last-checkpoint/trainer_state.json

{
  "best_metric": 0.3486693203449249,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.00751597143930853,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003757985719654265,
      "eval_loss": 0.5640259981155396,
      "eval_runtime": 256.133,
      "eval_samples_per_second": 4.377,
      "eval_steps_per_second": 2.19,
      "step": 1
    },
    {
      "epoch": 0.0011273957158962795,
      "grad_norm": 0.699572741985321,
      "learning_rate": 0.00012,
      "loss": 0.4837,
      "step": 3
    },
    {
      "epoch": 0.0018789928598271326,
      "eval_loss": 0.4370155930519104,
      "eval_runtime": 257.9937,
      "eval_samples_per_second": 4.345,
      "eval_steps_per_second": 2.174,
      "step": 5
    },
    {
      "epoch": 0.002254791431792559,
      "grad_norm": 0.46814200282096863,
      "learning_rate": 0.0001992114701314478,
      "loss": 0.4558,
      "step": 6
    },
    {
      "epoch": 0.0033821871476888386,
      "grad_norm": 0.3834305703639984,
      "learning_rate": 0.00018763066800438636,
      "loss": 0.3557,
      "step": 9
    },
    {
      "epoch": 0.003757985719654265,
      "eval_loss": 0.372182160615921,
      "eval_runtime": 258.0673,
      "eval_samples_per_second": 4.344,
      "eval_steps_per_second": 2.174,
      "step": 10
    },
    {
      "epoch": 0.004509582863585118,
      "grad_norm": 0.4100714325904846,
      "learning_rate": 0.000163742398974869,
      "loss": 0.4093,
      "step": 12
    },
    {
      "epoch": 0.005636978579481398,
      "grad_norm": 0.3543630540370941,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.3956,
      "step": 15
    },
    {
      "epoch": 0.005636978579481398,
      "eval_loss": 0.35663875937461853,
      "eval_runtime": 258.0391,
      "eval_samples_per_second": 4.344,
      "eval_steps_per_second": 2.174,
      "step": 15
    },
    {
      "epoch": 0.006764374295377677,
      "grad_norm": 0.3837605118751526,
      "learning_rate": 9.372094804706867e-05,
      "loss": 0.3204,
      "step": 18
    },
    {
      "epoch": 0.00751597143930853,
      "eval_loss": 0.3486693203449249,
      "eval_runtime": 258.2364,
      "eval_samples_per_second": 4.341,
      "eval_steps_per_second": 2.172,
      "step": 20
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9368592665542656.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}