last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.11080332409972299,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0110803324099723,
      "grad_norm": 0.08606012165546417,
      "learning_rate": 2e-05,
      "loss": 10.3679,
      "step": 1
    },
    {
      "epoch": 0.0110803324099723,
      "eval_loss": 10.373393058776855,
      "eval_runtime": 0.4078,
      "eval_samples_per_second": 93.184,
      "eval_steps_per_second": 46.592,
      "step": 1
    },
    {
      "epoch": 0.0221606648199446,
      "grad_norm": 0.18870310485363007,
      "learning_rate": 4e-05,
      "loss": 10.3646,
      "step": 2
    },
    {
      "epoch": 0.0332409972299169,
      "grad_norm": 0.2350943684577942,
      "learning_rate": 6e-05,
      "loss": 10.3604,
      "step": 3
    },
    {
      "epoch": 0.0332409972299169,
      "eval_loss": 10.373261451721191,
      "eval_runtime": 0.4066,
      "eval_samples_per_second": 93.457,
      "eval_steps_per_second": 46.728,
      "step": 3
    },
    {
      "epoch": 0.0443213296398892,
      "grad_norm": 0.14036059379577637,
      "learning_rate": 8e-05,
      "loss": 10.3715,
      "step": 4
    },
    {
      "epoch": 0.055401662049861494,
      "grad_norm": 0.1268535703420639,
      "learning_rate": 0.0001,
      "loss": 10.3677,
      "step": 5
    },
    {
      "epoch": 0.0664819944598338,
      "grad_norm": 0.15055766701698303,
      "learning_rate": 0.00012,
      "loss": 10.3802,
      "step": 6
    },
    {
      "epoch": 0.0664819944598338,
      "eval_loss": 10.37267780303955,
      "eval_runtime": 0.4337,
      "eval_samples_per_second": 87.62,
      "eval_steps_per_second": 43.81,
      "step": 6
    },
    {
      "epoch": 0.07756232686980609,
      "grad_norm": 0.16558660566806793,
      "learning_rate": 0.00014,
      "loss": 10.3895,
      "step": 7
    },
    {
      "epoch": 0.0886426592797784,
      "grad_norm": 0.12472208589315414,
      "learning_rate": 0.00016,
      "loss": 10.3771,
      "step": 8
    },
    {
      "epoch": 0.0997229916897507,
      "grad_norm": 0.11151370406150818,
      "learning_rate": 0.00018,
      "loss": 10.3862,
      "step": 9
    },
    {
      "epoch": 0.0997229916897507,
      "eval_loss": 10.371695518493652,
      "eval_runtime": 0.4355,
      "eval_samples_per_second": 87.261,
      "eval_steps_per_second": 43.63,
      "step": 9
    },
    {
      "epoch": 0.11080332409972299,
      "grad_norm": 0.18714073300361633,
      "learning_rate": 0.0002,
      "loss": 10.3692,
      "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": 2086058065920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}