last-checkpoint/trainer_state.json

{
  "best_metric": 1.2735178470611572,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.003678837487353996,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00036788374873539964,
      "grad_norm": 8.641034126281738,
      "learning_rate": 2e-05,
      "loss": 3.6742,
      "step": 1
    },
    {
      "epoch": 0.00036788374873539964,
      "eval_loss": 3.5604350566864014,
      "eval_runtime": 162.037,
      "eval_samples_per_second": 7.066,
      "eval_steps_per_second": 3.536,
      "step": 1
    },
    {
      "epoch": 0.0007357674974707993,
      "grad_norm": 6.875428676605225,
      "learning_rate": 4e-05,
      "loss": 3.3059,
      "step": 2
    },
    {
      "epoch": 0.0011036512462061989,
      "grad_norm": 7.295816898345947,
      "learning_rate": 6e-05,
      "loss": 3.3496,
      "step": 3
    },
    {
      "epoch": 0.0014715349949415985,
      "grad_norm": 6.719980716705322,
      "learning_rate": 8e-05,
      "loss": 3.6083,
      "step": 4
    },
    {
      "epoch": 0.001839418743676998,
      "grad_norm": 6.446127891540527,
      "learning_rate": 0.0001,
      "loss": 2.9195,
      "step": 5
    },
    {
      "epoch": 0.001839418743676998,
      "eval_loss": 2.9542577266693115,
      "eval_runtime": 160.8239,
      "eval_samples_per_second": 7.12,
      "eval_steps_per_second": 3.563,
      "step": 5
    },
    {
      "epoch": 0.0022073024924123977,
      "grad_norm": 6.19967794418335,
      "learning_rate": 0.00012,
      "loss": 2.6303,
      "step": 6
    },
    {
      "epoch": 0.002575186241147797,
      "grad_norm": 5.094878196716309,
      "learning_rate": 0.00014,
      "loss": 2.5328,
      "step": 7
    },
    {
      "epoch": 0.002943069989883197,
      "grad_norm": 4.440817356109619,
      "learning_rate": 0.00016,
      "loss": 2.0104,
      "step": 8
    },
    {
      "epoch": 0.0033109537386185966,
      "grad_norm": 5.241264820098877,
      "learning_rate": 0.00018,
      "loss": 1.8857,
      "step": 9
    },
    {
      "epoch": 0.003678837487353996,
      "grad_norm": 4.398327827453613,
      "learning_rate": 0.0002,
      "loss": 1.4926,
      "step": 10
    },
    {
      "epoch": 0.003678837487353996,
      "eval_loss": 1.2735178470611572,
      "eval_runtime": 156.5936,
      "eval_samples_per_second": 7.312,
      "eval_steps_per_second": 3.659,
      "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": 500097330708480.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}