{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.211864406779661,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00423728813559322,
      "grad_norm": 142.89096069335938,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 23.6038,
      "step": 1
    },
    {
      "epoch": 0.00423728813559322,
      "eval_loss": NaN,
      "eval_runtime": 4.2712,
      "eval_samples_per_second": 11.706,
      "eval_steps_per_second": 1.639,
      "step": 1
    },
    {
      "epoch": 0.00847457627118644,
      "grad_norm": 208.2849578857422,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 35.8788,
      "step": 2
    },
    {
      "epoch": 0.012711864406779662,
      "grad_norm": 237.0756072998047,
      "learning_rate": 8.999999999999999e-05,
      "loss": 10.4007,
      "step": 3
    },
    {
      "epoch": 0.01694915254237288,
      "grad_norm": NaN,
      "learning_rate": 0.00011999999999999999,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0211864406779661,
      "grad_norm": NaN,
      "learning_rate": 0.00015,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.025423728813559324,
      "grad_norm": NaN,
      "learning_rate": 0.00017999999999999998,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.029661016949152543,
      "grad_norm": NaN,
      "learning_rate": 0.00020999999999999998,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.03389830508474576,
      "grad_norm": NaN,
      "learning_rate": 0.00023999999999999998,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.038135593220338986,
      "grad_norm": NaN,
      "learning_rate": 0.00027,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0423728813559322,
      "grad_norm": NaN,
      "learning_rate": 0.0003,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.046610169491525424,
      "grad_norm": NaN,
      "learning_rate": 0.0002999794957488703,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.05084745762711865,
      "grad_norm": NaN,
      "learning_rate": 0.0002999179886011389,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.05508474576271186,
      "grad_norm": NaN,
      "learning_rate": 0.0002998154953722457,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.059322033898305086,
      "grad_norm": NaN,
      "learning_rate": 0.00029967204408281613,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.0635593220338983,
      "grad_norm": NaN,
      "learning_rate": 0.00029948767395100045,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.06779661016949153,
      "grad_norm": NaN,
      "learning_rate": 0.0002992624353817517,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.07203389830508475,
      "grad_norm": NaN,
      "learning_rate": 0.0002989963899530457,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.07627118644067797,
      "grad_norm": NaN,
      "learning_rate": 0.00029868961039904624,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.08050847457627118,
      "grad_norm": NaN,
      "learning_rate": 0.00029834218059022024,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.0847457627118644,
      "grad_norm": NaN,
      "learning_rate": 0.00029795419551040833,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.08898305084745763,
      "grad_norm": NaN,
      "learning_rate": 0.00029752576123085736,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.09322033898305085,
      "grad_norm": NaN,
      "learning_rate": 0.0002970569948812214,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.09745762711864407,
      "grad_norm": NaN,
      "learning_rate": 0.0002965480246175399,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.1016949152542373,
      "grad_norm": NaN,
      "learning_rate": 0.0002959989895872009,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.1059322033898305,
      "grad_norm": NaN,
      "learning_rate": 0.0002954100398908995,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.1059322033898305,
      "eval_loss": NaN,
      "eval_runtime": 3.7633,
      "eval_samples_per_second": 13.286,
      "eval_steps_per_second": 1.86,
      "step": 25
    },
    {
      "epoch": 0.11016949152542373,
      "grad_norm": NaN,
      "learning_rate": 0.0002947813365416023,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.11440677966101695,
      "grad_norm": NaN,
      "learning_rate": 0.0002941130514205272,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.11864406779661017,
      "grad_norm": NaN,
      "learning_rate": 0.0002934053672301536,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.1228813559322034,
      "grad_norm": NaN,
      "learning_rate": 0.00029265847744427303,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.1271186440677966,
      "grad_norm": NaN,
      "learning_rate": 0.00029187258625509513,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.13135593220338984,
      "grad_norm": NaN,
      "learning_rate": 0.00029104790851742417,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.13559322033898305,
      "grad_norm": NaN,
      "learning_rate": 0.0002901846696899191,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.13983050847457626,
      "grad_norm": NaN,
      "learning_rate": 0.00028928310577345606,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.1440677966101695,
      "grad_norm": NaN,
      "learning_rate": 0.0002883434632466077,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.1483050847457627,
      "grad_norm": NaN,
      "learning_rate": 0.00028736599899825856,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.15254237288135594,
      "grad_norm": NaN,
      "learning_rate": 0.00028635098025737434,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.15677966101694915,
      "grad_norm": NaN,
      "learning_rate": 0.00028529868451994384,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.16101694915254236,
      "grad_norm": NaN,
      "learning_rate": 0.0002842093994731145,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.1652542372881356,
      "grad_norm": NaN,
      "learning_rate": 0.00028308342291654174,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.1694915254237288,
      "grad_norm": NaN,
      "learning_rate": 0.00028192106268097334,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.17372881355932204,
      "grad_norm": NaN,
      "learning_rate": 0.00028072263654409154,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.17796610169491525,
      "grad_norm": NaN,
      "learning_rate": 0.0002794884721436361,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.18220338983050846,
      "grad_norm": NaN,
      "learning_rate": 0.00027821890688783083,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.1864406779661017,
      "grad_norm": NaN,
      "learning_rate": 0.0002769142878631403,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.1906779661016949,
      "grad_norm": NaN,
      "learning_rate": 0.00027557497173937923,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.19491525423728814,
      "grad_norm": NaN,
      "learning_rate": 0.000274201324672203,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.19915254237288135,
      "grad_norm": NaN,
      "learning_rate": 0.00027279372220300385,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.2033898305084746,
      "grad_norm": NaN,
      "learning_rate": 0.0002713525491562421,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.2076271186440678,
      "grad_norm": NaN,
      "learning_rate": 0.00026987819953423867,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.211864406779661,
      "grad_norm": NaN,
      "learning_rate": 0.00026837107640945905,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.211864406779661,
      "eval_loss": NaN,
      "eval_runtime": 3.761,
      "eval_samples_per_second": 13.294,
      "eval_steps_per_second": 1.861,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.47075947986944e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}