last-checkpoint/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 1.8518518518518519,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07407407407407407,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.07407407407407407,
      "eval_loss": NaN,
      "eval_runtime": 1.6243,
      "eval_samples_per_second": 56.024,
      "eval_steps_per_second": 7.388,
      "step": 1
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": NaN,
      "learning_rate": 9.983786540671051e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": NaN,
      "learning_rate": 9.935251313189564e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": NaN,
      "learning_rate": 9.85470908713026e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": NaN,
      "learning_rate": 9.742682209735727e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.5185185185185185,
      "grad_norm": NaN,
      "learning_rate": 9.599897218294122e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": NaN,
      "learning_rate": 9.42728012826605e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": NaN,
      "learning_rate": 9.225950427718975e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": NaN,
      "learning_rate": 8.997213817017507e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.8148148148148148,
      "grad_norm": NaN,
      "learning_rate": 8.742553740855506e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": NaN,
      "learning_rate": 8.463621767547998e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.9629629629629629,
      "grad_norm": NaN,
      "learning_rate": 8.162226877976887e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 1.037037037037037,
      "grad_norm": NaN,
      "learning_rate": 7.840323733655778e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": NaN,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": NaN,
      "learning_rate": 7.143462807015271e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 1.2592592592592593,
      "grad_norm": NaN,
      "learning_rate": 6.773024435212678e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": NaN,
      "learning_rate": 6.391087319582264e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 1.4074074074074074,
      "grad_norm": NaN,
      "learning_rate": 6.0001284688802226e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 1.4814814814814814,
      "grad_norm": NaN,
      "learning_rate": 5.602683401276615e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 1.5555555555555556,
      "grad_norm": NaN,
      "learning_rate": 5.201329700547076e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 1.6296296296296298,
      "grad_norm": NaN,
      "learning_rate": 4.798670299452926e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 1.7037037037037037,
      "grad_norm": NaN,
      "learning_rate": 4.397316598723385e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": NaN,
      "learning_rate": 3.9998715311197785e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 1.8518518518518519,
      "grad_norm": NaN,
      "learning_rate": 3.608912680417737e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 1.8518518518518519,
      "eval_loss": NaN,
      "eval_runtime": 1.6236,
      "eval_samples_per_second": 56.048,
      "eval_steps_per_second": 7.391,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 41,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 25,
  "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": 1.114626154561536e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}