last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.001620285980475554,
  "eval_steps": 10,
  "global_step": 40,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.050714951188885e-05,
      "eval_loss": 2.130146026611328,
      "eval_runtime": 332.2487,
      "eval_samples_per_second": 7.822,
      "eval_steps_per_second": 3.913,
      "step": 1
    },
    {
      "epoch": 0.00012152144853566654,
      "grad_norm": 1.2408714294433594,
      "learning_rate": 6e-05,
      "loss": 2.1776,
      "step": 3
    },
    {
      "epoch": 0.00024304289707133308,
      "grad_norm": 1.1398706436157227,
      "learning_rate": 0.00012,
      "loss": 2.3135,
      "step": 6
    },
    {
      "epoch": 0.0003645643456069996,
      "grad_norm": 1.4346201419830322,
      "learning_rate": 0.00018,
      "loss": 2.037,
      "step": 9
    },
    {
      "epoch": 0.0004050714951188885,
      "eval_loss": 2.0305228233337402,
      "eval_runtime": 335.7037,
      "eval_samples_per_second": 7.742,
      "eval_steps_per_second": 3.872,
      "step": 10
    },
    {
      "epoch": 0.00048608579414266616,
      "grad_norm": 1.5074211359024048,
      "learning_rate": 0.00019781476007338058,
      "loss": 2.0111,
      "step": 12
    },
    {
      "epoch": 0.0006076072426783327,
      "grad_norm": 1.5198981761932373,
      "learning_rate": 0.00018660254037844388,
      "loss": 2.1894,
      "step": 15
    },
    {
      "epoch": 0.0007291286912139992,
      "grad_norm": 1.4036415815353394,
      "learning_rate": 0.00016691306063588583,
      "loss": 2.1162,
      "step": 18
    },
    {
      "epoch": 0.000810142990237777,
      "eval_loss": 1.9362800121307373,
      "eval_runtime": 331.4839,
      "eval_samples_per_second": 7.841,
      "eval_steps_per_second": 3.922,
      "step": 20
    },
    {
      "epoch": 0.0008506501397496658,
      "grad_norm": 1.4190822839736938,
      "learning_rate": 0.00014067366430758004,
      "loss": 1.7328,
      "step": 21
    },
    {
      "epoch": 0.0009721715882853323,
      "grad_norm": 1.5082824230194092,
      "learning_rate": 0.00011045284632676536,
      "loss": 1.7984,
      "step": 24
    },
    {
      "epoch": 0.001093693036820999,
      "grad_norm": 1.2184019088745117,
      "learning_rate": 7.920883091822408e-05,
      "loss": 1.852,
      "step": 27
    },
    {
      "epoch": 0.0012152144853566655,
      "grad_norm": 1.190232515335083,
      "learning_rate": 5.000000000000002e-05,
      "loss": 1.8741,
      "step": 30
    },
    {
      "epoch": 0.0012152144853566655,
      "eval_loss": 1.899240255355835,
      "eval_runtime": 334.4518,
      "eval_samples_per_second": 7.771,
      "eval_steps_per_second": 3.887,
      "step": 30
    },
    {
      "epoch": 0.001336735933892332,
      "grad_norm": 1.4657238721847534,
      "learning_rate": 2.5685517452260567e-05,
      "loss": 2.0548,
      "step": 33
    },
    {
      "epoch": 0.0014582573824279985,
      "grad_norm": 1.554992437362671,
      "learning_rate": 8.645454235739903e-06,
      "loss": 2.1922,
      "step": 36
    },
    {
      "epoch": 0.001579778830963665,
      "grad_norm": 1.369084358215332,
      "learning_rate": 5.478104631726711e-07,
      "loss": 1.8381,
      "step": 39
    },
    {
      "epoch": 0.001620285980475554,
      "eval_loss": 1.891857385635376,
      "eval_runtime": 335.6622,
      "eval_samples_per_second": 7.743,
      "eval_steps_per_second": 3.873,
      "step": 40
    }
  ],
  "logging_steps": 3,
  "max_steps": 40,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6120570089373696.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}