
      "loss": 0.0857,
      "step": 400
    },
    {
      "epoch": 2.44,
      "eval_runtime": 33.8527,
      "eval_samples_per_second": 2.038,
      "eval_steps_per_second": 0.266,
      "step": 400
    },
    {
      "epoch": 3.05,
      "learning_rate": 0.0002,
      "loss": 0.0777,
      "step": 500
    },
    {
      "epoch": 3.05,
      "eval_runtime": 33.8767,
      "eval_samples_per_second": 2.037,
      "eval_steps_per_second": 0.266,
      "step": 500
    },
    {
      "epoch": 3.66,
      "learning_rate": 0.0002,
      "loss": 0.0576,
      "step": 600
    },
    {
      "epoch": 3.66,
      "eval_runtime": 33.8607,
      "eval_samples_per_second": 2.038,
      "eval_steps_per_second": 0.266,
      "step": 600
    },
    {
      "epoch": 4.27,
      "learning_rate": 0.0002,
      "loss": 0.0524,
      "step": 700
    },
    {
      "epoch": 4.27,
      "eval_runtime": 33.9187,
      "eval_samples_per_second": 2.034,
      "eval_steps_per_second": 0.265,
      "step": 700
    },
    {
      "epoch": 4.88,
      "learning_rate": 0.0002,
      "loss": 0.0431,
      "step": 800
    },
    {
      "epoch": 4.88,
      "eval_runtime": 33.8539,
      "eval_samples_per_second": 2.038,
      "eval_steps_per_second": 0.266,
      "step": 800
    },
    {
      "epoch": 5.49,
      "learning_rate": 0.0002,
      "loss": 0.0356,
      "step": 900
    },
    {
      "epoch": 5.49,
      "eval_runtime": 33.8728,
      "eval_samples_per_second": 2.037,
      "eval_steps_per_second": 0.266,
      "step": 900
    },
    {
      "epoch": 6.1,
      "learning_rate": 0.0002,
      "loss": 0.0345,
      "step": 1000
    },
    {
      "epoch": 6.1,
      "eval_runtime": 33.8717,
      "eval_samples_per_second": 2.037,
      "eval_steps_per_second": 0.266,
      "step": 1000
    },
    {
      "epoch": 6.71,
      "learning_rate": 0.0002,
      "loss": 0.0287,
      "step": 1100
    },
    {
      "epoch": 6.71,
      "eval_runtime": 33.8531,
      "eval_samples_per_second": 2.038,
      "eval_steps_per_second": 0.266,
      "step": 1100
    },
    {
      "epoch": 7.32,
      "learning_rate": 0.0002,
      "loss": 0.0267,
      "step": 1200
    },
    {
      "epoch": 7.32,
      "eval_runtime": 33.8867,
      "eval_samples_per_second": 2.036,
      "eval_steps_per_second": 0.266,
      "step": 1200
    },
    {
      "epoch": 7.93,
      "learning_rate": 0.0002,
      "loss": 0.0257,
      "step": 1300
    },
    {
      "epoch": 7.93,
      "eval_runtime": 33.8768,
      "eval_samples_per_second": 2.037,
      "eval_steps_per_second": 0.266,
      "step": 1300
    }
  ],
  "logging_steps": 100,
  "max_steps": 1312,
  "num_train_epochs": 8,
  "save_steps": 100,
  "total_flos": 1.0796396610532147e+17,
  "trial_name": null,
  "trial_params": null
}