last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.005389221556886228,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005988023952095808,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 10.8959,
      "step": 1
    },
    {
      "epoch": 0.0005988023952095808,
      "eval_loss": 11.577476501464844,
      "eval_runtime": 47.7616,
      "eval_samples_per_second": 14.74,
      "eval_steps_per_second": 7.37,
      "step": 1
    },
    {
      "epoch": 0.0011976047904191617,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 10.0136,
      "step": 2
    },
    {
      "epoch": 0.0017964071856287425,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 11.649,
      "step": 3
    },
    {
      "epoch": 0.0017964071856287425,
      "eval_loss": 11.577476501464844,
      "eval_runtime": 47.9565,
      "eval_samples_per_second": 14.68,
      "eval_steps_per_second": 7.34,
      "step": 3
    },
    {
      "epoch": 0.0023952095808383233,
      "grad_norm": 9.167847633361816,
      "learning_rate": 2e-05,
      "loss": 11.4872,
      "step": 4
    },
    {
      "epoch": 0.0029940119760479044,
      "grad_norm": 6.535604953765869,
      "learning_rate": 4e-05,
      "loss": 9.9558,
      "step": 5
    },
    {
      "epoch": 0.003592814371257485,
      "grad_norm": 8.272323608398438,
      "learning_rate": 6e-05,
      "loss": 11.9577,
      "step": 6
    },
    {
      "epoch": 0.003592814371257485,
      "eval_loss": 11.506834983825684,
      "eval_runtime": 47.6191,
      "eval_samples_per_second": 14.784,
      "eval_steps_per_second": 7.392,
      "step": 6
    },
    {
      "epoch": 0.004191616766467066,
      "grad_norm": 8.094924926757812,
      "learning_rate": 8e-05,
      "loss": 12.3056,
      "step": 7
    },
    {
      "epoch": 0.004790419161676647,
      "grad_norm": 9.111627578735352,
      "learning_rate": 0.0001,
      "loss": 9.0397,
      "step": 8
    },
    {
      "epoch": 0.005389221556886228,
      "grad_norm": 6.980569839477539,
      "learning_rate": 0.00012,
      "loss": 9.2177,
      "step": 9
    },
    {
      "epoch": 0.005389221556886228,
      "eval_loss": 10.915068626403809,
      "eval_runtime": 47.9969,
      "eval_samples_per_second": 14.668,
      "eval_steps_per_second": 7.334,
      "step": 9
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3329215646662656.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}