last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.005864242779651078,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005864242779651077,
      "grad_norm": 3.436047077178955,
      "learning_rate": 2e-05,
      "loss": 2.4464,
      "step": 1
    },
    {
      "epoch": 0.0005864242779651077,
      "eval_loss": 2.367367744445801,
      "eval_runtime": 110.1746,
      "eval_samples_per_second": 6.517,
      "eval_steps_per_second": 3.258,
      "step": 1
    },
    {
      "epoch": 0.0011728485559302155,
      "grad_norm": 3.8748509883880615,
      "learning_rate": 4e-05,
      "loss": 2.7912,
      "step": 2
    },
    {
      "epoch": 0.0017592728338953233,
      "grad_norm": 2.7464218139648438,
      "learning_rate": 6e-05,
      "loss": 2.4864,
      "step": 3
    },
    {
      "epoch": 0.0017592728338953233,
      "eval_loss": 2.3375210762023926,
      "eval_runtime": 110.4015,
      "eval_samples_per_second": 6.504,
      "eval_steps_per_second": 3.252,
      "step": 3
    },
    {
      "epoch": 0.002345697111860431,
      "grad_norm": 3.067667007446289,
      "learning_rate": 8e-05,
      "loss": 2.2758,
      "step": 4
    },
    {
      "epoch": 0.002932121389825539,
      "grad_norm": 3.1528449058532715,
      "learning_rate": 0.0001,
      "loss": 2.0774,
      "step": 5
    },
    {
      "epoch": 0.0035185456677906467,
      "grad_norm": 3.4223129749298096,
      "learning_rate": 0.00012,
      "loss": 2.3995,
      "step": 6
    },
    {
      "epoch": 0.0035185456677906467,
      "eval_loss": 2.007136821746826,
      "eval_runtime": 110.0306,
      "eval_samples_per_second": 6.525,
      "eval_steps_per_second": 3.263,
      "step": 6
    },
    {
      "epoch": 0.004104969945755754,
      "grad_norm": 3.431300163269043,
      "learning_rate": 0.00014,
      "loss": 1.9596,
      "step": 7
    },
    {
      "epoch": 0.004691394223720862,
      "grad_norm": 2.9658634662628174,
      "learning_rate": 0.00016,
      "loss": 1.8995,
      "step": 8
    },
    {
      "epoch": 0.00527781850168597,
      "grad_norm": 3.0212576389312744,
      "learning_rate": 0.00018,
      "loss": 1.8483,
      "step": 9
    },
    {
      "epoch": 0.00527781850168597,
      "eval_loss": 1.6423418521881104,
      "eval_runtime": 109.9227,
      "eval_samples_per_second": 6.532,
      "eval_steps_per_second": 3.266,
      "step": 9
    },
    {
      "epoch": 0.005864242779651078,
      "grad_norm": 2.9213950634002686,
      "learning_rate": 0.0002,
      "loss": 1.8063,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1935445139128320.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}