last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.000421474105684632,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.21474105684632e-05,
      "grad_norm": 0.01097105909138918,
      "learning_rate": 2e-05,
      "loss": 11.7653,
      "step": 1
    },
    {
      "epoch": 4.21474105684632e-05,
      "eval_loss": 11.765829086303711,
      "eval_runtime": 44.926,
      "eval_samples_per_second": 222.366,
      "eval_steps_per_second": 111.183,
      "step": 1
    },
    {
      "epoch": 8.42948211369264e-05,
      "grad_norm": 0.010537141002714634,
      "learning_rate": 4e-05,
      "loss": 11.7684,
      "step": 2
    },
    {
      "epoch": 0.0001264422317053896,
      "grad_norm": 0.013774622231721878,
      "learning_rate": 6e-05,
      "loss": 11.7666,
      "step": 3
    },
    {
      "epoch": 0.0001264422317053896,
      "eval_loss": 11.765824317932129,
      "eval_runtime": 44.9441,
      "eval_samples_per_second": 222.276,
      "eval_steps_per_second": 111.138,
      "step": 3
    },
    {
      "epoch": 0.0001685896422738528,
      "grad_norm": 0.0140291228890419,
      "learning_rate": 8e-05,
      "loss": 11.765,
      "step": 4
    },
    {
      "epoch": 0.000210737052842316,
      "grad_norm": 0.012857336550951004,
      "learning_rate": 0.0001,
      "loss": 11.764,
      "step": 5
    },
    {
      "epoch": 0.0002528844634107792,
      "grad_norm": 0.012306353077292442,
      "learning_rate": 0.00012,
      "loss": 11.7684,
      "step": 6
    },
    {
      "epoch": 0.0002528844634107792,
      "eval_loss": 11.765801429748535,
      "eval_runtime": 45.1213,
      "eval_samples_per_second": 221.403,
      "eval_steps_per_second": 110.701,
      "step": 6
    },
    {
      "epoch": 0.0002950318739792424,
      "grad_norm": 0.01133581344038248,
      "learning_rate": 0.00014,
      "loss": 11.7684,
      "step": 7
    },
    {
      "epoch": 0.0003371792845477056,
      "grad_norm": 0.0108329551294446,
      "learning_rate": 0.00016,
      "loss": 11.7639,
      "step": 8
    },
    {
      "epoch": 0.0003793266951161688,
      "grad_norm": 0.013684643432497978,
      "learning_rate": 0.00018,
      "loss": 11.7665,
      "step": 9
    },
    {
      "epoch": 0.0003793266951161688,
      "eval_loss": 11.765763282775879,
      "eval_runtime": 44.9712,
      "eval_samples_per_second": 222.142,
      "eval_steps_per_second": 111.071,
      "step": 9
    },
    {
      "epoch": 0.000421474105684632,
      "grad_norm": 0.015935491770505905,
      "learning_rate": 0.0002,
      "loss": 11.7665,
      "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": 812484919296.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}