last-checkpoint/trainer_state.json

{
  "best_metric": 1.560912847518921,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.0859106529209622,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000859106529209622,
      "eval_loss": 2.452996253967285,
      "eval_runtime": 40.3135,
      "eval_samples_per_second": 12.155,
      "eval_steps_per_second": 3.051,
      "step": 1
    },
    {
      "epoch": 0.00859106529209622,
      "grad_norm": 3.6383719444274902,
      "learning_rate": 5.05e-06,
      "loss": 2.3216,
      "step": 10
    },
    {
      "epoch": 0.01718213058419244,
      "grad_norm": 1.7264111042022705,
      "learning_rate": 1.01e-05,
      "loss": 2.1091,
      "step": 20
    },
    {
      "epoch": 0.02577319587628866,
      "grad_norm": 0.6366956233978271,
      "learning_rate": 9.323076923076924e-06,
      "loss": 1.7,
      "step": 30
    },
    {
      "epoch": 0.03436426116838488,
      "grad_norm": 0.8026286959648132,
      "learning_rate": 8.546153846153847e-06,
      "loss": 1.6107,
      "step": 40
    },
    {
      "epoch": 0.0429553264604811,
      "grad_norm": 1.2900722026824951,
      "learning_rate": 7.76923076923077e-06,
      "loss": 1.7347,
      "step": 50
    },
    {
      "epoch": 0.0429553264604811,
      "eval_loss": 1.6046526432037354,
      "eval_runtime": 38.9755,
      "eval_samples_per_second": 12.572,
      "eval_steps_per_second": 3.156,
      "step": 50
    },
    {
      "epoch": 0.05154639175257732,
      "grad_norm": 0.4915436804294586,
      "learning_rate": 6.992307692307692e-06,
      "loss": 1.5171,
      "step": 60
    },
    {
      "epoch": 0.06013745704467354,
      "grad_norm": 0.4138346016407013,
      "learning_rate": 6.215384615384615e-06,
      "loss": 1.5871,
      "step": 70
    },
    {
      "epoch": 0.06872852233676977,
      "grad_norm": 0.5473077297210693,
      "learning_rate": 5.438461538461538e-06,
      "loss": 1.557,
      "step": 80
    },
    {
      "epoch": 0.07731958762886598,
      "grad_norm": 0.7715198397636414,
      "learning_rate": 4.661538461538462e-06,
      "loss": 1.5657,
      "step": 90
    },
    {
      "epoch": 0.0859106529209622,
      "grad_norm": 1.106988787651062,
      "learning_rate": 3.884615384615385e-06,
      "loss": 1.6544,
      "step": 100
    },
    {
      "epoch": 0.0859106529209622,
      "eval_loss": 1.560912847518921,
      "eval_runtime": 38.5363,
      "eval_samples_per_second": 12.715,
      "eval_steps_per_second": 3.192,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 150,
  "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": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.9793401356288e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}