last-checkpoint/trainer_state.json

{
  "best_metric": 1.330490231513977,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.003608805485384338,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00036088054853843375,
      "grad_norm": 3.6869497299194336,
      "learning_rate": 2e-05,
      "loss": 8.6382,
      "step": 1
    },
    {
      "epoch": 0.00036088054853843375,
      "eval_loss": 2.059074878692627,
      "eval_runtime": 280.1233,
      "eval_samples_per_second": 4.166,
      "eval_steps_per_second": 2.085,
      "step": 1
    },
    {
      "epoch": 0.0007217610970768675,
      "grad_norm": 3.044846296310425,
      "learning_rate": 4e-05,
      "loss": 7.5329,
      "step": 2
    },
    {
      "epoch": 0.0010826416456153013,
      "grad_norm": 3.2137176990509033,
      "learning_rate": 6e-05,
      "loss": 7.9115,
      "step": 3
    },
    {
      "epoch": 0.001443522194153735,
      "grad_norm": 3.5442140102386475,
      "learning_rate": 8e-05,
      "loss": 7.7322,
      "step": 4
    },
    {
      "epoch": 0.001804402742692169,
      "grad_norm": 3.074554920196533,
      "learning_rate": 0.0001,
      "loss": 7.2018,
      "step": 5
    },
    {
      "epoch": 0.001804402742692169,
      "eval_loss": 1.8853472471237183,
      "eval_runtime": 279.6366,
      "eval_samples_per_second": 4.173,
      "eval_steps_per_second": 2.088,
      "step": 5
    },
    {
      "epoch": 0.0021652832912306026,
      "grad_norm": 3.8418097496032715,
      "learning_rate": 0.00012,
      "loss": 7.5068,
      "step": 6
    },
    {
      "epoch": 0.0025261638397690365,
      "grad_norm": 4.259398460388184,
      "learning_rate": 0.00014,
      "loss": 7.5668,
      "step": 7
    },
    {
      "epoch": 0.00288704438830747,
      "grad_norm": 4.92379093170166,
      "learning_rate": 0.00016,
      "loss": 7.3567,
      "step": 8
    },
    {
      "epoch": 0.003247924936845904,
      "grad_norm": 3.6357803344726562,
      "learning_rate": 0.00018,
      "loss": 6.1502,
      "step": 9
    },
    {
      "epoch": 0.003608805485384338,
      "grad_norm": 4.020624160766602,
      "learning_rate": 0.0002,
      "loss": 5.6372,
      "step": 10
    },
    {
      "epoch": 0.003608805485384338,
      "eval_loss": 1.330490231513977,
      "eval_runtime": 278.9813,
      "eval_samples_per_second": 4.183,
      "eval_steps_per_second": 2.093,
      "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": 5705610716774400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}