last-checkpoint/trainer_state.json

{
  "best_metric": 1.2146193981170654,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.03460207612456748,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011534025374855825,
      "eval_loss": 1.332622766494751,
      "eval_runtime": 16.3496,
      "eval_samples_per_second": 22.325,
      "eval_steps_per_second": 11.193,
      "step": 1
    },
    {
      "epoch": 0.0034602076124567475,
      "grad_norm": 0.751387894153595,
      "learning_rate": 0.00012,
      "loss": 1.2534,
      "step": 3
    },
    {
      "epoch": 0.0057670126874279125,
      "eval_loss": 1.2998837232589722,
      "eval_runtime": 16.1457,
      "eval_samples_per_second": 22.607,
      "eval_steps_per_second": 11.334,
      "step": 5
    },
    {
      "epoch": 0.006920415224913495,
      "grad_norm": 0.8091318011283875,
      "learning_rate": 0.0001992114701314478,
      "loss": 1.2854,
      "step": 6
    },
    {
      "epoch": 0.010380622837370242,
      "grad_norm": 1.202852725982666,
      "learning_rate": 0.00018763066800438636,
      "loss": 1.2962,
      "step": 9
    },
    {
      "epoch": 0.011534025374855825,
      "eval_loss": 1.2497470378875732,
      "eval_runtime": 16.2508,
      "eval_samples_per_second": 22.46,
      "eval_steps_per_second": 11.261,
      "step": 10
    },
    {
      "epoch": 0.01384083044982699,
      "grad_norm": 0.845567524433136,
      "learning_rate": 0.000163742398974869,
      "loss": 1.2615,
      "step": 12
    },
    {
      "epoch": 0.01730103806228374,
      "grad_norm": 0.7856248021125793,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.2766,
      "step": 15
    },
    {
      "epoch": 0.01730103806228374,
      "eval_loss": 1.231576681137085,
      "eval_runtime": 16.2615,
      "eval_samples_per_second": 22.446,
      "eval_steps_per_second": 11.254,
      "step": 15
    },
    {
      "epoch": 0.020761245674740483,
      "grad_norm": 0.9804477691650391,
      "learning_rate": 9.372094804706867e-05,
      "loss": 1.1915,
      "step": 18
    },
    {
      "epoch": 0.02306805074971165,
      "eval_loss": 1.2197264432907104,
      "eval_runtime": 16.1202,
      "eval_samples_per_second": 22.642,
      "eval_steps_per_second": 11.352,
      "step": 20
    },
    {
      "epoch": 0.02422145328719723,
      "grad_norm": 0.7158284187316895,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 1.2062,
      "step": 21
    },
    {
      "epoch": 0.02768166089965398,
      "grad_norm": 0.8357627391815186,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 1.2136,
      "step": 24
    },
    {
      "epoch": 0.02883506343713956,
      "eval_loss": 1.215375304222107,
      "eval_runtime": 16.1664,
      "eval_samples_per_second": 22.578,
      "eval_steps_per_second": 11.32,
      "step": 25
    },
    {
      "epoch": 0.031141868512110725,
      "grad_norm": 0.78094482421875,
      "learning_rate": 7.022351411174866e-06,
      "loss": 1.2646,
      "step": 27
    },
    {
      "epoch": 0.03460207612456748,
      "grad_norm": 0.6926222443580627,
      "learning_rate": 0.0,
      "loss": 1.221,
      "step": 30
    },
    {
      "epoch": 0.03460207612456748,
      "eval_loss": 1.2146193981170654,
      "eval_runtime": 16.1371,
      "eval_samples_per_second": 22.619,
      "eval_steps_per_second": 11.34,
      "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": 1959403255234560.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}