checkpoint-1451/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 291,
  "global_step": 1451,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06891798759476224,
      "grad_norm": 47.0,
      "learning_rate": 9.88326321974139e-06,
      "loss": 0.6874,
      "step": 100
    },
    {
      "epoch": 0.13783597518952448,
      "grad_norm": 25.0,
      "learning_rate": 9.53850386931162e-06,
      "loss": 0.6895,
      "step": 200
    },
    {
      "epoch": 0.2005513439007581,
      "eval_accuracy": 0.569592611154865,
      "eval_loss": 0.6835629940032959,
      "eval_runtime": 378.97,
      "eval_samples_per_second": 221.131,
      "eval_steps_per_second": 27.643,
      "step": 291
    },
    {
      "epoch": 0.2067539627842867,
      "grad_norm": 21.625,
      "learning_rate": 8.981820387323976e-06,
      "loss": 0.6849,
      "step": 300
    },
    {
      "epoch": 0.27567195037904896,
      "grad_norm": 14.5,
      "learning_rate": 8.239206948702616e-06,
      "loss": 0.6902,
      "step": 400
    },
    {
      "epoch": 0.34458993797381116,
      "grad_norm": 23.875,
      "learning_rate": 7.345339674168113e-06,
      "loss": 0.6849,
      "step": 500
    },
    {
      "epoch": 0.4011026878015162,
      "eval_accuracy": 0.5740077802439083,
      "eval_loss": 0.6811934113502502,
      "eval_runtime": 377.4685,
      "eval_samples_per_second": 222.011,
      "eval_steps_per_second": 27.753,
      "step": 582
    },
    {
      "epoch": 0.4135079255685734,
      "grad_norm": 25.125,
      "learning_rate": 6.341957438763544e-06,
      "loss": 0.6813,
      "step": 600
    },
    {
      "epoch": 0.4824259131633356,
      "grad_norm": 14.875,
      "learning_rate": 5.275912887100837e-06,
      "loss": 0.6878,
      "step": 700
    },
    {
      "epoch": 0.5513439007580979,
      "grad_norm": 21.25,
      "learning_rate": 4.1969846626093244e-06,
      "loss": 0.6902,
      "step": 800
    },
    {
      "epoch": 0.6016540317022743,
      "eval_accuracy": 0.5770864657168087,
      "eval_loss": 0.6811434030532837,
      "eval_runtime": 379.7091,
      "eval_samples_per_second": 220.701,
      "eval_steps_per_second": 27.59,
      "step": 873
    },
    {
      "epoch": 0.6202618883528601,
      "grad_norm": 12.125,
      "learning_rate": 3.155553008111921e-06,
      "loss": 0.6893,
      "step": 900
    },
    {
      "epoch": 0.6891798759476223,
      "grad_norm": 39.5,
      "learning_rate": 2.2002472748907948e-06,
      "loss": 0.6849,
      "step": 1000
    },
    {
      "epoch": 0.7580978635423845,
      "grad_norm": 21.875,
      "learning_rate": 1.3756751891294767e-06,
      "loss": 0.6868,
      "step": 1100
    },
    {
      "epoch": 0.8022053756030324,
      "eval_accuracy": 0.5794491778239182,
      "eval_loss": 0.6808037161827087,
      "eval_runtime": 378.7407,
      "eval_samples_per_second": 221.265,
      "eval_steps_per_second": 27.66,
      "step": 1164
    },
    {
      "epoch": 0.8270158511371468,
      "grad_norm": 14.75,
      "learning_rate": 7.203399069811245e-07,
      "loss": 0.6872,
      "step": 1200
    },
    {
      "epoch": 0.895933838731909,
      "grad_norm": 26.125,
      "learning_rate": 2.6484212077688697e-07,
      "loss": 0.6866,
      "step": 1300
    },
    {
      "epoch": 0.9648518263266712,
      "grad_norm": 24.75,
      "learning_rate": 3.045116850732776e-08,
      "loss": 0.6843,
      "step": 1400
    }
  ],
  "logging_steps": 100,
  "max_steps": 1451,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 291,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}