last-checkpoint/trainer_state.json

{
  "best_metric": 0.5909367203712463,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.0023559901048415596,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00023559901048415596,
      "grad_norm": 0.3784501254558563,
      "learning_rate": 2e-05,
      "loss": 0.6132,
      "step": 1
    },
    {
      "epoch": 0.00023559901048415596,
      "eval_loss": 0.6598115563392639,
      "eval_runtime": 432.1218,
      "eval_samples_per_second": 4.138,
      "eval_steps_per_second": 2.069,
      "step": 1
    },
    {
      "epoch": 0.0004711980209683119,
      "grad_norm": 0.3668363094329834,
      "learning_rate": 4e-05,
      "loss": 0.6555,
      "step": 2
    },
    {
      "epoch": 0.0007067970314524679,
      "grad_norm": 0.5077784657478333,
      "learning_rate": 6e-05,
      "loss": 0.6326,
      "step": 3
    },
    {
      "epoch": 0.0009423960419366238,
      "grad_norm": 0.4163624048233032,
      "learning_rate": 8e-05,
      "loss": 0.7083,
      "step": 4
    },
    {
      "epoch": 0.0011779950524207798,
      "grad_norm": 0.4140971601009369,
      "learning_rate": 0.0001,
      "loss": 0.6878,
      "step": 5
    },
    {
      "epoch": 0.0011779950524207798,
      "eval_loss": 0.6515950560569763,
      "eval_runtime": 426.6242,
      "eval_samples_per_second": 4.191,
      "eval_steps_per_second": 2.096,
      "step": 5
    },
    {
      "epoch": 0.0014135940629049358,
      "grad_norm": 0.47956836223602295,
      "learning_rate": 0.00012,
      "loss": 0.6468,
      "step": 6
    },
    {
      "epoch": 0.0016491930733890919,
      "grad_norm": 0.4840953052043915,
      "learning_rate": 0.00014,
      "loss": 0.6795,
      "step": 7
    },
    {
      "epoch": 0.0018847920838732477,
      "grad_norm": 0.4249662458896637,
      "learning_rate": 0.00016,
      "loss": 0.5602,
      "step": 8
    },
    {
      "epoch": 0.0021203910943574035,
      "grad_norm": 0.4048328399658203,
      "learning_rate": 0.00018,
      "loss": 0.7123,
      "step": 9
    },
    {
      "epoch": 0.0023559901048415596,
      "grad_norm": 0.38470837473869324,
      "learning_rate": 0.0002,
      "loss": 0.6979,
      "step": 10
    },
    {
      "epoch": 0.0023559901048415596,
      "eval_loss": 0.5909367203712463,
      "eval_runtime": 435.8721,
      "eval_samples_per_second": 4.102,
      "eval_steps_per_second": 2.051,
      "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": 3699130509557760.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}