last-checkpoint/trainer_state.json

{
  "best_metric": 1.8087369203567505,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.028421202216853774,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002842120221685377,
      "eval_loss": 2.4652628898620605,
      "eval_runtime": 82.1891,
      "eval_samples_per_second": 9.016,
      "eval_steps_per_second": 2.263,
      "step": 1
    },
    {
      "epoch": 0.002842120221685377,
      "grad_norm": 2.0982413291931152,
      "learning_rate": 4.12e-05,
      "loss": 1.8261,
      "step": 10
    },
    {
      "epoch": 0.005684240443370754,
      "grad_norm": 4.10166597366333,
      "learning_rate": 8.24e-05,
      "loss": 1.4635,
      "step": 20
    },
    {
      "epoch": 0.008526360665056132,
      "grad_norm": 1.6615333557128906,
      "learning_rate": 0.0001236,
      "loss": 1.667,
      "step": 30
    },
    {
      "epoch": 0.011368480886741509,
      "grad_norm": 1.931045651435852,
      "learning_rate": 0.0001648,
      "loss": 1.5695,
      "step": 40
    },
    {
      "epoch": 0.014210601108426887,
      "grad_norm": 1.6880329847335815,
      "learning_rate": 0.000206,
      "loss": 1.8497,
      "step": 50
    },
    {
      "epoch": 0.014210601108426887,
      "eval_loss": 1.8087369203567505,
      "eval_runtime": 81.6706,
      "eval_samples_per_second": 9.073,
      "eval_steps_per_second": 2.277,
      "step": 50
    },
    {
      "epoch": 0.017052721330112264,
      "grad_norm": 3.674773931503296,
      "learning_rate": 0.0002057490971767619,
      "loss": 1.7821,
      "step": 60
    },
    {
      "epoch": 0.019894841551797642,
      "grad_norm": 3.0321569442749023,
      "learning_rate": 0.00020499761108038175,
      "loss": 1.6055,
      "step": 70
    },
    {
      "epoch": 0.022736961773483017,
      "grad_norm": 2.507596254348755,
      "learning_rate": 0.00020374920287558198,
      "loss": 1.3591,
      "step": 80
    },
    {
      "epoch": 0.025579081995168396,
      "grad_norm": 8.490031242370605,
      "learning_rate": 0.00020200995468164684,
      "loss": 1.2845,
      "step": 90
    },
    {
      "epoch": 0.028421202216853774,
      "grad_norm": 42.760581970214844,
      "learning_rate": 0.00019978833994094855,
      "loss": 1.8626,
      "step": 100
    },
    {
      "epoch": 0.028421202216853774,
      "eval_loss": 2.087491750717163,
      "eval_runtime": 81.5271,
      "eval_samples_per_second": 9.089,
      "eval_steps_per_second": 2.281,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.7577745273847808e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}