last-checkpoint/trainer_state.json

{
  "best_metric": 1.2455830574035645,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.01697792869269949,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016977928692699492,
      "eval_loss": 1.4329637289047241,
      "eval_runtime": 234.9554,
      "eval_samples_per_second": 5.278,
      "eval_steps_per_second": 1.319,
      "step": 1
    },
    {
      "epoch": 0.001697792869269949,
      "grad_norm": 1.341242790222168,
      "learning_rate": 4.12e-05,
      "loss": 1.4209,
      "step": 10
    },
    {
      "epoch": 0.003395585738539898,
      "grad_norm": 0.7306675910949707,
      "learning_rate": 8.24e-05,
      "loss": 1.338,
      "step": 20
    },
    {
      "epoch": 0.0050933786078098476,
      "grad_norm": 0.7428624629974365,
      "learning_rate": 0.0001236,
      "loss": 1.2576,
      "step": 30
    },
    {
      "epoch": 0.006791171477079796,
      "grad_norm": 0.7021359205245972,
      "learning_rate": 0.0001648,
      "loss": 1.2015,
      "step": 40
    },
    {
      "epoch": 0.008488964346349746,
      "grad_norm": 0.8103872537612915,
      "learning_rate": 0.000206,
      "loss": 1.2281,
      "step": 50
    },
    {
      "epoch": 0.008488964346349746,
      "eval_loss": 1.2455830574035645,
      "eval_runtime": 237.2217,
      "eval_samples_per_second": 5.227,
      "eval_steps_per_second": 1.307,
      "step": 50
    },
    {
      "epoch": 0.010186757215619695,
      "grad_norm": 0.7842703461647034,
      "learning_rate": 0.0002057490971767619,
      "loss": 1.2212,
      "step": 60
    },
    {
      "epoch": 0.011884550084889643,
      "grad_norm": 0.8670001029968262,
      "learning_rate": 0.00020499761108038175,
      "loss": 1.2051,
      "step": 70
    },
    {
      "epoch": 0.013582342954159592,
      "grad_norm": 0.8176340460777283,
      "learning_rate": 0.00020374920287558198,
      "loss": 1.209,
      "step": 80
    },
    {
      "epoch": 0.015280135823429542,
      "grad_norm": 1.0117417573928833,
      "learning_rate": 0.00020200995468164684,
      "loss": 1.2546,
      "step": 90
    },
    {
      "epoch": 0.01697792869269949,
      "grad_norm": 1.4239269495010376,
      "learning_rate": 0.00019978833994094855,
      "loss": 1.3016,
      "step": 100
    },
    {
      "epoch": 0.01697792869269949,
      "eval_loss": 1.3394960165023804,
      "eval_runtime": 236.5162,
      "eval_samples_per_second": 5.243,
      "eval_steps_per_second": 1.311,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.193703014544179e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}