{
  "best_metric": 1.3398202657699585,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0017435778216901082,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.81192607230036e-05,
      "eval_loss": 2.2182366847991943,
      "eval_runtime": 237.8317,
      "eval_samples_per_second": 60.925,
      "eval_steps_per_second": 15.233,
      "step": 1
    },
    {
      "epoch": 0.0001743577821690108,
      "grad_norm": 2.076202392578125,
      "learning_rate": 0.00012,
      "loss": 6.6136,
      "step": 3
    },
    {
      "epoch": 0.000290596303615018,
      "eval_loss": 2.0416693687438965,
      "eval_runtime": 236.0224,
      "eval_samples_per_second": 61.392,
      "eval_steps_per_second": 15.35,
      "step": 5
    },
    {
      "epoch": 0.0003487155643380216,
      "grad_norm": 2.1901042461395264,
      "learning_rate": 0.0001992114701314478,
      "loss": 7.04,
      "step": 6
    },
    {
      "epoch": 0.0005230733465070325,
      "grad_norm": 2.604962110519409,
      "learning_rate": 0.00018763066800438636,
      "loss": 7.2788,
      "step": 9
    },
    {
      "epoch": 0.000581192607230036,
      "eval_loss": 1.7173281908035278,
      "eval_runtime": 235.5597,
      "eval_samples_per_second": 61.513,
      "eval_steps_per_second": 15.38,
      "step": 10
    },
    {
      "epoch": 0.0006974311286760432,
      "grad_norm": 2.9086358547210693,
      "learning_rate": 0.000163742398974869,
      "loss": 6.7148,
      "step": 12
    },
    {
      "epoch": 0.0008717889108450541,
      "grad_norm": 3.048389196395874,
      "learning_rate": 0.00013090169943749476,
      "loss": 6.5216,
      "step": 15
    },
    {
      "epoch": 0.0008717889108450541,
      "eval_loss": 1.4961720705032349,
      "eval_runtime": 235.7834,
      "eval_samples_per_second": 61.455,
      "eval_steps_per_second": 15.366,
      "step": 15
    },
    {
      "epoch": 0.001046146693014065,
      "grad_norm": 3.2019808292388916,
      "learning_rate": 9.372094804706867e-05,
      "loss": 6.2214,
      "step": 18
    },
    {
      "epoch": 0.001162385214460072,
      "eval_loss": 1.386073112487793,
      "eval_runtime": 235.5561,
      "eval_samples_per_second": 61.514,
      "eval_steps_per_second": 15.381,
      "step": 20
    },
    {
      "epoch": 0.0012205044751830757,
      "grad_norm": 2.8324685096740723,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 6.3543,
      "step": 21
    },
    {
      "epoch": 0.0013948622573520864,
      "grad_norm": 2.5789592266082764,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 6.0648,
      "step": 24
    },
    {
      "epoch": 0.00145298151807509,
      "eval_loss": 1.346395492553711,
      "eval_runtime": 235.7083,
      "eval_samples_per_second": 61.474,
      "eval_steps_per_second": 15.371,
      "step": 25
    },
    {
      "epoch": 0.0015692200395210972,
      "grad_norm": 2.725504159927368,
      "learning_rate": 7.022351411174866e-06,
      "loss": 5.876,
      "step": 27
    },
    {
      "epoch": 0.0017435778216901082,
      "grad_norm": 2.9919424057006836,
      "learning_rate": 0.0,
      "loss": 6.0495,
      "step": 30
    },
    {
      "epoch": 0.0017435778216901082,
      "eval_loss": 1.3398202657699585,
      "eval_runtime": 235.2336,
      "eval_samples_per_second": 61.598,
      "eval_steps_per_second": 15.402,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": 3756313804800000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}