last-checkpoint/trainer_state.json

{
  "best_metric": 0.9329267144203186,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0299625468164794,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009987515605493133,
      "eval_loss": 1.3787546157836914,
      "eval_runtime": 48.8757,
      "eval_samples_per_second": 8.634,
      "eval_steps_per_second": 4.317,
      "step": 1
    },
    {
      "epoch": 0.00299625468164794,
      "grad_norm": 0.5186976194381714,
      "learning_rate": 0.00012,
      "loss": 1.3718,
      "step": 3
    },
    {
      "epoch": 0.004993757802746567,
      "eval_loss": 1.2428629398345947,
      "eval_runtime": 49.6346,
      "eval_samples_per_second": 8.502,
      "eval_steps_per_second": 4.251,
      "step": 5
    },
    {
      "epoch": 0.00599250936329588,
      "grad_norm": 1.1188064813613892,
      "learning_rate": 0.0001992114701314478,
      "loss": 1.2362,
      "step": 6
    },
    {
      "epoch": 0.008988764044943821,
      "grad_norm": 0.6766451597213745,
      "learning_rate": 0.00018763066800438636,
      "loss": 1.1053,
      "step": 9
    },
    {
      "epoch": 0.009987515605493134,
      "eval_loss": 0.9852341413497925,
      "eval_runtime": 49.7858,
      "eval_samples_per_second": 8.476,
      "eval_steps_per_second": 4.238,
      "step": 10
    },
    {
      "epoch": 0.01198501872659176,
      "grad_norm": 0.5351176857948303,
      "learning_rate": 0.000163742398974869,
      "loss": 0.9607,
      "step": 12
    },
    {
      "epoch": 0.0149812734082397,
      "grad_norm": 0.5625289082527161,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.9699,
      "step": 15
    },
    {
      "epoch": 0.0149812734082397,
      "eval_loss": 0.9624225497245789,
      "eval_runtime": 49.8125,
      "eval_samples_per_second": 8.472,
      "eval_steps_per_second": 4.236,
      "step": 15
    },
    {
      "epoch": 0.017977528089887642,
      "grad_norm": 0.4904978573322296,
      "learning_rate": 9.372094804706867e-05,
      "loss": 0.9741,
      "step": 18
    },
    {
      "epoch": 0.019975031210986267,
      "eval_loss": 0.9407100677490234,
      "eval_runtime": 49.819,
      "eval_samples_per_second": 8.471,
      "eval_steps_per_second": 4.235,
      "step": 20
    },
    {
      "epoch": 0.020973782771535582,
      "grad_norm": 0.4452764391899109,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 0.9141,
      "step": 21
    },
    {
      "epoch": 0.02397003745318352,
      "grad_norm": 0.5386295318603516,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 0.9,
      "step": 24
    },
    {
      "epoch": 0.024968789013732832,
      "eval_loss": 0.9346191883087158,
      "eval_runtime": 49.834,
      "eval_samples_per_second": 8.468,
      "eval_steps_per_second": 4.234,
      "step": 25
    },
    {
      "epoch": 0.02696629213483146,
      "grad_norm": 0.48347967863082886,
      "learning_rate": 7.022351411174866e-06,
      "loss": 0.96,
      "step": 27
    },
    {
      "epoch": 0.0299625468164794,
      "grad_norm": 0.4335913062095642,
      "learning_rate": 0.0,
      "loss": 0.9135,
      "step": 30
    },
    {
      "epoch": 0.0299625468164794,
      "eval_loss": 0.9329267144203186,
      "eval_runtime": 49.8408,
      "eval_samples_per_second": 8.467,
      "eval_steps_per_second": 4.233,
      "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": 4939038012211200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}