{
  "best_metric": 0.6529822945594788,
  "best_model_checkpoint": "miner_id_24/checkpoint-250",
  "epoch": 0.5004468275245755,
  "eval_steps": 50,
  "global_step": 280,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0017873100983020554,
      "eval_loss": 3.3430755138397217,
      "eval_runtime": 20.397,
      "eval_samples_per_second": 5.785,
      "eval_steps_per_second": 1.471,
      "step": 1
    },
    {
      "epoch": 0.017873100983020553,
      "grad_norm": 14.790982246398926,
      "learning_rate": 4.16e-05,
      "loss": 5.5737,
      "step": 10
    },
    {
      "epoch": 0.035746201966041107,
      "grad_norm": 8.204423904418945,
      "learning_rate": 8.32e-05,
      "loss": 4.7228,
      "step": 20
    },
    {
      "epoch": 0.05361930294906166,
      "grad_norm": 9.69465160369873,
      "learning_rate": 0.0001248,
      "loss": 3.5246,
      "step": 30
    },
    {
      "epoch": 0.07149240393208221,
      "grad_norm": 5.571041584014893,
      "learning_rate": 0.0001664,
      "loss": 1.8915,
      "step": 40
    },
    {
      "epoch": 0.08936550491510277,
      "grad_norm": 8.176162719726562,
      "learning_rate": 0.000208,
      "loss": 1.5708,
      "step": 50
    },
    {
      "epoch": 0.08936550491510277,
      "eval_loss": 1.4437922239303589,
      "eval_runtime": 20.4976,
      "eval_samples_per_second": 5.757,
      "eval_steps_per_second": 1.464,
      "step": 50
    },
    {
      "epoch": 0.10723860589812333,
      "grad_norm": 12.052813529968262,
      "learning_rate": 0.00020703133838777837,
      "loss": 0.9903,
      "step": 60
    },
    {
      "epoch": 0.12511170688114387,
      "grad_norm": 9.54784107208252,
      "learning_rate": 0.0002041433978841711,
      "loss": 1.9003,
      "step": 70
    },
    {
      "epoch": 0.14298480786416443,
      "grad_norm": 5.111771583557129,
      "learning_rate": 0.00019938997535656712,
      "loss": 2.2635,
      "step": 80
    },
    {
      "epoch": 0.16085790884718498,
      "grad_norm": 11.855950355529785,
      "learning_rate": 0.0001928596180728348,
      "loss": 1.8408,
      "step": 90
    },
    {
      "epoch": 0.17873100983020554,
      "grad_norm": 7.051792621612549,
      "learning_rate": 0.00018467397423325966,
      "loss": 2.8008,
      "step": 100
    },
    {
      "epoch": 0.17873100983020554,
      "eval_loss": 1.326716423034668,
      "eval_runtime": 20.4346,
      "eval_samples_per_second": 5.775,
      "eval_steps_per_second": 1.468,
      "step": 100
    },
    {
      "epoch": 0.1966041108132261,
      "grad_norm": 4.326223373413086,
      "learning_rate": 0.00017498552689474003,
      "loss": 2.2905,
      "step": 110
    },
    {
      "epoch": 0.21447721179624665,
      "grad_norm": 3.754796266555786,
      "learning_rate": 0.0001639747534999462,
      "loss": 1.6449,
      "step": 120
    },
    {
      "epoch": 0.2323503127792672,
      "grad_norm": 3.4767560958862305,
      "learning_rate": 0.00015184676392403983,
      "loss": 1.7208,
      "step": 130
    },
    {
      "epoch": 0.25022341376228774,
      "grad_norm": 14.138089179992676,
      "learning_rate": 0.00013882747966578255,
      "loss": 2.1643,
      "step": 140
    },
    {
      "epoch": 0.2680965147453083,
      "grad_norm": 7.055633544921875,
      "learning_rate": 0.00012515942535747392,
      "loss": 1.2235,
      "step": 150
    },
    {
      "epoch": 0.2680965147453083,
      "eval_loss": 0.9262405037879944,
      "eval_runtime": 20.4014,
      "eval_samples_per_second": 5.784,
      "eval_steps_per_second": 1.47,
      "step": 150
    },
    {
      "epoch": 0.28596961572832885,
      "grad_norm": 4.541979789733887,
      "learning_rate": 0.00011109721098992579,
      "loss": 1.3878,
      "step": 160
    },
    {
      "epoch": 0.30384271671134944,
      "grad_norm": 9.299073219299316,
      "learning_rate": 9.690278901007422e-05,
      "loss": 2.0393,
      "step": 170
    },
    {
      "epoch": 0.32171581769436997,
      "grad_norm": 4.212630748748779,
      "learning_rate": 8.28405746425261e-05,
      "loss": 1.6107,
      "step": 180
    },
    {
      "epoch": 0.33958891867739055,
      "grad_norm": 4.568448066711426,
      "learning_rate": 6.917252033421744e-05,
      "loss": 1.2569,
      "step": 190
    },
    {
      "epoch": 0.3574620196604111,
      "grad_norm": 7.974542617797852,
      "learning_rate": 5.6153236075960175e-05,
      "loss": 1.4066,
      "step": 200
    },
    {
      "epoch": 0.3574620196604111,
      "eval_loss": 0.7788324356079102,
      "eval_runtime": 20.4254,
      "eval_samples_per_second": 5.777,
      "eval_steps_per_second": 1.469,
      "step": 200
    },
    {
      "epoch": 0.3753351206434316,
      "grad_norm": 3.5257070064544678,
      "learning_rate": 4.402524650005382e-05,
      "loss": 2.5386,
      "step": 210
    },
    {
      "epoch": 0.3932082216264522,
      "grad_norm": 3.2501423358917236,
      "learning_rate": 3.301447310525999e-05,
      "loss": 1.6518,
      "step": 220
    },
    {
      "epoch": 0.4110813226094727,
      "grad_norm": 4.823462009429932,
      "learning_rate": 2.3326025766740328e-05,
      "loss": 1.6046,
      "step": 230
    },
    {
      "epoch": 0.4289544235924933,
      "grad_norm": 4.6733598709106445,
      "learning_rate": 1.5140381927165188e-05,
      "loss": 1.5009,
      "step": 240
    },
    {
      "epoch": 0.44682752457551383,
      "grad_norm": 4.058295249938965,
      "learning_rate": 8.610024643432906e-06,
      "loss": 1.4336,
      "step": 250
    },
    {
      "epoch": 0.44682752457551383,
      "eval_loss": 0.6529822945594788,
      "eval_runtime": 20.8809,
      "eval_samples_per_second": 5.651,
      "eval_steps_per_second": 1.437,
      "step": 250
    },
    {
      "epoch": 0.4647006255585344,
      "grad_norm": 2.818467140197754,
      "learning_rate": 3.85660211582889e-06,
      "loss": 0.8045,
      "step": 260
    },
    {
      "epoch": 0.48257372654155495,
      "grad_norm": 1.863735556602478,
      "learning_rate": 9.686616122216014e-07,
      "loss": 1.3993,
      "step": 270
    },
    {
      "epoch": 0.5004468275245755,
      "grad_norm": 3.8920769691467285,
      "learning_rate": 0.0,
      "loss": 1.767,
      "step": 280
    }
  ],
  "logging_steps": 10,
  "max_steps": 280,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": 7.671790653407232e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}