last-checkpoint/trainer_state.json

{
  "best_metric": 1.1946930885314941,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.0851063829787234,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00425531914893617,
      "eval_loss": 2.4387693405151367,
      "eval_runtime": 7.599,
      "eval_samples_per_second": 13.028,
      "eval_steps_per_second": 6.58,
      "step": 1
    },
    {
      "epoch": 0.01276595744680851,
      "grad_norm": 4.859747409820557,
      "learning_rate": 0.00012,
      "loss": 2.3682,
      "step": 3
    },
    {
      "epoch": 0.02127659574468085,
      "eval_loss": 1.6072040796279907,
      "eval_runtime": 7.7816,
      "eval_samples_per_second": 12.722,
      "eval_steps_per_second": 6.425,
      "step": 5
    },
    {
      "epoch": 0.02553191489361702,
      "grad_norm": 1.4412251710891724,
      "learning_rate": 0.0001992114701314478,
      "loss": 1.7322,
      "step": 6
    },
    {
      "epoch": 0.03829787234042553,
      "grad_norm": 1.558541178703308,
      "learning_rate": 0.00018763066800438636,
      "loss": 1.357,
      "step": 9
    },
    {
      "epoch": 0.0425531914893617,
      "eval_loss": 1.296438217163086,
      "eval_runtime": 7.9452,
      "eval_samples_per_second": 12.46,
      "eval_steps_per_second": 6.293,
      "step": 10
    },
    {
      "epoch": 0.05106382978723404,
      "grad_norm": 1.7230987548828125,
      "learning_rate": 0.000163742398974869,
      "loss": 1.4363,
      "step": 12
    },
    {
      "epoch": 0.06382978723404255,
      "grad_norm": 1.4550708532333374,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.3038,
      "step": 15
    },
    {
      "epoch": 0.06382978723404255,
      "eval_loss": 1.222257137298584,
      "eval_runtime": 8.1242,
      "eval_samples_per_second": 12.186,
      "eval_steps_per_second": 6.154,
      "step": 15
    },
    {
      "epoch": 0.07659574468085106,
      "grad_norm": 1.2237554788589478,
      "learning_rate": 9.372094804706867e-05,
      "loss": 1.1423,
      "step": 18
    },
    {
      "epoch": 0.0851063829787234,
      "eval_loss": 1.1946930885314941,
      "eval_runtime": 8.2924,
      "eval_samples_per_second": 11.939,
      "eval_steps_per_second": 6.03,
      "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": 2010596581048320.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}