last-checkpoint/trainer_state.json

{
  "best_metric": 2.0806500911712646,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0006418450906873626,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.139483635624542e-05,
      "eval_loss": 3.7263901233673096,
      "eval_runtime": 5024.784,
      "eval_samples_per_second": 3.917,
      "eval_steps_per_second": 1.958,
      "step": 1
    },
    {
      "epoch": 6.418450906873626e-05,
      "grad_norm": 4.048289775848389,
      "learning_rate": 6e-05,
      "loss": 3.7554,
      "step": 3
    },
    {
      "epoch": 0.0001069741817812271,
      "eval_loss": 3.1972880363464355,
      "eval_runtime": 5049.6965,
      "eval_samples_per_second": 3.897,
      "eval_steps_per_second": 1.949,
      "step": 5
    },
    {
      "epoch": 0.0001283690181374725,
      "grad_norm": 3.210604190826416,
      "learning_rate": 9.96057350657239e-05,
      "loss": 3.5514,
      "step": 6
    },
    {
      "epoch": 0.0001925535272062088,
      "grad_norm": 3.702566385269165,
      "learning_rate": 9.381533400219318e-05,
      "loss": 2.9402,
      "step": 9
    },
    {
      "epoch": 0.0002139483635624542,
      "eval_loss": 2.4024550914764404,
      "eval_runtime": 5048.6525,
      "eval_samples_per_second": 3.898,
      "eval_steps_per_second": 1.949,
      "step": 10
    },
    {
      "epoch": 0.000256738036274945,
      "grad_norm": 2.3049252033233643,
      "learning_rate": 8.18711994874345e-05,
      "loss": 2.5073,
      "step": 12
    },
    {
      "epoch": 0.0003209225453436813,
      "grad_norm": 2.5028700828552246,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.2915,
      "step": 15
    },
    {
      "epoch": 0.0003209225453436813,
      "eval_loss": 2.176945924758911,
      "eval_runtime": 5038.5523,
      "eval_samples_per_second": 3.906,
      "eval_steps_per_second": 1.953,
      "step": 15
    },
    {
      "epoch": 0.0003851070544124176,
      "grad_norm": 2.0715272426605225,
      "learning_rate": 4.6860474023534335e-05,
      "loss": 2.2345,
      "step": 18
    },
    {
      "epoch": 0.0004278967271249084,
      "eval_loss": 2.105510950088501,
      "eval_runtime": 5039.1582,
      "eval_samples_per_second": 3.906,
      "eval_steps_per_second": 1.953,
      "step": 20
    },
    {
      "epoch": 0.0004492915634811538,
      "grad_norm": 2.413928270339966,
      "learning_rate": 2.8711035421746367e-05,
      "loss": 2.1637,
      "step": 21
    },
    {
      "epoch": 0.00051347607254989,
      "grad_norm": 2.0797808170318604,
      "learning_rate": 1.3551568628929434e-05,
      "loss": 2.0466,
      "step": 24
    },
    {
      "epoch": 0.0005348709089061355,
      "eval_loss": 2.0851852893829346,
      "eval_runtime": 5039.8201,
      "eval_samples_per_second": 3.905,
      "eval_steps_per_second": 1.953,
      "step": 25
    },
    {
      "epoch": 0.0005776605816186263,
      "grad_norm": 2.0577657222747803,
      "learning_rate": 3.511175705587433e-06,
      "loss": 2.0755,
      "step": 27
    },
    {
      "epoch": 0.0006418450906873626,
      "grad_norm": 2.2678091526031494,
      "learning_rate": 0.0,
      "loss": 1.8957,
      "step": 30
    },
    {
      "epoch": 0.0006418450906873626,
      "eval_loss": 2.0806500911712646,
      "eval_runtime": 5054.3412,
      "eval_samples_per_second": 3.894,
      "eval_steps_per_second": 1.947,
      "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": 2.225661850681344e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}