last-checkpoint/trainer_state.json

{
  "best_metric": 11.93172550201416,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.012759170653907496,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004253056884635832,
      "eval_loss": 11.931965827941895,
      "eval_runtime": 13.4867,
      "eval_samples_per_second": 73.405,
      "eval_steps_per_second": 36.703,
      "step": 1
    },
    {
      "epoch": 0.0012759170653907496,
      "grad_norm": 0.01435521524399519,
      "learning_rate": 3e-05,
      "loss": 11.932,
      "step": 3
    },
    {
      "epoch": 0.002126528442317916,
      "eval_loss": 11.931951522827148,
      "eval_runtime": 14.5596,
      "eval_samples_per_second": 67.996,
      "eval_steps_per_second": 33.998,
      "step": 5
    },
    {
      "epoch": 0.002551834130781499,
      "grad_norm": 0.01298422273248434,
      "learning_rate": 6e-05,
      "loss": 11.931,
      "step": 6
    },
    {
      "epoch": 0.003827751196172249,
      "grad_norm": 0.01278271060436964,
      "learning_rate": 9e-05,
      "loss": 11.9308,
      "step": 9
    },
    {
      "epoch": 0.004253056884635832,
      "eval_loss": 11.931888580322266,
      "eval_runtime": 14.25,
      "eval_samples_per_second": 69.474,
      "eval_steps_per_second": 34.737,
      "step": 10
    },
    {
      "epoch": 0.005103668261562998,
      "grad_norm": 0.009385287761688232,
      "learning_rate": 9.755282581475769e-05,
      "loss": 11.9327,
      "step": 12
    },
    {
      "epoch": 0.006379585326953748,
      "grad_norm": 0.01152839045971632,
      "learning_rate": 8.535533905932738e-05,
      "loss": 11.9341,
      "step": 15
    },
    {
      "epoch": 0.006379585326953748,
      "eval_loss": 11.931816101074219,
      "eval_runtime": 13.5936,
      "eval_samples_per_second": 72.829,
      "eval_steps_per_second": 36.414,
      "step": 15
    },
    {
      "epoch": 0.007655502392344498,
      "grad_norm": 0.013427882455289364,
      "learning_rate": 6.545084971874738e-05,
      "loss": 11.9304,
      "step": 18
    },
    {
      "epoch": 0.008506113769271665,
      "eval_loss": 11.931757926940918,
      "eval_runtime": 14.2756,
      "eval_samples_per_second": 69.349,
      "eval_steps_per_second": 34.675,
      "step": 20
    },
    {
      "epoch": 0.008931419457735247,
      "grad_norm": 0.009563617408275604,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 11.9308,
      "step": 21
    },
    {
      "epoch": 0.010207336523125997,
      "grad_norm": 0.01416687574237585,
      "learning_rate": 2.061073738537635e-05,
      "loss": 11.9324,
      "step": 24
    },
    {
      "epoch": 0.01063264221158958,
      "eval_loss": 11.931729316711426,
      "eval_runtime": 13.535,
      "eval_samples_per_second": 73.144,
      "eval_steps_per_second": 36.572,
      "step": 25
    },
    {
      "epoch": 0.011483253588516746,
      "grad_norm": 0.0107727674767375,
      "learning_rate": 5.449673790581611e-06,
      "loss": 11.9328,
      "step": 27
    },
    {
      "epoch": 0.012759170653907496,
      "grad_norm": 0.011838309466838837,
      "learning_rate": 0.0,
      "loss": 11.9332,
      "step": 30
    },
    {
      "epoch": 0.012759170653907496,
      "eval_loss": 11.93172550201416,
      "eval_runtime": 14.3757,
      "eval_samples_per_second": 68.866,
      "eval_steps_per_second": 34.433,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 11335729152.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}