last-checkpoint/trainer_state.json

{
  "best_metric": 1.3310236930847168,
  "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": 1.8467991352081299,
      "eval_runtime": 1847.6296,
      "eval_samples_per_second": 8.437,
      "eval_steps_per_second": 0.264,
      "step": 1
    },
    {
      "epoch": 0.0027010236879777437,
      "grad_norm": 0.796185314655304,
      "learning_rate": 0.000201,
      "loss": 1.3322,
      "step": 50
    },
    {
      "epoch": 0.0027010236879777437,
      "eval_loss": 1.3517159223556519,
      "eval_runtime": 1842.6641,
      "eval_samples_per_second": 8.46,
      "eval_steps_per_second": 0.265,
      "step": 50
    },
    {
      "epoch": 0.005402047375955487,
      "grad_norm": 0.8316030502319336,
      "learning_rate": 0.000201,
      "loss": 1.2478,
      "step": 100
    },
    {
      "epoch": 0.005402047375955487,
      "eval_loss": 1.3310236930847168,
      "eval_runtime": 1844.5642,
      "eval_samples_per_second": 8.451,
      "eval_steps_per_second": 0.265,
      "step": 100
    },
    {
      "epoch": 0.00810307106393323,
      "grad_norm": 1.0529603958129883,
      "learning_rate": 0.000201,
      "loss": 1.2689,
      "step": 150
    },
    {
      "epoch": 0.00810307106393323,
      "eval_loss": 1.3370928764343262,
      "eval_runtime": 1845.2096,
      "eval_samples_per_second": 8.448,
      "eval_steps_per_second": 0.264,
      "step": 150
    },
    {
      "epoch": 0.010804094751910975,
      "grad_norm": 1.1472487449645996,
      "learning_rate": 0.000201,
      "loss": 1.3044,
      "step": 200
    },
    {
      "epoch": 0.010804094751910975,
      "eval_loss": 1.34417724609375,
      "eval_runtime": 1843.9296,
      "eval_samples_per_second": 8.454,
      "eval_steps_per_second": 0.265,
      "step": 200
    },
    {
      "epoch": 0.013505118439888717,
      "grad_norm": 1.0352643728256226,
      "learning_rate": 0.000201,
      "loss": 1.3059,
      "step": 250
    },
    {
      "epoch": 0.013505118439888717,
      "eval_loss": 1.3383946418762207,
      "eval_runtime": 1848.8241,
      "eval_samples_per_second": 8.432,
      "eval_steps_per_second": 0.264,
      "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
}