{
  "best_metric": 1.2853014469146729,
  "best_model_checkpoint": "data/Llama-31-8B_task-1_60-samples_config-1/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": 1.9813579320907593,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.073,
      "step": 1
    },
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 1.8313475847244263,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.0852,
      "step": 2
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 1.7238192558288574,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 2.1529,
      "step": 4
    },
    {
      "epoch": 0.8695652173913043,
      "eval_loss": 2.0041069984436035,
      "eval_runtime": 4.8643,
      "eval_samples_per_second": 2.467,
      "eval_steps_per_second": 2.467,
      "step": 5
    },
    {
      "epoch": 1.0434782608695652,
      "grad_norm": 1.8038513660430908,
      "learning_rate": 2.4e-05,
      "loss": 2.0483,
      "step": 6
    },
    {
      "epoch": 1.391304347826087,
      "grad_norm": 1.8350396156311035,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 2.0287,
      "step": 8
    },
    {
      "epoch": 1.7391304347826086,
      "grad_norm": 1.627516746520996,
      "learning_rate": 4e-05,
      "loss": 1.7276,
      "step": 10
    },
    {
      "epoch": 1.9130434782608696,
      "eval_loss": 1.6163220405578613,
      "eval_runtime": 4.8521,
      "eval_samples_per_second": 2.473,
      "eval_steps_per_second": 2.473,
      "step": 11
    },
    {
      "epoch": 2.0869565217391304,
      "grad_norm": 0.9827105402946472,
      "learning_rate": 4.8e-05,
      "loss": 1.5965,
      "step": 12
    },
    {
      "epoch": 2.4347826086956523,
      "grad_norm": 0.7503597140312195,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 1.5403,
      "step": 14
    },
    {
      "epoch": 2.782608695652174,
      "grad_norm": 1.0193320512771606,
      "learning_rate": 6.400000000000001e-05,
      "loss": 1.5018,
      "step": 16
    },
    {
      "epoch": 2.9565217391304346,
      "eval_loss": 1.463134765625,
      "eval_runtime": 4.9169,
      "eval_samples_per_second": 2.441,
      "eval_steps_per_second": 2.441,
      "step": 17
    },
    {
      "epoch": 3.130434782608696,
      "grad_norm": 0.7495579719543457,
      "learning_rate": 7.2e-05,
      "loss": 1.4009,
      "step": 18
    },
    {
      "epoch": 3.4782608695652173,
      "grad_norm": 0.8146828413009644,
      "learning_rate": 8e-05,
      "loss": 1.2842,
      "step": 20
    },
    {
      "epoch": 3.8260869565217392,
      "grad_norm": 0.8759430050849915,
      "learning_rate": 8.800000000000001e-05,
      "loss": 1.3727,
      "step": 22
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.3337726593017578,
      "eval_runtime": 4.9016,
      "eval_samples_per_second": 2.448,
      "eval_steps_per_second": 2.448,
      "step": 23
    },
    {
      "epoch": 4.173913043478261,
      "grad_norm": 0.7865839004516602,
      "learning_rate": 9.6e-05,
      "loss": 1.2452,
      "step": 24
    },
    {
      "epoch": 4.521739130434782,
      "grad_norm": 0.7563604116439819,
      "learning_rate": 9.999512620046522e-05,
      "loss": 1.1817,
      "step": 26
    },
    {
      "epoch": 4.869565217391305,
      "grad_norm": 0.791088342666626,
      "learning_rate": 9.995614150494293e-05,
      "loss": 1.0912,
      "step": 28
    },
    {
      "epoch": 4.869565217391305,
      "eval_loss": 1.2853014469146729,
      "eval_runtime": 4.8827,
      "eval_samples_per_second": 2.458,
      "eval_steps_per_second": 2.458,
      "step": 28
    },
    {
      "epoch": 5.217391304347826,
      "grad_norm": 0.8185644745826721,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.0722,
      "step": 30
    },
    {
      "epoch": 5.565217391304348,
      "grad_norm": 0.9191321134567261,
      "learning_rate": 9.976136999909156e-05,
      "loss": 0.9712,
      "step": 32
    },
    {
      "epoch": 5.913043478260869,
      "grad_norm": 1.0726240873336792,
      "learning_rate": 9.96057350657239e-05,
      "loss": 0.8709,
      "step": 34
    },
    {
      "epoch": 5.913043478260869,
      "eval_loss": 1.2904514074325562,
      "eval_runtime": 4.8494,
      "eval_samples_per_second": 2.475,
      "eval_steps_per_second": 2.475,
      "step": 34
    },
    {
      "epoch": 6.260869565217392,
      "grad_norm": 0.9275307059288025,
      "learning_rate": 9.941141907232765e-05,
      "loss": 0.6996,
      "step": 36
    },
    {
      "epoch": 6.608695652173913,
      "grad_norm": 1.382583498954773,
      "learning_rate": 9.917857354066931e-05,
      "loss": 0.7177,
      "step": 38
    },
    {
      "epoch": 6.956521739130435,
      "grad_norm": 1.5849192142486572,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.713,
      "step": 40
    },
    {
      "epoch": 6.956521739130435,
      "eval_loss": 1.4712576866149902,
      "eval_runtime": 4.8441,
      "eval_samples_per_second": 2.477,
      "eval_steps_per_second": 2.477,
      "step": 40
    },
    {
      "epoch": 7.304347826086957,
      "grad_norm": 1.2915489673614502,
      "learning_rate": 9.859805002892732e-05,
      "loss": 0.5017,
      "step": 42
    },
    {
      "epoch": 7.6521739130434785,
      "grad_norm": 1.3434025049209595,
      "learning_rate": 9.825082472361557e-05,
      "loss": 0.4617,
      "step": 44
    },
    {
      "epoch": 8.0,
      "grad_norm": 1.7452040910720825,
      "learning_rate": 9.786597487660337e-05,
      "loss": 0.4007,
      "step": 46
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.671922206878662,
      "eval_runtime": 4.8483,
      "eval_samples_per_second": 2.475,
      "eval_steps_per_second": 2.475,
      "step": 46
    },
    {
      "epoch": 8.347826086956522,
      "grad_norm": 1.627158761024475,
      "learning_rate": 9.744380058222483e-05,
      "loss": 0.2485,
      "step": 48
    },
    {
      "epoch": 8.695652173913043,
      "grad_norm": 1.4861387014389038,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.2182,
      "step": 50
    },
    {
      "epoch": 8.869565217391305,
      "eval_loss": 2.0389816761016846,
      "eval_runtime": 4.8412,
      "eval_samples_per_second": 2.479,
      "eval_steps_per_second": 2.479,
      "step": 51
    },
    {
      "epoch": 9.043478260869565,
      "grad_norm": 1.8841030597686768,
      "learning_rate": 9.648882429441257e-05,
      "loss": 0.1563,
      "step": 52
    },
    {
      "epoch": 9.391304347826088,
      "grad_norm": 2.056680917739868,
      "learning_rate": 9.595676696276172e-05,
      "loss": 0.0866,
      "step": 54
    },
    {
      "epoch": 9.73913043478261,
      "grad_norm": 2.4738428592681885,
      "learning_rate": 9.538887392664544e-05,
      "loss": 0.0802,
      "step": 56
    },
    {
      "epoch": 9.91304347826087,
      "eval_loss": 2.5002787113189697,
      "eval_runtime": 4.8542,
      "eval_samples_per_second": 2.472,
      "eval_steps_per_second": 2.472,
      "step": 57
    },
    {
      "epoch": 10.08695652173913,
      "grad_norm": 1.4879595041275024,
      "learning_rate": 9.478558801197065e-05,
      "loss": 0.0638,
      "step": 58
    },
    {
      "epoch": 10.434782608695652,
      "grad_norm": 2.2851953506469727,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.0328,
      "step": 60
    },
    {
      "epoch": 10.782608695652174,
      "grad_norm": 1.1112951040267944,
      "learning_rate": 9.347474647526095e-05,
      "loss": 0.0304,
      "step": 62
    },
    {
      "epoch": 10.956521739130435,
      "eval_loss": 2.7327919006347656,
      "eval_runtime": 4.8404,
      "eval_samples_per_second": 2.479,
      "eval_steps_per_second": 2.479,
      "step": 63
    },
    {
      "epoch": 11.130434782608695,
      "grad_norm": 1.1123360395431519,
      "learning_rate": 9.276821300802534e-05,
      "loss": 0.029,
      "step": 64
    },
    {
      "epoch": 11.478260869565217,
      "grad_norm": 1.831784963607788,
      "learning_rate": 9.202833017478422e-05,
      "loss": 0.0298,
      "step": 66
    },
    {
      "epoch": 11.826086956521738,
      "grad_norm": 1.1904350519180298,
      "learning_rate": 9.125567491391476e-05,
      "loss": 0.0155,
      "step": 68
    },
    {
      "epoch": 12.0,
      "eval_loss": 2.7460126876831055,
      "eval_runtime": 4.839,
      "eval_samples_per_second": 2.48,
      "eval_steps_per_second": 2.48,
      "step": 69
    },
    {
      "epoch": 12.0,
      "step": 69,
      "total_flos": 8262552305795072.0,
      "train_loss": 0.8597148116678,
      "train_runtime": 650.8523,
      "train_samples_per_second": 3.534,
      "train_steps_per_second": 0.384
    }
  ],
  "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": 8262552305795072.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}