last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00046078702423739745,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.607870242373975e-05,
      "grad_norm": 0.3347959816455841,
      "learning_rate": 2e-05,
      "loss": 4.5458,
      "step": 1
    },
    {
      "epoch": 4.607870242373975e-05,
      "eval_loss": 1.1763094663619995,
      "eval_runtime": 704.1942,
      "eval_samples_per_second": 12.977,
      "eval_steps_per_second": 6.488,
      "step": 1
    },
    {
      "epoch": 9.21574048474795e-05,
      "grad_norm": 0.3298984169960022,
      "learning_rate": 4e-05,
      "loss": 3.6827,
      "step": 2
    },
    {
      "epoch": 0.00013823610727121925,
      "grad_norm": 0.3755097985267639,
      "learning_rate": 6e-05,
      "loss": 4.302,
      "step": 3
    },
    {
      "epoch": 0.00013823610727121925,
      "eval_loss": 1.1759552955627441,
      "eval_runtime": 703.1445,
      "eval_samples_per_second": 12.996,
      "eval_steps_per_second": 6.498,
      "step": 3
    },
    {
      "epoch": 0.000184314809694959,
      "grad_norm": 0.2986769378185272,
      "learning_rate": 8e-05,
      "loss": 3.098,
      "step": 4
    },
    {
      "epoch": 0.00023039351211869873,
      "grad_norm": 0.33066195249557495,
      "learning_rate": 0.0001,
      "loss": 3.9477,
      "step": 5
    },
    {
      "epoch": 0.0002764722145424385,
      "grad_norm": 0.41436532139778137,
      "learning_rate": 0.00012,
      "loss": 4.5851,
      "step": 6
    },
    {
      "epoch": 0.0002764722145424385,
      "eval_loss": 1.170326590538025,
      "eval_runtime": 704.7785,
      "eval_samples_per_second": 12.966,
      "eval_steps_per_second": 6.483,
      "step": 6
    },
    {
      "epoch": 0.00032255091696617823,
      "grad_norm": 0.39940911531448364,
      "learning_rate": 0.00014,
      "loss": 4.4628,
      "step": 7
    },
    {
      "epoch": 0.000368629619389918,
      "grad_norm": 0.5509176850318909,
      "learning_rate": 0.00016,
      "loss": 5.1362,
      "step": 8
    },
    {
      "epoch": 0.0004147083218136577,
      "grad_norm": 0.5903463959693909,
      "learning_rate": 0.00018,
      "loss": 4.7602,
      "step": 9
    },
    {
      "epoch": 0.0004147083218136577,
      "eval_loss": 1.1366020441055298,
      "eval_runtime": 703.5932,
      "eval_samples_per_second": 12.988,
      "eval_steps_per_second": 6.494,
      "step": 9
    },
    {
      "epoch": 0.00046078702423739745,
      "grad_norm": 0.7386853694915771,
      "learning_rate": 0.0002,
      "loss": 4.7492,
      "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": 5065958888570880.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}