last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0006324910660636918,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.324910660636919e-05,
      "grad_norm": 12.095507621765137,
      "learning_rate": 2e-05,
      "loss": 8.0756,
      "step": 1
    },
    {
      "epoch": 6.324910660636919e-05,
      "eval_loss": 9.130346298217773,
      "eval_runtime": 226.4984,
      "eval_samples_per_second": 29.395,
      "eval_steps_per_second": 14.698,
      "step": 1
    },
    {
      "epoch": 0.00012649821321273838,
      "grad_norm": 15.04973316192627,
      "learning_rate": 4e-05,
      "loss": 7.2496,
      "step": 2
    },
    {
      "epoch": 0.00018974731981910754,
      "grad_norm": 14.547382354736328,
      "learning_rate": 6e-05,
      "loss": 8.5275,
      "step": 3
    },
    {
      "epoch": 0.00018974731981910754,
      "eval_loss": 9.00229549407959,
      "eval_runtime": 226.4272,
      "eval_samples_per_second": 29.405,
      "eval_steps_per_second": 14.702,
      "step": 3
    },
    {
      "epoch": 0.00025299642642547676,
      "grad_norm": 16.72240447998047,
      "learning_rate": 8e-05,
      "loss": 8.9993,
      "step": 4
    },
    {
      "epoch": 0.0003162455330318459,
      "grad_norm": 12.045751571655273,
      "learning_rate": 0.0001,
      "loss": 8.7741,
      "step": 5
    },
    {
      "epoch": 0.0003794946396382151,
      "grad_norm": 17.086132049560547,
      "learning_rate": 0.00012,
      "loss": 9.3432,
      "step": 6
    },
    {
      "epoch": 0.0003794946396382151,
      "eval_loss": 7.4766669273376465,
      "eval_runtime": 226.3391,
      "eval_samples_per_second": 29.416,
      "eval_steps_per_second": 14.708,
      "step": 6
    },
    {
      "epoch": 0.0004427437462445843,
      "grad_norm": 13.617958068847656,
      "learning_rate": 0.00014,
      "loss": 7.4227,
      "step": 7
    },
    {
      "epoch": 0.0005059928528509535,
      "grad_norm": 12.062705993652344,
      "learning_rate": 0.00016,
      "loss": 6.9968,
      "step": 8
    },
    {
      "epoch": 0.0005692419594573227,
      "grad_norm": 14.231619834899902,
      "learning_rate": 0.00018,
      "loss": 5.896,
      "step": 9
    },
    {
      "epoch": 0.0005692419594573227,
      "eval_loss": 6.201642990112305,
      "eval_runtime": 226.526,
      "eval_samples_per_second": 29.392,
      "eval_steps_per_second": 14.696,
      "step": 9
    },
    {
      "epoch": 0.0006324910660636918,
      "grad_norm": 15.345791816711426,
      "learning_rate": 0.0002,
      "loss": 5.3196,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1911091416268800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}