last-checkpoint/trainer_state.json

{
  "best_metric": 2.940157890319824,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.0003989706557082727,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.9897065570827266e-05,
      "grad_norm": 34.571083068847656,
      "learning_rate": 2e-05,
      "loss": 13.0737,
      "step": 1
    },
    {
      "epoch": 3.9897065570827266e-05,
      "eval_loss": 13.415596008300781,
      "eval_runtime": 1769.5683,
      "eval_samples_per_second": 5.964,
      "eval_steps_per_second": 2.982,
      "step": 1
    },
    {
      "epoch": 7.979413114165453e-05,
      "grad_norm": 29.27878761291504,
      "learning_rate": 4e-05,
      "loss": 12.9275,
      "step": 2
    },
    {
      "epoch": 0.0001196911967124818,
      "grad_norm": 32.823585510253906,
      "learning_rate": 6e-05,
      "loss": 13.7609,
      "step": 3
    },
    {
      "epoch": 0.00015958826228330906,
      "grad_norm": 31.356901168823242,
      "learning_rate": 8e-05,
      "loss": 11.9954,
      "step": 4
    },
    {
      "epoch": 0.00019948532785413634,
      "grad_norm": 26.919424057006836,
      "learning_rate": 0.0001,
      "loss": 13.2038,
      "step": 5
    },
    {
      "epoch": 0.00019948532785413634,
      "eval_loss": 9.15496826171875,
      "eval_runtime": 1765.7038,
      "eval_samples_per_second": 5.977,
      "eval_steps_per_second": 2.989,
      "step": 5
    },
    {
      "epoch": 0.0002393823934249636,
      "grad_norm": 29.31121063232422,
      "learning_rate": 0.00012,
      "loss": 9.1004,
      "step": 6
    },
    {
      "epoch": 0.00027927945899579087,
      "grad_norm": 36.97990417480469,
      "learning_rate": 0.00014,
      "loss": 5.5883,
      "step": 7
    },
    {
      "epoch": 0.0003191765245666181,
      "grad_norm": 15.210268020629883,
      "learning_rate": 0.00016,
      "loss": 6.3717,
      "step": 8
    },
    {
      "epoch": 0.0003590735901374454,
      "grad_norm": 8.212323188781738,
      "learning_rate": 0.00018,
      "loss": 3.0233,
      "step": 9
    },
    {
      "epoch": 0.0003989706557082727,
      "grad_norm": 11.827737808227539,
      "learning_rate": 0.0002,
      "loss": 4.0085,
      "step": 10
    },
    {
      "epoch": 0.0003989706557082727,
      "eval_loss": 2.940157890319824,
      "eval_runtime": 1741.7012,
      "eval_samples_per_second": 6.06,
      "eval_steps_per_second": 3.03,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": 2774346372218880.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}