last-checkpoint/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.16992353440951571,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006796941376380629,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.006796941376380629,
      "eval_loss": NaN,
      "eval_runtime": 25.4966,
      "eval_samples_per_second": 38.907,
      "eval_steps_per_second": 4.863,
      "step": 1
    },
    {
      "epoch": 0.013593882752761258,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.020390824129141887,
      "grad_norm": NaN,
      "learning_rate": 9.989294616193017e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.027187765505522515,
      "grad_norm": NaN,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.033984706881903144,
      "grad_norm": NaN,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.04078164825828377,
      "grad_norm": NaN,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0475785896346644,
      "grad_norm": NaN,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.05437553101104503,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.06117247238742566,
      "grad_norm": NaN,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.06796941376380629,
      "grad_norm": NaN,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.07476635514018691,
      "grad_norm": NaN,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.08156329651656755,
      "grad_norm": NaN,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.08836023789294817,
      "grad_norm": NaN,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.0951571792693288,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.10195412064570943,
      "grad_norm": NaN,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.10875106202209006,
      "grad_norm": NaN,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.11554800339847068,
      "grad_norm": NaN,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.12234494477485132,
      "grad_norm": NaN,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.12914188615123195,
      "grad_norm": NaN,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.13593882752761258,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.1427357689039932,
      "grad_norm": NaN,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.14953271028037382,
      "grad_norm": NaN,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.15632965165675447,
      "grad_norm": NaN,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.1631265930331351,
      "grad_norm": NaN,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.16992353440951571,
      "grad_norm": NaN,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.16992353440951571,
      "eval_loss": NaN,
      "eval_runtime": 25.4911,
      "eval_samples_per_second": 38.916,
      "eval_steps_per_second": 4.864,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.812028905324544e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}