last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0019809607659714962,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00022010675177461069,
      "grad_norm": 2.3234410285949707,
      "learning_rate": 2e-05,
      "loss": 0.9409,
      "step": 1
    },
    {
      "epoch": 0.00022010675177461069,
      "eval_loss": 1.067487120628357,
      "eval_runtime": 60.8653,
      "eval_samples_per_second": 31.43,
      "eval_steps_per_second": 15.723,
      "step": 1
    },
    {
      "epoch": 0.00044021350354922137,
      "grad_norm": 1.5731563568115234,
      "learning_rate": 4e-05,
      "loss": 0.8715,
      "step": 2
    },
    {
      "epoch": 0.0006603202553238321,
      "grad_norm": 1.8221330642700195,
      "learning_rate": 6e-05,
      "loss": 1.0494,
      "step": 3
    },
    {
      "epoch": 0.0006603202553238321,
      "eval_loss": 1.0474679470062256,
      "eval_runtime": 59.6174,
      "eval_samples_per_second": 32.088,
      "eval_steps_per_second": 16.052,
      "step": 3
    },
    {
      "epoch": 0.0008804270070984427,
      "grad_norm": 3.308648109436035,
      "learning_rate": 8e-05,
      "loss": 1.0557,
      "step": 4
    },
    {
      "epoch": 0.0011005337588730535,
      "grad_norm": 1.81417977809906,
      "learning_rate": 0.0001,
      "loss": 0.8147,
      "step": 5
    },
    {
      "epoch": 0.0013206405106476642,
      "grad_norm": 2.7671899795532227,
      "learning_rate": 0.00012,
      "loss": 0.8201,
      "step": 6
    },
    {
      "epoch": 0.0013206405106476642,
      "eval_loss": 0.637837827205658,
      "eval_runtime": 59.6348,
      "eval_samples_per_second": 32.079,
      "eval_steps_per_second": 16.048,
      "step": 6
    },
    {
      "epoch": 0.0015407472624222747,
      "grad_norm": 1.5493115186691284,
      "learning_rate": 0.00014,
      "loss": 0.5435,
      "step": 7
    },
    {
      "epoch": 0.0017608540141968855,
      "grad_norm": 1.634792447090149,
      "learning_rate": 0.00016,
      "loss": 0.4386,
      "step": 8
    },
    {
      "epoch": 0.0019809607659714962,
      "grad_norm": 1.606994390487671,
      "learning_rate": 0.00018,
      "loss": 0.4914,
      "step": 9
    },
    {
      "epoch": 0.0019809607659714962,
      "eval_loss": 0.4517509341239929,
      "eval_runtime": 59.7395,
      "eval_samples_per_second": 32.022,
      "eval_steps_per_second": 16.02,
      "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": 1664607823331328.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}