checkpoint-190/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.968152866242038,
  "eval_steps": 500,
  "global_step": 190,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5095541401273885,
      "grad_norm": 21.399980545043945,
      "learning_rate": 4.8157894736842105e-05,
      "loss": 41.5426,
      "step": 10
    },
    {
      "epoch": 1.0509554140127388,
      "grad_norm": 17.988994598388672,
      "learning_rate": 4.552631578947369e-05,
      "loss": 29.4127,
      "step": 20
    },
    {
      "epoch": 1.5605095541401273,
      "grad_norm": 33.763912200927734,
      "learning_rate": 4.289473684210527e-05,
      "loss": 25.5085,
      "step": 30
    },
    {
      "epoch": 2.1019108280254777,
      "grad_norm": 16.56460952758789,
      "learning_rate": 4.026315789473684e-05,
      "loss": 20.56,
      "step": 40
    },
    {
      "epoch": 2.611464968152866,
      "grad_norm": 10.511013984680176,
      "learning_rate": 3.7631578947368425e-05,
      "loss": 18.1336,
      "step": 50
    },
    {
      "epoch": 3.1528662420382165,
      "grad_norm": 10.428191184997559,
      "learning_rate": 3.5e-05,
      "loss": 17.3703,
      "step": 60
    },
    {
      "epoch": 3.662420382165605,
      "grad_norm": 14.895818710327148,
      "learning_rate": 3.236842105263158e-05,
      "loss": 15.4829,
      "step": 70
    },
    {
      "epoch": 4.203821656050955,
      "grad_norm": 14.849196434020996,
      "learning_rate": 2.9736842105263157e-05,
      "loss": 15.0444,
      "step": 80
    },
    {
      "epoch": 4.713375796178344,
      "grad_norm": 18.697587966918945,
      "learning_rate": 2.710526315789474e-05,
      "loss": 12.8919,
      "step": 90
    },
    {
      "epoch": 5.254777070063694,
      "grad_norm": 15.368135452270508,
      "learning_rate": 2.4473684210526318e-05,
      "loss": 12.3344,
      "step": 100
    },
    {
      "epoch": 5.764331210191083,
      "grad_norm": 12.972413063049316,
      "learning_rate": 2.1842105263157896e-05,
      "loss": 10.8471,
      "step": 110
    },
    {
      "epoch": 6.305732484076433,
      "grad_norm": 12.219730377197266,
      "learning_rate": 1.9210526315789474e-05,
      "loss": 10.4139,
      "step": 120
    },
    {
      "epoch": 6.8152866242038215,
      "grad_norm": 10.693161964416504,
      "learning_rate": 1.6578947368421053e-05,
      "loss": 9.3934,
      "step": 130
    },
    {
      "epoch": 7.356687898089172,
      "grad_norm": 7.562994956970215,
      "learning_rate": 1.3947368421052631e-05,
      "loss": 9.3898,
      "step": 140
    },
    {
      "epoch": 7.86624203821656,
      "grad_norm": 8.633628845214844,
      "learning_rate": 1.1315789473684212e-05,
      "loss": 8.2861,
      "step": 150
    },
    {
      "epoch": 8.40764331210191,
      "grad_norm": 5.833484649658203,
      "learning_rate": 8.68421052631579e-06,
      "loss": 8.2805,
      "step": 160
    },
    {
      "epoch": 8.9171974522293,
      "grad_norm": 5.1007280349731445,
      "learning_rate": 6.0526315789473685e-06,
      "loss": 7.5686,
      "step": 170
    },
    {
      "epoch": 9.45859872611465,
      "grad_norm": 3.2410666942596436,
      "learning_rate": 3.421052631578948e-06,
      "loss": 7.6358,
      "step": 180
    },
    {
      "epoch": 9.968152866242038,
      "grad_norm": 3.1020469665527344,
      "learning_rate": 7.894736842105264e-07,
      "loss": 7.4635,
      "step": 190
    }
  ],
  "logging_steps": 10,
  "max_steps": 190,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4446215761035264.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}