last-checkpoint/trainer_state.json

{
  "best_metric": 0.38599851727485657,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.018484288354898338,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0018484288354898336,
      "grad_norm": 7.424246311187744,
      "learning_rate": 2e-05,
      "loss": 2.2815,
      "step": 1
    },
    {
      "epoch": 0.0018484288354898336,
      "eval_loss": 0.5765224099159241,
      "eval_runtime": 174.6364,
      "eval_samples_per_second": 1.306,
      "eval_steps_per_second": 0.653,
      "step": 1
    },
    {
      "epoch": 0.0036968576709796672,
      "grad_norm": 8.377918243408203,
      "learning_rate": 4e-05,
      "loss": 2.6385,
      "step": 2
    },
    {
      "epoch": 0.005545286506469501,
      "grad_norm": 6.679048538208008,
      "learning_rate": 6e-05,
      "loss": 2.1105,
      "step": 3
    },
    {
      "epoch": 0.0073937153419593345,
      "grad_norm": 6.829878807067871,
      "learning_rate": 8e-05,
      "loss": 1.7918,
      "step": 4
    },
    {
      "epoch": 0.009242144177449169,
      "grad_norm": 6.1202802658081055,
      "learning_rate": 0.0001,
      "loss": 1.5985,
      "step": 5
    },
    {
      "epoch": 0.009242144177449169,
      "eval_loss": 0.44307413697242737,
      "eval_runtime": 175.5501,
      "eval_samples_per_second": 1.299,
      "eval_steps_per_second": 0.649,
      "step": 5
    },
    {
      "epoch": 0.011090573012939002,
      "grad_norm": 6.970052719116211,
      "learning_rate": 0.00012,
      "loss": 2.1845,
      "step": 6
    },
    {
      "epoch": 0.012939001848428836,
      "grad_norm": 3.6210474967956543,
      "learning_rate": 0.00014,
      "loss": 1.6165,
      "step": 7
    },
    {
      "epoch": 0.014787430683918669,
      "grad_norm": 5.715263366699219,
      "learning_rate": 0.00016,
      "loss": 1.592,
      "step": 8
    },
    {
      "epoch": 0.0166358595194085,
      "grad_norm": 4.726752281188965,
      "learning_rate": 0.00018,
      "loss": 1.8184,
      "step": 9
    },
    {
      "epoch": 0.018484288354898338,
      "grad_norm": 3.724501609802246,
      "learning_rate": 0.0002,
      "loss": 1.2781,
      "step": 10
    },
    {
      "epoch": 0.018484288354898338,
      "eval_loss": 0.38599851727485657,
      "eval_runtime": 174.0489,
      "eval_samples_per_second": 1.31,
      "eval_steps_per_second": 0.655,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 500,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.414506945183744e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}