last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.011560693641618497,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011560693641618498,
      "grad_norm": 8.86544418334961,
      "learning_rate": 2e-05,
      "loss": 4.8382,
      "step": 1
    },
    {
      "epoch": 0.0023121387283236996,
      "grad_norm": 9.398510932922363,
      "learning_rate": 4e-05,
      "loss": 6.1737,
      "step": 2
    },
    {
      "epoch": 0.003468208092485549,
      "grad_norm": 10.827157020568848,
      "learning_rate": 6e-05,
      "loss": 6.3809,
      "step": 3
    },
    {
      "epoch": 0.003468208092485549,
      "eval_loss": 6.183577537536621,
      "eval_runtime": 18.4455,
      "eval_samples_per_second": 19.788,
      "eval_steps_per_second": 9.921,
      "step": 3
    },
    {
      "epoch": 0.004624277456647399,
      "grad_norm": 17.195674896240234,
      "learning_rate": 8e-05,
      "loss": 7.602,
      "step": 4
    },
    {
      "epoch": 0.005780346820809248,
      "grad_norm": 8.001276016235352,
      "learning_rate": 0.0001,
      "loss": 5.3469,
      "step": 5
    },
    {
      "epoch": 0.006936416184971098,
      "grad_norm": 7.932531833648682,
      "learning_rate": 0.00012,
      "loss": 5.0063,
      "step": 6
    },
    {
      "epoch": 0.006936416184971098,
      "eval_loss": 5.616068363189697,
      "eval_runtime": 16.9717,
      "eval_samples_per_second": 21.506,
      "eval_steps_per_second": 10.783,
      "step": 6
    },
    {
      "epoch": 0.008092485549132947,
      "grad_norm": 7.412410736083984,
      "learning_rate": 0.00014,
      "loss": 4.4387,
      "step": 7
    },
    {
      "epoch": 0.009248554913294798,
      "grad_norm": 7.8807220458984375,
      "learning_rate": 0.00016,
      "loss": 4.8257,
      "step": 8
    },
    {
      "epoch": 0.010404624277456647,
      "grad_norm": 15.530240058898926,
      "learning_rate": 0.00018,
      "loss": 5.0285,
      "step": 9
    },
    {
      "epoch": 0.010404624277456647,
      "eval_loss": 4.390628337860107,
      "eval_runtime": 16.7613,
      "eval_samples_per_second": 21.776,
      "eval_steps_per_second": 10.918,
      "step": 9
    },
    {
      "epoch": 0.011560693641618497,
      "grad_norm": 9.691489219665527,
      "learning_rate": 0.0002,
      "loss": 3.651,
      "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": 89038163804160.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}