last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03372681281618887,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003372681281618887,
      "grad_norm": 0.030453594401478767,
      "learning_rate": 2e-05,
      "loss": 10.381,
      "step": 1
    },
    {
      "epoch": 0.003372681281618887,
      "eval_loss": 10.37465763092041,
      "eval_runtime": 0.3273,
      "eval_samples_per_second": 381.963,
      "eval_steps_per_second": 192.509,
      "step": 1
    },
    {
      "epoch": 0.006745362563237774,
      "grad_norm": 0.029300829395651817,
      "learning_rate": 4e-05,
      "loss": 10.3787,
      "step": 2
    },
    {
      "epoch": 0.01011804384485666,
      "grad_norm": 0.02577313221991062,
      "learning_rate": 6e-05,
      "loss": 10.3806,
      "step": 3
    },
    {
      "epoch": 0.01011804384485666,
      "eval_loss": 10.374650955200195,
      "eval_runtime": 0.3238,
      "eval_samples_per_second": 386.063,
      "eval_steps_per_second": 194.576,
      "step": 3
    },
    {
      "epoch": 0.013490725126475547,
      "grad_norm": 0.022721419110894203,
      "learning_rate": 8e-05,
      "loss": 10.3721,
      "step": 4
    },
    {
      "epoch": 0.016863406408094434,
      "grad_norm": 0.03573333099484444,
      "learning_rate": 0.0001,
      "loss": 10.3794,
      "step": 5
    },
    {
      "epoch": 0.02023608768971332,
      "grad_norm": 0.04152175039052963,
      "learning_rate": 0.00012,
      "loss": 10.3683,
      "step": 6
    },
    {
      "epoch": 0.02023608768971332,
      "eval_loss": 10.374604225158691,
      "eval_runtime": 0.337,
      "eval_samples_per_second": 370.951,
      "eval_steps_per_second": 186.96,
      "step": 6
    },
    {
      "epoch": 0.023608768971332208,
      "grad_norm": 0.02588420733809471,
      "learning_rate": 0.00014,
      "loss": 10.3753,
      "step": 7
    },
    {
      "epoch": 0.026981450252951095,
      "grad_norm": 0.028491251170635223,
      "learning_rate": 0.00016,
      "loss": 10.3721,
      "step": 8
    },
    {
      "epoch": 0.03035413153456998,
      "grad_norm": 0.026920998468995094,
      "learning_rate": 0.00018,
      "loss": 10.3763,
      "step": 9
    },
    {
      "epoch": 0.03035413153456998,
      "eval_loss": 10.37453556060791,
      "eval_runtime": 0.3633,
      "eval_samples_per_second": 344.086,
      "eval_steps_per_second": 173.419,
      "step": 9
    },
    {
      "epoch": 0.03372681281618887,
      "grad_norm": 0.036097653210163116,
      "learning_rate": 0.0002,
      "loss": 10.384,
      "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
}