last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.007093596059113301,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007881773399014779,
      "grad_norm": 1.420249342918396,
      "learning_rate": 2e-05,
      "loss": 6.4461,
      "step": 1
    },
    {
      "epoch": 0.0015763546798029558,
      "grad_norm": 1.4954193830490112,
      "learning_rate": 4e-05,
      "loss": 6.4123,
      "step": 2
    },
    {
      "epoch": 0.0023645320197044333,
      "grad_norm": 1.5775469541549683,
      "learning_rate": 6e-05,
      "loss": 6.4432,
      "step": 3
    },
    {
      "epoch": 0.0023645320197044333,
      "eval_loss": 6.295650005340576,
      "eval_runtime": 12.3779,
      "eval_samples_per_second": 43.222,
      "eval_steps_per_second": 21.652,
      "step": 3
    },
    {
      "epoch": 0.0031527093596059115,
      "grad_norm": 1.4721767902374268,
      "learning_rate": 8e-05,
      "loss": 6.7091,
      "step": 4
    },
    {
      "epoch": 0.003940886699507389,
      "grad_norm": 1.3564282655715942,
      "learning_rate": 0.0001,
      "loss": 6.0962,
      "step": 5
    },
    {
      "epoch": 0.004729064039408867,
      "grad_norm": 1.4763870239257812,
      "learning_rate": 0.00012,
      "loss": 5.9891,
      "step": 6
    },
    {
      "epoch": 0.004729064039408867,
      "eval_loss": 6.271442413330078,
      "eval_runtime": 13.182,
      "eval_samples_per_second": 40.586,
      "eval_steps_per_second": 20.331,
      "step": 6
    },
    {
      "epoch": 0.005517241379310344,
      "grad_norm": 1.3695040941238403,
      "learning_rate": 0.00014,
      "loss": 6.6824,
      "step": 7
    },
    {
      "epoch": 0.006305418719211823,
      "grad_norm": 1.585157871246338,
      "learning_rate": 0.00016,
      "loss": 6.067,
      "step": 8
    },
    {
      "epoch": 0.007093596059113301,
      "grad_norm": 1.153540849685669,
      "learning_rate": 0.00018,
      "loss": 6.3986,
      "step": 9
    },
    {
      "epoch": 0.007093596059113301,
      "eval_loss": 6.218323707580566,
      "eval_runtime": 13.5637,
      "eval_samples_per_second": 39.443,
      "eval_steps_per_second": 19.759,
      "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": 786702532608.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}