last-checkpoint/trainer_state.json

{
  "best_metric": 2.6543691158294678,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.024106066693451184,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008035355564483728,
      "eval_loss": 7.053991794586182,
      "eval_runtime": 33.5181,
      "eval_samples_per_second": 15.633,
      "eval_steps_per_second": 7.817,
      "step": 1
    },
    {
      "epoch": 0.0024106066693451184,
      "grad_norm": 8.473215103149414,
      "learning_rate": 0.00012,
      "loss": 7.0802,
      "step": 3
    },
    {
      "epoch": 0.004017677782241864,
      "eval_loss": 5.087779998779297,
      "eval_runtime": 33.5195,
      "eval_samples_per_second": 15.633,
      "eval_steps_per_second": 7.816,
      "step": 5
    },
    {
      "epoch": 0.004821213338690237,
      "grad_norm": 7.567628860473633,
      "learning_rate": 0.0001992114701314478,
      "loss": 5.3814,
      "step": 6
    },
    {
      "epoch": 0.007231820008035355,
      "grad_norm": 10.147040367126465,
      "learning_rate": 0.00018763066800438636,
      "loss": 3.9045,
      "step": 9
    },
    {
      "epoch": 0.008035355564483728,
      "eval_loss": 3.009207010269165,
      "eval_runtime": 33.6027,
      "eval_samples_per_second": 15.594,
      "eval_steps_per_second": 7.797,
      "step": 10
    },
    {
      "epoch": 0.009642426677380474,
      "grad_norm": 2.42024302482605,
      "learning_rate": 0.000163742398974869,
      "loss": 2.8922,
      "step": 12
    },
    {
      "epoch": 0.012053033346725592,
      "grad_norm": 1.6962127685546875,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.8453,
      "step": 15
    },
    {
      "epoch": 0.012053033346725592,
      "eval_loss": 2.7773540019989014,
      "eval_runtime": 33.7032,
      "eval_samples_per_second": 15.547,
      "eval_steps_per_second": 7.774,
      "step": 15
    },
    {
      "epoch": 0.01446364001607071,
      "grad_norm": 2.6688599586486816,
      "learning_rate": 9.372094804706867e-05,
      "loss": 2.7708,
      "step": 18
    },
    {
      "epoch": 0.016070711128967456,
      "eval_loss": 2.6902265548706055,
      "eval_runtime": 33.5796,
      "eval_samples_per_second": 15.605,
      "eval_steps_per_second": 7.802,
      "step": 20
    },
    {
      "epoch": 0.01687424668541583,
      "grad_norm": 2.4370040893554688,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 2.7871,
      "step": 21
    },
    {
      "epoch": 0.019284853354760947,
      "grad_norm": 2.2035434246063232,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 2.7107,
      "step": 24
    },
    {
      "epoch": 0.020088388911209322,
      "eval_loss": 2.6591219902038574,
      "eval_runtime": 33.7978,
      "eval_samples_per_second": 15.504,
      "eval_steps_per_second": 7.752,
      "step": 25
    },
    {
      "epoch": 0.021695460024106068,
      "grad_norm": 1.9634120464324951,
      "learning_rate": 7.022351411174866e-06,
      "loss": 2.728,
      "step": 27
    },
    {
      "epoch": 0.024106066693451184,
      "grad_norm": 1.874236822128296,
      "learning_rate": 0.0,
      "loss": 2.611,
      "step": 30
    },
    {
      "epoch": 0.024106066693451184,
      "eval_loss": 2.6543691158294678,
      "eval_runtime": 33.6148,
      "eval_samples_per_second": 15.588,
      "eval_steps_per_second": 7.794,
      "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": 1.150341542313984e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}