last-checkpoint/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 3.0684931506849313,
  "eval_steps": 25,
  "global_step": 28,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1095890410958904,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.1095890410958904,
      "eval_loss": NaN,
      "eval_runtime": 3.6233,
      "eval_samples_per_second": 13.8,
      "eval_steps_per_second": 3.588,
      "step": 1
    },
    {
      "epoch": 0.2191780821917808,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.3287671232876712,
      "grad_norm": NaN,
      "learning_rate": 9.967189933441243e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.4383561643835616,
      "grad_norm": NaN,
      "learning_rate": 9.869238178417235e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.547945205479452,
      "grad_norm": NaN,
      "learning_rate": 9.707573092084368e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.6575342465753424,
      "grad_norm": NaN,
      "learning_rate": 9.484552115439445e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.7671232876712328,
      "grad_norm": NaN,
      "learning_rate": 9.203427396521454e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.8767123287671232,
      "grad_norm": NaN,
      "learning_rate": 8.868298366769954e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.9863013698630136,
      "grad_norm": NaN,
      "learning_rate": 8.484051962083579e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 1.095890410958904,
      "grad_norm": NaN,
      "learning_rate": 8.056291360290201e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 1.2054794520547945,
      "grad_norm": NaN,
      "learning_rate": 7.591254274196959e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 1.3150684931506849,
      "grad_norm": NaN,
      "learning_rate": 7.095721991691411e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 1.4246575342465753,
      "grad_norm": NaN,
      "learning_rate": 6.576920489294011e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 1.5342465753424657,
      "grad_norm": NaN,
      "learning_rate": 6.042415061148954e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 1.643835616438356,
      "grad_norm": NaN,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 1.7534246575342465,
      "grad_norm": NaN,
      "learning_rate": 4.9575849388510473e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 1.8630136986301369,
      "grad_norm": NaN,
      "learning_rate": 4.423079510705992e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 1.9726027397260273,
      "grad_norm": NaN,
      "learning_rate": 3.904278008308589e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 2.0821917808219177,
      "grad_norm": NaN,
      "learning_rate": 3.408745725803042e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 2.191780821917808,
      "grad_norm": NaN,
      "learning_rate": 2.9437086397097995e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 2.3013698630136985,
      "grad_norm": NaN,
      "learning_rate": 2.515948037916423e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 2.410958904109589,
      "grad_norm": NaN,
      "learning_rate": 2.1317016332300447e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 2.5205479452054793,
      "grad_norm": NaN,
      "learning_rate": 1.7965726034785466e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 2.6301369863013697,
      "grad_norm": NaN,
      "learning_rate": 1.515447884560556e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 2.73972602739726,
      "grad_norm": NaN,
      "learning_rate": 1.292426907915634e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 2.73972602739726,
      "eval_loss": NaN,
      "eval_runtime": 3.2321,
      "eval_samples_per_second": 15.47,
      "eval_steps_per_second": 4.022,
      "step": 25
    },
    {
      "epoch": 2.8493150684931505,
      "grad_norm": NaN,
      "learning_rate": 1.130761821582766e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 2.958904109589041,
      "grad_norm": NaN,
      "learning_rate": 1.0328100665587574e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 3.0684931506849313,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 28
    }
  ],
  "logging_steps": 1,
  "max_steps": 28,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.342126825697444e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}