last-checkpoint/trainer_state.json

{
  "best_metric": 1.3348661661148071,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.013505118439888717,
  "eval_steps": 50,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.402047375955487e-05,
      "eval_loss": 1.846793293952942,
      "eval_runtime": 1840.3648,
      "eval_samples_per_second": 8.471,
      "eval_steps_per_second": 0.265,
      "step": 1
    },
    {
      "epoch": 0.0027010236879777437,
      "grad_norm": 1.2499018907546997,
      "learning_rate": 0.000202,
      "loss": 1.3341,
      "step": 50
    },
    {
      "epoch": 0.0027010236879777437,
      "eval_loss": 1.375239372253418,
      "eval_runtime": 1835.2681,
      "eval_samples_per_second": 8.494,
      "eval_steps_per_second": 0.266,
      "step": 50
    },
    {
      "epoch": 0.005402047375955487,
      "grad_norm": 0.8809305429458618,
      "learning_rate": 0.000202,
      "loss": 1.2536,
      "step": 100
    },
    {
      "epoch": 0.005402047375955487,
      "eval_loss": 1.3348661661148071,
      "eval_runtime": 1837.2507,
      "eval_samples_per_second": 8.485,
      "eval_steps_per_second": 0.266,
      "step": 100
    },
    {
      "epoch": 0.00810307106393323,
      "grad_norm": 1.2271238565444946,
      "learning_rate": 0.000202,
      "loss": 1.2749,
      "step": 150
    },
    {
      "epoch": 0.00810307106393323,
      "eval_loss": 1.344261884689331,
      "eval_runtime": 1837.1269,
      "eval_samples_per_second": 8.486,
      "eval_steps_per_second": 0.266,
      "step": 150
    },
    {
      "epoch": 0.010804094751910975,
      "grad_norm": 1.0673139095306396,
      "learning_rate": 0.000202,
      "loss": 1.303,
      "step": 200
    },
    {
      "epoch": 0.010804094751910975,
      "eval_loss": 1.3638064861297607,
      "eval_runtime": 1834.8855,
      "eval_samples_per_second": 8.496,
      "eval_steps_per_second": 0.266,
      "step": 200
    },
    {
      "epoch": 0.013505118439888717,
      "grad_norm": 1.301340103149414,
      "learning_rate": 0.000202,
      "loss": 1.3134,
      "step": 250
    },
    {
      "epoch": 0.013505118439888717,
      "eval_loss": 1.3406997919082642,
      "eval_runtime": 1839.6086,
      "eval_samples_per_second": 8.474,
      "eval_steps_per_second": 0.265,
      "step": 250
    }
  ],
  "logging_steps": 50,
  "max_steps": 400,
  "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": 3
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.15902737924096e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}