last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0003883721381828068,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.8837213818280675e-05,
      "grad_norm": 0.09116487205028534,
      "learning_rate": 2e-05,
      "loss": 10.3833,
      "step": 1
    },
    {
      "epoch": 3.8837213818280675e-05,
      "eval_loss": 10.375828742980957,
      "eval_runtime": 59.4677,
      "eval_samples_per_second": 182.317,
      "eval_steps_per_second": 91.159,
      "step": 1
    },
    {
      "epoch": 7.767442763656135e-05,
      "grad_norm": 0.13251082599163055,
      "learning_rate": 4e-05,
      "loss": 10.3816,
      "step": 2
    },
    {
      "epoch": 0.00011651164145484203,
      "grad_norm": 0.08048108220100403,
      "learning_rate": 6e-05,
      "loss": 10.385,
      "step": 3
    },
    {
      "epoch": 0.00011651164145484203,
      "eval_loss": 10.375800132751465,
      "eval_runtime": 59.4582,
      "eval_samples_per_second": 182.347,
      "eval_steps_per_second": 91.173,
      "step": 3
    },
    {
      "epoch": 0.0001553488552731227,
      "grad_norm": 0.06645001471042633,
      "learning_rate": 8e-05,
      "loss": 10.3744,
      "step": 4
    },
    {
      "epoch": 0.0001941860690914034,
      "grad_norm": 0.10007822513580322,
      "learning_rate": 0.0001,
      "loss": 10.3704,
      "step": 5
    },
    {
      "epoch": 0.00023302328290968405,
      "grad_norm": 0.10815110802650452,
      "learning_rate": 0.00012,
      "loss": 10.3775,
      "step": 6
    },
    {
      "epoch": 0.00023302328290968405,
      "eval_loss": 10.37564754486084,
      "eval_runtime": 59.3153,
      "eval_samples_per_second": 182.786,
      "eval_steps_per_second": 91.393,
      "step": 6
    },
    {
      "epoch": 0.0002718604967279647,
      "grad_norm": 0.0938277393579483,
      "learning_rate": 0.00014,
      "loss": 10.3709,
      "step": 7
    },
    {
      "epoch": 0.0003106977105462454,
      "grad_norm": 0.08944696187973022,
      "learning_rate": 0.00016,
      "loss": 10.3851,
      "step": 8
    },
    {
      "epoch": 0.0003495349243645261,
      "grad_norm": 0.106475830078125,
      "learning_rate": 0.00018,
      "loss": 10.3803,
      "step": 9
    },
    {
      "epoch": 0.0003495349243645261,
      "eval_loss": 10.375385284423828,
      "eval_runtime": 58.5506,
      "eval_samples_per_second": 185.173,
      "eval_steps_per_second": 92.587,
      "step": 9
    },
    {
      "epoch": 0.0003883721381828068,
      "grad_norm": 0.07338559627532959,
      "learning_rate": 0.0002,
      "loss": 10.3845,
      "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": 129309081600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}