last-checkpoint/trainer_state.json

{
  "best_metric": 2.0030875205993652,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.02577873254564984,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008592910848549946,
      "eval_loss": 2.2387137413024902,
      "eval_runtime": 6.0356,
      "eval_samples_per_second": 81.184,
      "eval_steps_per_second": 40.592,
      "step": 1
    },
    {
      "epoch": 0.0025778732545649837,
      "grad_norm": 3.6572017669677734,
      "learning_rate": 0.00012,
      "loss": 9.4828,
      "step": 3
    },
    {
      "epoch": 0.004296455424274973,
      "eval_loss": 2.1862692832946777,
      "eval_runtime": 5.1444,
      "eval_samples_per_second": 95.25,
      "eval_steps_per_second": 47.625,
      "step": 5
    },
    {
      "epoch": 0.0051557465091299675,
      "grad_norm": 2.9871788024902344,
      "learning_rate": 0.0001992114701314478,
      "loss": 9.1289,
      "step": 6
    },
    {
      "epoch": 0.007733619763694952,
      "grad_norm": 3.6695291996002197,
      "learning_rate": 0.00018763066800438636,
      "loss": 8.9151,
      "step": 9
    },
    {
      "epoch": 0.008592910848549946,
      "eval_loss": 2.104604721069336,
      "eval_runtime": 5.1536,
      "eval_samples_per_second": 95.079,
      "eval_steps_per_second": 47.54,
      "step": 10
    },
    {
      "epoch": 0.010311493018259935,
      "grad_norm": 3.9996907711029053,
      "learning_rate": 0.000163742398974869,
      "loss": 8.8568,
      "step": 12
    },
    {
      "epoch": 0.01288936627282492,
      "grad_norm": 3.884136438369751,
      "learning_rate": 0.00013090169943749476,
      "loss": 8.6792,
      "step": 15
    },
    {
      "epoch": 0.01288936627282492,
      "eval_loss": 2.04828143119812,
      "eval_runtime": 5.29,
      "eval_samples_per_second": 92.627,
      "eval_steps_per_second": 46.314,
      "step": 15
    },
    {
      "epoch": 0.015467239527389903,
      "grad_norm": 3.819817066192627,
      "learning_rate": 9.372094804706867e-05,
      "loss": 8.3578,
      "step": 18
    },
    {
      "epoch": 0.017185821697099892,
      "eval_loss": 2.018906354904175,
      "eval_runtime": 5.137,
      "eval_samples_per_second": 95.387,
      "eval_steps_per_second": 47.693,
      "step": 20
    },
    {
      "epoch": 0.01804511278195489,
      "grad_norm": 3.4456512928009033,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 7.9461,
      "step": 21
    },
    {
      "epoch": 0.02062298603651987,
      "grad_norm": 3.77186918258667,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 8.3606,
      "step": 24
    },
    {
      "epoch": 0.021482277121374866,
      "eval_loss": 2.0057647228240967,
      "eval_runtime": 5.2572,
      "eval_samples_per_second": 93.205,
      "eval_steps_per_second": 46.602,
      "step": 25
    },
    {
      "epoch": 0.023200859291084855,
      "grad_norm": 3.1643145084381104,
      "learning_rate": 7.022351411174866e-06,
      "loss": 8.425,
      "step": 27
    },
    {
      "epoch": 0.02577873254564984,
      "grad_norm": 3.8465747833251953,
      "learning_rate": 0.0,
      "loss": 8.1357,
      "step": 30
    },
    {
      "epoch": 0.02577873254564984,
      "eval_loss": 2.0030875205993652,
      "eval_runtime": 5.1722,
      "eval_samples_per_second": 94.738,
      "eval_steps_per_second": 47.369,
      "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": 137956228595712.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}