last-checkpoint/trainer_state.json

{
  "best_metric": 2.177536964416504,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0014133776191654005,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.711258730551335e-05,
      "eval_loss": 2.3641092777252197,
      "eval_runtime": 1871.9307,
      "eval_samples_per_second": 4.775,
      "eval_steps_per_second": 2.387,
      "step": 1
    },
    {
      "epoch": 0.00014133776191654006,
      "grad_norm": 0.6187059283256531,
      "learning_rate": 6e-05,
      "loss": 2.2919,
      "step": 3
    },
    {
      "epoch": 0.00023556293652756677,
      "eval_loss": 2.2891592979431152,
      "eval_runtime": 1907.7919,
      "eval_samples_per_second": 4.685,
      "eval_steps_per_second": 2.342,
      "step": 5
    },
    {
      "epoch": 0.00028267552383308013,
      "grad_norm": 0.9118744730949402,
      "learning_rate": 9.96057350657239e-05,
      "loss": 2.2652,
      "step": 6
    },
    {
      "epoch": 0.00042401328574962014,
      "grad_norm": 0.6678541302680969,
      "learning_rate": 9.381533400219318e-05,
      "loss": 2.2276,
      "step": 9
    },
    {
      "epoch": 0.00047112587305513353,
      "eval_loss": 2.2322335243225098,
      "eval_runtime": 1912.0867,
      "eval_samples_per_second": 4.674,
      "eval_steps_per_second": 2.337,
      "step": 10
    },
    {
      "epoch": 0.0005653510476661603,
      "grad_norm": 0.5005286335945129,
      "learning_rate": 8.18711994874345e-05,
      "loss": 2.2123,
      "step": 12
    },
    {
      "epoch": 0.0007066888095827003,
      "grad_norm": 0.6007933020591736,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.231,
      "step": 15
    },
    {
      "epoch": 0.0007066888095827003,
      "eval_loss": 2.204803705215454,
      "eval_runtime": 1911.5406,
      "eval_samples_per_second": 4.676,
      "eval_steps_per_second": 2.338,
      "step": 15
    },
    {
      "epoch": 0.0008480265714992403,
      "grad_norm": 0.6446805596351624,
      "learning_rate": 4.6860474023534335e-05,
      "loss": 2.2172,
      "step": 18
    },
    {
      "epoch": 0.0009422517461102671,
      "eval_loss": 2.1887054443359375,
      "eval_runtime": 1909.8438,
      "eval_samples_per_second": 4.68,
      "eval_steps_per_second": 2.34,
      "step": 20
    },
    {
      "epoch": 0.0009893643334157804,
      "grad_norm": 0.680305540561676,
      "learning_rate": 2.8711035421746367e-05,
      "loss": 2.1851,
      "step": 21
    },
    {
      "epoch": 0.0011307020953323205,
      "grad_norm": 0.6678304076194763,
      "learning_rate": 1.3551568628929434e-05,
      "loss": 2.2019,
      "step": 24
    },
    {
      "epoch": 0.0011778146826378337,
      "eval_loss": 2.1794984340667725,
      "eval_runtime": 1908.038,
      "eval_samples_per_second": 4.684,
      "eval_steps_per_second": 2.342,
      "step": 25
    },
    {
      "epoch": 0.0012720398572488604,
      "grad_norm": 0.6334486603736877,
      "learning_rate": 3.511175705587433e-06,
      "loss": 2.149,
      "step": 27
    },
    {
      "epoch": 0.0014133776191654005,
      "grad_norm": 0.5381951928138733,
      "learning_rate": 0.0,
      "loss": 2.1624,
      "step": 30
    },
    {
      "epoch": 0.0014133776191654005,
      "eval_loss": 2.177536964416504,
      "eval_runtime": 1909.3608,
      "eval_samples_per_second": 4.681,
      "eval_steps_per_second": 2.341,
      "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": 1.1221045163851776e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}