last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00031336665465427825,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.1336665465427825e-05,
      "grad_norm": 4.4659423828125,
      "learning_rate": 2e-05,
      "loss": 2.3745,
      "step": 1
    },
    {
      "epoch": 6.267333093085565e-05,
      "grad_norm": 4.945820331573486,
      "learning_rate": 4e-05,
      "loss": 2.4926,
      "step": 2
    },
    {
      "epoch": 9.400999639628348e-05,
      "grad_norm": 4.904719829559326,
      "learning_rate": 6e-05,
      "loss": 2.5051,
      "step": 3
    },
    {
      "epoch": 9.400999639628348e-05,
      "eval_loss": 2.4358768463134766,
      "eval_runtime": 907.5382,
      "eval_samples_per_second": 14.806,
      "eval_steps_per_second": 7.404,
      "step": 3
    },
    {
      "epoch": 0.0001253466618617113,
      "grad_norm": 5.215977668762207,
      "learning_rate": 8e-05,
      "loss": 2.4588,
      "step": 4
    },
    {
      "epoch": 0.00015668332732713913,
      "grad_norm": 4.574519157409668,
      "learning_rate": 0.0001,
      "loss": 2.3348,
      "step": 5
    },
    {
      "epoch": 0.00018801999279256695,
      "grad_norm": 3.121293544769287,
      "learning_rate": 0.00012,
      "loss": 2.2783,
      "step": 6
    },
    {
      "epoch": 0.00018801999279256695,
      "eval_loss": 1.8826760053634644,
      "eval_runtime": 919.8555,
      "eval_samples_per_second": 14.608,
      "eval_steps_per_second": 7.304,
      "step": 6
    },
    {
      "epoch": 0.00021935665825799478,
      "grad_norm": 2.1884148120880127,
      "learning_rate": 0.00014,
      "loss": 1.9445,
      "step": 7
    },
    {
      "epoch": 0.0002506933237234226,
      "grad_norm": 1.762728214263916,
      "learning_rate": 0.00016,
      "loss": 1.6886,
      "step": 8
    },
    {
      "epoch": 0.0002820299891888504,
      "grad_norm": 2.1065804958343506,
      "learning_rate": 0.00018,
      "loss": 1.6875,
      "step": 9
    },
    {
      "epoch": 0.0002820299891888504,
      "eval_loss": 1.4193613529205322,
      "eval_runtime": 920.8157,
      "eval_samples_per_second": 14.592,
      "eval_steps_per_second": 7.297,
      "step": 9
    },
    {
      "epoch": 0.00031336665465427825,
      "grad_norm": 1.6040438413619995,
      "learning_rate": 0.0002,
      "loss": 1.4018,
      "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": 685606636093440.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}