last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01876348625574632,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.381743127873159e-05,
      "eval_loss": 0.9324500560760498,
      "eval_runtime": 245.1562,
      "eval_samples_per_second": 9.153,
      "eval_steps_per_second": 4.577,
      "step": 1
    },
    {
      "epoch": 0.0009381743127873159,
      "grad_norm": 1.0036320686340332,
      "learning_rate": 0.0002,
      "loss": 1.5169,
      "step": 10
    },
    {
      "epoch": 0.0018763486255746317,
      "grad_norm": 0.7501591444015503,
      "learning_rate": 0.0002,
      "loss": 1.1409,
      "step": 20
    },
    {
      "epoch": 0.0028145229383619475,
      "grad_norm": 0.8483043909072876,
      "learning_rate": 0.0002,
      "loss": 0.9805,
      "step": 30
    },
    {
      "epoch": 0.0037526972511492634,
      "grad_norm": 0.5633870363235474,
      "learning_rate": 0.0002,
      "loss": 1.1368,
      "step": 40
    },
    {
      "epoch": 0.00469087156393658,
      "grad_norm": 0.8526553511619568,
      "learning_rate": 0.0002,
      "loss": 1.0437,
      "step": 50
    },
    {
      "epoch": 0.00469087156393658,
      "eval_loss": 0.5282271504402161,
      "eval_runtime": 245.0343,
      "eval_samples_per_second": 9.158,
      "eval_steps_per_second": 4.579,
      "step": 50
    },
    {
      "epoch": 0.005629045876723895,
      "grad_norm": 0.6110089421272278,
      "learning_rate": 0.0002,
      "loss": 0.9785,
      "step": 60
    },
    {
      "epoch": 0.006567220189511211,
      "grad_norm": 0.6589618921279907,
      "learning_rate": 0.0002,
      "loss": 1.2064,
      "step": 70
    },
    {
      "epoch": 0.007505394502298527,
      "grad_norm": 0.6540957093238831,
      "learning_rate": 0.0002,
      "loss": 1.0105,
      "step": 80
    },
    {
      "epoch": 0.008443568815085843,
      "grad_norm": 0.7634976506233215,
      "learning_rate": 0.0002,
      "loss": 0.97,
      "step": 90
    },
    {
      "epoch": 0.00938174312787316,
      "grad_norm": 0.7584695816040039,
      "learning_rate": 0.0002,
      "loss": 0.9857,
      "step": 100
    },
    {
      "epoch": 0.00938174312787316,
      "eval_loss": 0.5102854371070862,
      "eval_runtime": 245.1252,
      "eval_samples_per_second": 9.155,
      "eval_steps_per_second": 4.577,
      "step": 100
    },
    {
      "epoch": 0.010319917440660475,
      "grad_norm": 0.5788394808769226,
      "learning_rate": 0.0002,
      "loss": 1.0154,
      "step": 110
    },
    {
      "epoch": 0.01125809175344779,
      "grad_norm": 0.5604102611541748,
      "learning_rate": 0.0002,
      "loss": 1.1134,
      "step": 120
    },
    {
      "epoch": 0.012196266066235107,
      "grad_norm": 0.836513876914978,
      "learning_rate": 0.0002,
      "loss": 1.1753,
      "step": 130
    },
    {
      "epoch": 0.013134440379022422,
      "grad_norm": 1.2483829259872437,
      "learning_rate": 0.0002,
      "loss": 1.0936,
      "step": 140
    },
    {
      "epoch": 0.014072614691809739,
      "grad_norm": 0.7146385312080383,
      "learning_rate": 0.0002,
      "loss": 1.0279,
      "step": 150
    },
    {
      "epoch": 0.014072614691809739,
      "eval_loss": 0.5074164867401123,
      "eval_runtime": 245.1114,
      "eval_samples_per_second": 9.155,
      "eval_steps_per_second": 4.578,
      "step": 150
    },
    {
      "epoch": 0.015010789004597054,
      "grad_norm": 0.8109822869300842,
      "learning_rate": 0.0002,
      "loss": 1.0838,
      "step": 160
    },
    {
      "epoch": 0.01594896331738437,
      "grad_norm": 0.43211817741394043,
      "learning_rate": 0.0002,
      "loss": 1.0516,
      "step": 170
    },
    {
      "epoch": 0.016887137630171686,
      "grad_norm": 0.5124821662902832,
      "learning_rate": 0.0002,
      "loss": 0.9819,
      "step": 180
    },
    {
      "epoch": 0.017825311942959002,
      "grad_norm": 2.5899274349212646,
      "learning_rate": 0.0002,
      "loss": 0.987,
      "step": 190
    },
    {
      "epoch": 0.01876348625574632,
      "grad_norm": 0.7276327610015869,
      "learning_rate": 0.0002,
      "loss": 0.9722,
      "step": 200
    },
    {
      "epoch": 0.01876348625574632,
      "eval_loss": 0.4974622130393982,
      "eval_runtime": 245.2117,
      "eval_samples_per_second": 9.151,
      "eval_steps_per_second": 4.576,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.4339615678464e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}