{
  "best_metric": 0.48605167865753174,
  "best_model_checkpoint": "data/Mistral-7B_task-2_60-samples_config-1_auto/checkpoint-28",
  "epoch": 12.0,
  "eval_steps": 500,
  "global_step": 69,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.17391304347826086,
      "grad_norm": 1.5140224695205688,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.7126,
      "step": 1
    },
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 1.6478224992752075,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.8549,
      "step": 2
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 1.4883278608322144,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.7334,
      "step": 4
    },
    {
      "epoch": 0.8695652173913043,
      "eval_loss": 0.7062659859657288,
      "eval_runtime": 16.5385,
      "eval_samples_per_second": 0.726,
      "eval_steps_per_second": 0.726,
      "step": 5
    },
    {
      "epoch": 1.0434782608695652,
      "grad_norm": 1.2950339317321777,
      "learning_rate": 2.4e-05,
      "loss": 0.7356,
      "step": 6
    },
    {
      "epoch": 1.391304347826087,
      "grad_norm": 1.0016504526138306,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.655,
      "step": 8
    },
    {
      "epoch": 1.7391304347826086,
      "grad_norm": 0.7504082322120667,
      "learning_rate": 4e-05,
      "loss": 0.6319,
      "step": 10
    },
    {
      "epoch": 1.9130434782608696,
      "eval_loss": 0.5730427503585815,
      "eval_runtime": 16.5383,
      "eval_samples_per_second": 0.726,
      "eval_steps_per_second": 0.726,
      "step": 11
    },
    {
      "epoch": 2.0869565217391304,
      "grad_norm": 0.7791630029678345,
      "learning_rate": 4.8e-05,
      "loss": 0.5786,
      "step": 12
    },
    {
      "epoch": 2.4347826086956523,
      "grad_norm": 0.6501785516738892,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 0.5012,
      "step": 14
    },
    {
      "epoch": 2.782608695652174,
      "grad_norm": 0.7398867011070251,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.5266,
      "step": 16
    },
    {
      "epoch": 2.9565217391304346,
      "eval_loss": 0.5148289799690247,
      "eval_runtime": 16.5377,
      "eval_samples_per_second": 0.726,
      "eval_steps_per_second": 0.726,
      "step": 17
    },
    {
      "epoch": 3.130434782608696,
      "grad_norm": 0.6889784336090088,
      "learning_rate": 7.2e-05,
      "loss": 0.4804,
      "step": 18
    },
    {
      "epoch": 3.4782608695652173,
      "grad_norm": 0.7188368439674377,
      "learning_rate": 8e-05,
      "loss": 0.4278,
      "step": 20
    },
    {
      "epoch": 3.8260869565217392,
      "grad_norm": 0.6705220341682434,
      "learning_rate": 8.800000000000001e-05,
      "loss": 0.4086,
      "step": 22
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.48897695541381836,
      "eval_runtime": 16.5378,
      "eval_samples_per_second": 0.726,
      "eval_steps_per_second": 0.726,
      "step": 23
    },
    {
      "epoch": 4.173913043478261,
      "grad_norm": 0.7117646336555481,
      "learning_rate": 9.6e-05,
      "loss": 0.3999,
      "step": 24
    },
    {
      "epoch": 4.521739130434782,
      "grad_norm": 0.6636248826980591,
      "learning_rate": 9.999512620046522e-05,
      "loss": 0.3644,
      "step": 26
    },
    {
      "epoch": 4.869565217391305,
      "grad_norm": 0.7620681524276733,
      "learning_rate": 9.995614150494293e-05,
      "loss": 0.307,
      "step": 28
    },
    {
      "epoch": 4.869565217391305,
      "eval_loss": 0.48605167865753174,
      "eval_runtime": 16.5364,
      "eval_samples_per_second": 0.726,
      "eval_steps_per_second": 0.726,
      "step": 28
    },
    {
      "epoch": 5.217391304347826,
      "grad_norm": 0.6405394673347473,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.2639,
      "step": 30
    },
    {
      "epoch": 5.565217391304348,
      "grad_norm": 0.7212449312210083,
      "learning_rate": 9.976136999909156e-05,
      "loss": 0.2559,
      "step": 32
    },
    {
      "epoch": 5.913043478260869,
      "grad_norm": 0.7872556447982788,
      "learning_rate": 9.96057350657239e-05,
      "loss": 0.2061,
      "step": 34
    },
    {
      "epoch": 5.913043478260869,
      "eval_loss": 0.5479660034179688,
      "eval_runtime": 16.5381,
      "eval_samples_per_second": 0.726,
      "eval_steps_per_second": 0.726,
      "step": 34
    },
    {
      "epoch": 6.260869565217392,
      "grad_norm": 0.7487961053848267,
      "learning_rate": 9.941141907232765e-05,
      "loss": 0.1666,
      "step": 36
    },
    {
      "epoch": 6.608695652173913,
      "grad_norm": 0.7282887697219849,
      "learning_rate": 9.917857354066931e-05,
      "loss": 0.1278,
      "step": 38
    },
    {
      "epoch": 6.956521739130435,
      "grad_norm": 0.8547887802124023,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.1025,
      "step": 40
    },
    {
      "epoch": 6.956521739130435,
      "eval_loss": 0.6543639898300171,
      "eval_runtime": 16.5393,
      "eval_samples_per_second": 0.726,
      "eval_steps_per_second": 0.726,
      "step": 40
    },
    {
      "epoch": 7.304347826086957,
      "grad_norm": 1.0089316368103027,
      "learning_rate": 9.859805002892732e-05,
      "loss": 0.0678,
      "step": 42
    },
    {
      "epoch": 7.6521739130434785,
      "grad_norm": 0.7182652950286865,
      "learning_rate": 9.825082472361557e-05,
      "loss": 0.0501,
      "step": 44
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.8632131218910217,
      "learning_rate": 9.786597487660337e-05,
      "loss": 0.0474,
      "step": 46
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.7596723437309265,
      "eval_runtime": 16.5398,
      "eval_samples_per_second": 0.726,
      "eval_steps_per_second": 0.726,
      "step": 46
    },
    {
      "epoch": 8.347826086956522,
      "grad_norm": 0.6312950253486633,
      "learning_rate": 9.744380058222483e-05,
      "loss": 0.0269,
      "step": 48
    },
    {
      "epoch": 8.695652173913043,
      "grad_norm": 0.7501206994056702,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.0255,
      "step": 50
    },
    {
      "epoch": 8.869565217391305,
      "eval_loss": 0.7984176278114319,
      "eval_runtime": 16.5415,
      "eval_samples_per_second": 0.725,
      "eval_steps_per_second": 0.725,
      "step": 51
    },
    {
      "epoch": 9.043478260869565,
      "grad_norm": 0.8554216623306274,
      "learning_rate": 9.648882429441257e-05,
      "loss": 0.0291,
      "step": 52
    },
    {
      "epoch": 9.391304347826088,
      "grad_norm": 0.8836772441864014,
      "learning_rate": 9.595676696276172e-05,
      "loss": 0.0191,
      "step": 54
    },
    {
      "epoch": 9.73913043478261,
      "grad_norm": 0.7133678197860718,
      "learning_rate": 9.538887392664544e-05,
      "loss": 0.0223,
      "step": 56
    },
    {
      "epoch": 9.91304347826087,
      "eval_loss": 0.7588582634925842,
      "eval_runtime": 16.5401,
      "eval_samples_per_second": 0.726,
      "eval_steps_per_second": 0.726,
      "step": 57
    },
    {
      "epoch": 10.08695652173913,
      "grad_norm": 0.5711161494255066,
      "learning_rate": 9.478558801197065e-05,
      "loss": 0.0205,
      "step": 58
    },
    {
      "epoch": 10.434782608695652,
      "grad_norm": 0.44387462735176086,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.0113,
      "step": 60
    },
    {
      "epoch": 10.782608695652174,
      "grad_norm": 0.6449446678161621,
      "learning_rate": 9.347474647526095e-05,
      "loss": 0.0134,
      "step": 62
    },
    {
      "epoch": 10.956521739130435,
      "eval_loss": 0.8148854374885559,
      "eval_runtime": 16.5379,
      "eval_samples_per_second": 0.726,
      "eval_steps_per_second": 0.726,
      "step": 63
    },
    {
      "epoch": 11.130434782608695,
      "grad_norm": 0.5001112818717957,
      "learning_rate": 9.276821300802534e-05,
      "loss": 0.0129,
      "step": 64
    },
    {
      "epoch": 11.478260869565217,
      "grad_norm": 0.38408565521240234,
      "learning_rate": 9.202833017478422e-05,
      "loss": 0.0085,
      "step": 66
    },
    {
      "epoch": 11.826086956521738,
      "grad_norm": 0.4452236592769623,
      "learning_rate": 9.125567491391476e-05,
      "loss": 0.0068,
      "step": 68
    },
    {
      "epoch": 12.0,
      "eval_loss": 0.8506963849067688,
      "eval_runtime": 16.5373,
      "eval_samples_per_second": 0.726,
      "eval_steps_per_second": 0.726,
      "step": 69
    },
    {
      "epoch": 12.0,
      "step": 69,
      "total_flos": 6.846832342309274e+16,
      "train_loss": 0.26155890712001617,
      "train_runtime": 2487.0101,
      "train_samples_per_second": 0.925,
      "train_steps_per_second": 0.101
    }
  ],
  "logging_steps": 2,
  "max_steps": 250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 7,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.846832342309274e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}