last-checkpoint/trainer_state.json

{
  "best_metric": 1.1645457744598389,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.010217113665389528,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00034057045551298427,
      "eval_loss": 1.4796533584594727,
      "eval_runtime": 164.2532,
      "eval_samples_per_second": 7.531,
      "eval_steps_per_second": 3.769,
      "step": 1
    },
    {
      "epoch": 0.0010217113665389529,
      "grad_norm": 0.384747713804245,
      "learning_rate": 6e-05,
      "loss": 1.3415,
      "step": 3
    },
    {
      "epoch": 0.0017028522775649213,
      "eval_loss": 1.4507091045379639,
      "eval_runtime": 165.8491,
      "eval_samples_per_second": 7.459,
      "eval_steps_per_second": 3.732,
      "step": 5
    },
    {
      "epoch": 0.0020434227330779057,
      "grad_norm": 0.5841999053955078,
      "learning_rate": 0.00012,
      "loss": 1.2883,
      "step": 6
    },
    {
      "epoch": 0.0030651340996168583,
      "grad_norm": 0.470478892326355,
      "learning_rate": 0.00018,
      "loss": 1.2974,
      "step": 9
    },
    {
      "epoch": 0.0034057045551298426,
      "eval_loss": 1.2941644191741943,
      "eval_runtime": 165.8717,
      "eval_samples_per_second": 7.458,
      "eval_steps_per_second": 3.732,
      "step": 10
    },
    {
      "epoch": 0.004086845466155811,
      "grad_norm": 0.5516128540039062,
      "learning_rate": 0.00019510565162951537,
      "loss": 1.2105,
      "step": 12
    },
    {
      "epoch": 0.005108556832694764,
      "grad_norm": 0.6083524227142334,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.3534,
      "step": 15
    },
    {
      "epoch": 0.005108556832694764,
      "eval_loss": 1.2232894897460938,
      "eval_runtime": 165.8974,
      "eval_samples_per_second": 7.456,
      "eval_steps_per_second": 3.731,
      "step": 15
    },
    {
      "epoch": 0.006130268199233717,
      "grad_norm": 0.38056692481040955,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.1349,
      "step": 18
    },
    {
      "epoch": 0.006811409110259685,
      "eval_loss": 1.1814048290252686,
      "eval_runtime": 165.895,
      "eval_samples_per_second": 7.457,
      "eval_steps_per_second": 3.731,
      "step": 20
    },
    {
      "epoch": 0.007151979565772669,
      "grad_norm": 0.46628570556640625,
      "learning_rate": 8.435655349597689e-05,
      "loss": 1.0381,
      "step": 21
    },
    {
      "epoch": 0.008173690932311623,
      "grad_norm": 0.3525000810623169,
      "learning_rate": 4.12214747707527e-05,
      "loss": 1.003,
      "step": 24
    },
    {
      "epoch": 0.008514261387824606,
      "eval_loss": 1.1674165725708008,
      "eval_runtime": 165.9767,
      "eval_samples_per_second": 7.453,
      "eval_steps_per_second": 3.729,
      "step": 25
    },
    {
      "epoch": 0.009195402298850575,
      "grad_norm": 0.39437252283096313,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 1.1823,
      "step": 27
    },
    {
      "epoch": 0.010217113665389528,
      "grad_norm": 0.30337342619895935,
      "learning_rate": 0.0,
      "loss": 0.9293,
      "step": 30
    },
    {
      "epoch": 0.010217113665389528,
      "eval_loss": 1.1645457744598389,
      "eval_runtime": 165.9841,
      "eval_samples_per_second": 7.453,
      "eval_steps_per_second": 3.729,
      "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": 1.123859998703616e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}