last-checkpoint/trainer_state.json

{
  "best_metric": 2.0486538410186768,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.11461318051575932,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0038204393505253103,
      "eval_loss": 2.355255603790283,
      "eval_runtime": 86.6983,
      "eval_samples_per_second": 2.549,
      "eval_steps_per_second": 0.646,
      "step": 1
    },
    {
      "epoch": 0.011461318051575931,
      "grad_norm": 0.22021570801734924,
      "learning_rate": 0.00012,
      "loss": 2.3681,
      "step": 3
    },
    {
      "epoch": 0.019102196752626553,
      "eval_loss": 2.2745025157928467,
      "eval_runtime": 87.0605,
      "eval_samples_per_second": 2.538,
      "eval_steps_per_second": 0.643,
      "step": 5
    },
    {
      "epoch": 0.022922636103151862,
      "grad_norm": 0.3847930133342743,
      "learning_rate": 0.0001992114701314478,
      "loss": 2.2964,
      "step": 6
    },
    {
      "epoch": 0.034383954154727794,
      "grad_norm": 0.19991150498390198,
      "learning_rate": 0.00018763066800438636,
      "loss": 2.2225,
      "step": 9
    },
    {
      "epoch": 0.038204393505253106,
      "eval_loss": 2.1533548831939697,
      "eval_runtime": 86.9934,
      "eval_samples_per_second": 2.54,
      "eval_steps_per_second": 0.644,
      "step": 10
    },
    {
      "epoch": 0.045845272206303724,
      "grad_norm": 0.16003547608852386,
      "learning_rate": 0.000163742398974869,
      "loss": 2.1493,
      "step": 12
    },
    {
      "epoch": 0.05730659025787966,
      "grad_norm": 0.17825794219970703,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.1093,
      "step": 15
    },
    {
      "epoch": 0.05730659025787966,
      "eval_loss": 2.093752861022949,
      "eval_runtime": 86.9783,
      "eval_samples_per_second": 2.541,
      "eval_steps_per_second": 0.644,
      "step": 15
    },
    {
      "epoch": 0.06876790830945559,
      "grad_norm": 0.15024003386497498,
      "learning_rate": 9.372094804706867e-05,
      "loss": 2.1147,
      "step": 18
    },
    {
      "epoch": 0.07640878701050621,
      "eval_loss": 2.0634360313415527,
      "eval_runtime": 86.9622,
      "eval_samples_per_second": 2.541,
      "eval_steps_per_second": 0.644,
      "step": 20
    },
    {
      "epoch": 0.08022922636103152,
      "grad_norm": 0.1427949070930481,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 2.0835,
      "step": 21
    },
    {
      "epoch": 0.09169054441260745,
      "grad_norm": 0.13537243008613586,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 2.08,
      "step": 24
    },
    {
      "epoch": 0.09551098376313276,
      "eval_loss": 2.051386833190918,
      "eval_runtime": 86.9123,
      "eval_samples_per_second": 2.543,
      "eval_steps_per_second": 0.644,
      "step": 25
    },
    {
      "epoch": 0.10315186246418338,
      "grad_norm": 0.13574567437171936,
      "learning_rate": 7.022351411174866e-06,
      "loss": 2.1146,
      "step": 27
    },
    {
      "epoch": 0.11461318051575932,
      "grad_norm": 0.13817577064037323,
      "learning_rate": 0.0,
      "loss": 2.023,
      "step": 30
    },
    {
      "epoch": 0.11461318051575932,
      "eval_loss": 2.0486538410186768,
      "eval_runtime": 86.9329,
      "eval_samples_per_second": 2.542,
      "eval_steps_per_second": 0.644,
      "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": 7.6173476364288e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}