{
  "best_metric": 1.5732864141464233,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.1059322033898305,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00423728813559322,
      "grad_norm": 0.27673590183258057,
      "learning_rate": 2e-05,
      "loss": 1.7047,
      "step": 1
    },
    {
      "epoch": 0.00423728813559322,
      "eval_loss": 1.764668583869934,
      "eval_runtime": 16.5519,
      "eval_samples_per_second": 6.042,
      "eval_steps_per_second": 3.021,
      "step": 1
    },
    {
      "epoch": 0.00847457627118644,
      "grad_norm": 0.49966296553611755,
      "learning_rate": 4e-05,
      "loss": 1.7618,
      "step": 2
    },
    {
      "epoch": 0.012711864406779662,
      "grad_norm": 0.2676803171634674,
      "learning_rate": 6e-05,
      "loss": 1.7926,
      "step": 3
    },
    {
      "epoch": 0.01694915254237288,
      "grad_norm": 0.4576026201248169,
      "learning_rate": 8e-05,
      "loss": 1.7089,
      "step": 4
    },
    {
      "epoch": 0.0211864406779661,
      "grad_norm": 0.3100014328956604,
      "learning_rate": 0.0001,
      "loss": 1.839,
      "step": 5
    },
    {
      "epoch": 0.0211864406779661,
      "eval_loss": 1.7582393884658813,
      "eval_runtime": 15.6777,
      "eval_samples_per_second": 6.378,
      "eval_steps_per_second": 3.189,
      "step": 5
    },
    {
      "epoch": 0.025423728813559324,
      "grad_norm": 0.7545116543769836,
      "learning_rate": 0.00012,
      "loss": 1.7292,
      "step": 6
    },
    {
      "epoch": 0.029661016949152543,
      "grad_norm": 0.3743640184402466,
      "learning_rate": 0.00014,
      "loss": 2.0527,
      "step": 7
    },
    {
      "epoch": 0.03389830508474576,
      "grad_norm": 0.43906688690185547,
      "learning_rate": 0.00016,
      "loss": 1.9522,
      "step": 8
    },
    {
      "epoch": 0.038135593220338986,
      "grad_norm": 0.3741382956504822,
      "learning_rate": 0.00018,
      "loss": 1.9569,
      "step": 9
    },
    {
      "epoch": 0.0423728813559322,
      "grad_norm": 0.5588337779045105,
      "learning_rate": 0.0002,
      "loss": 1.6476,
      "step": 10
    },
    {
      "epoch": 0.0423728813559322,
      "eval_loss": 1.6932556629180908,
      "eval_runtime": 15.5438,
      "eval_samples_per_second": 6.433,
      "eval_steps_per_second": 3.217,
      "step": 10
    },
    {
      "epoch": 0.046610169491525424,
      "grad_norm": 0.4901130199432373,
      "learning_rate": 0.00019781476007338058,
      "loss": 1.9861,
      "step": 11
    },
    {
      "epoch": 0.05084745762711865,
      "grad_norm": 0.5694382786750793,
      "learning_rate": 0.0001913545457642601,
      "loss": 1.5954,
      "step": 12
    },
    {
      "epoch": 0.05508474576271186,
      "grad_norm": 0.4953717291355133,
      "learning_rate": 0.00018090169943749476,
      "loss": 2.0111,
      "step": 13
    },
    {
      "epoch": 0.059322033898305086,
      "grad_norm": 0.7269114851951599,
      "learning_rate": 0.00016691306063588583,
      "loss": 1.484,
      "step": 14
    },
    {
      "epoch": 0.0635593220338983,
      "grad_norm": 0.9006850123405457,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.7068,
      "step": 15
    },
    {
      "epoch": 0.0635593220338983,
      "eval_loss": 1.6160073280334473,
      "eval_runtime": 15.5466,
      "eval_samples_per_second": 6.432,
      "eval_steps_per_second": 3.216,
      "step": 15
    },
    {
      "epoch": 0.06779661016949153,
      "grad_norm": 0.6504830121994019,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.9114,
      "step": 16
    },
    {
      "epoch": 0.07203389830508475,
      "grad_norm": 0.4439529776573181,
      "learning_rate": 0.00011045284632676536,
      "loss": 1.7195,
      "step": 17
    },
    {
      "epoch": 0.07627118644067797,
      "grad_norm": 0.44182923436164856,
      "learning_rate": 8.954715367323468e-05,
      "loss": 1.6958,
      "step": 18
    },
    {
      "epoch": 0.08050847457627118,
      "grad_norm": 0.5301311612129211,
      "learning_rate": 6.909830056250527e-05,
      "loss": 1.5541,
      "step": 19
    },
    {
      "epoch": 0.0847457627118644,
      "grad_norm": 0.5610678791999817,
      "learning_rate": 5.000000000000002e-05,
      "loss": 1.1802,
      "step": 20
    },
    {
      "epoch": 0.0847457627118644,
      "eval_loss": 1.577897310256958,
      "eval_runtime": 15.5103,
      "eval_samples_per_second": 6.447,
      "eval_steps_per_second": 3.224,
      "step": 20
    },
    {
      "epoch": 0.08898305084745763,
      "grad_norm": 0.3756644129753113,
      "learning_rate": 3.308693936411421e-05,
      "loss": 1.1892,
      "step": 21
    },
    {
      "epoch": 0.09322033898305085,
      "grad_norm": 0.47590842843055725,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 1.6276,
      "step": 22
    },
    {
      "epoch": 0.09745762711864407,
      "grad_norm": 0.4191993474960327,
      "learning_rate": 8.645454235739903e-06,
      "loss": 1.4896,
      "step": 23
    },
    {
      "epoch": 0.1016949152542373,
      "grad_norm": 0.5012941956520081,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 1.8067,
      "step": 24
    },
    {
      "epoch": 0.1059322033898305,
      "grad_norm": 0.6124191880226135,
      "learning_rate": 0.0,
      "loss": 1.536,
      "step": 25
    },
    {
      "epoch": 0.1059322033898305,
      "eval_loss": 1.5732864141464233,
      "eval_runtime": 15.5251,
      "eval_samples_per_second": 6.441,
      "eval_steps_per_second": 3.221,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": 6055749243371520.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}