trainer_state.json

{
  "best_metric": 5.264073371887207,
  "best_model_checkpoint": "./coco_outputs/checkpoint-32",
  "epoch": 10.0,
  "global_step": 40,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 5.533133506774902,
      "eval_runtime": 0.5515,
      "eval_samples_per_second": 14.505,
      "eval_steps_per_second": 1.813,
      "step": 4
    },
    {
      "epoch": 2.0,
      "eval_loss": 5.527740478515625,
      "eval_runtime": 0.5553,
      "eval_samples_per_second": 14.406,
      "eval_steps_per_second": 1.801,
      "step": 8
    },
    {
      "epoch": 2.5,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 5.4377,
      "step": 10
    },
    {
      "epoch": 3.0,
      "eval_loss": 5.444962024688721,
      "eval_runtime": 0.5512,
      "eval_samples_per_second": 14.513,
      "eval_steps_per_second": 1.814,
      "step": 12
    },
    {
      "epoch": 4.0,
      "eval_loss": 5.395962715148926,
      "eval_runtime": 0.5633,
      "eval_samples_per_second": 14.203,
      "eval_steps_per_second": 1.775,
      "step": 16
    },
    {
      "epoch": 5.0,
      "learning_rate": 1e-05,
      "loss": 5.1582,
      "step": 20
    },
    {
      "epoch": 5.0,
      "eval_loss": 5.334904670715332,
      "eval_runtime": 0.5523,
      "eval_samples_per_second": 14.484,
      "eval_steps_per_second": 1.81,
      "step": 20
    },
    {
      "epoch": 6.0,
      "eval_loss": 5.314438819885254,
      "eval_runtime": 0.552,
      "eval_samples_per_second": 14.493,
      "eval_steps_per_second": 1.812,
      "step": 24
    },
    {
      "epoch": 7.0,
      "eval_loss": 5.273761749267578,
      "eval_runtime": 0.5505,
      "eval_samples_per_second": 14.531,
      "eval_steps_per_second": 1.816,
      "step": 28
    },
    {
      "epoch": 7.5,
      "learning_rate": 5e-06,
      "loss": 5.0556,
      "step": 30
    },
    {
      "epoch": 8.0,
      "eval_loss": 5.264073371887207,
      "eval_runtime": 0.5581,
      "eval_samples_per_second": 14.334,
      "eval_steps_per_second": 1.792,
      "step": 32
    },
    {
      "epoch": 9.0,
      "eval_loss": 5.284775733947754,
      "eval_runtime": 0.5423,
      "eval_samples_per_second": 14.752,
      "eval_steps_per_second": 1.844,
      "step": 36
    },
    {
      "epoch": 10.0,
      "learning_rate": 0.0,
      "loss": 4.9784,
      "step": 40
    },
    {
      "epoch": 10.0,
      "eval_loss": 5.279171943664551,
      "eval_runtime": 0.5633,
      "eval_samples_per_second": 14.202,
      "eval_steps_per_second": 1.775,
      "step": 40
    },
    {
      "epoch": 10.0,
      "step": 40,
      "total_flos": 1.530004230144e+17,
      "train_loss": 5.157479572296142,
      "train_runtime": 182.2038,
      "train_samples_per_second": 1.756,
      "train_steps_per_second": 0.22
    }
  ],
  "max_steps": 40,
  "num_train_epochs": 10,
  "total_flos": 1.530004230144e+17,
  "trial_name": null,
  "trial_params": null
}