last-checkpoint/trainer_state.json

{
  "best_metric": 1.6414285898208618,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.05364327223960662,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001788109074653554,
      "eval_loss": 2.64847469329834,
      "eval_runtime": 22.0136,
      "eval_samples_per_second": 10.721,
      "eval_steps_per_second": 5.36,
      "step": 1
    },
    {
      "epoch": 0.005364327223960662,
      "grad_norm": 3.505396842956543,
      "learning_rate": 6e-05,
      "loss": 10.5576,
      "step": 3
    },
    {
      "epoch": 0.008940545373267769,
      "eval_loss": 2.574577808380127,
      "eval_runtime": 22.2405,
      "eval_samples_per_second": 10.611,
      "eval_steps_per_second": 5.306,
      "step": 5
    },
    {
      "epoch": 0.010728654447921324,
      "grad_norm": 4.872518062591553,
      "learning_rate": 0.00012,
      "loss": 10.941,
      "step": 6
    },
    {
      "epoch": 0.016092981671881983,
      "grad_norm": 4.743135452270508,
      "learning_rate": 0.00018,
      "loss": 8.6214,
      "step": 9
    },
    {
      "epoch": 0.017881090746535537,
      "eval_loss": 1.9574334621429443,
      "eval_runtime": 22.3329,
      "eval_samples_per_second": 10.567,
      "eval_steps_per_second": 5.284,
      "step": 10
    },
    {
      "epoch": 0.021457308895842648,
      "grad_norm": 7.875356674194336,
      "learning_rate": 0.00019510565162951537,
      "loss": 7.8164,
      "step": 12
    },
    {
      "epoch": 0.02682163611980331,
      "grad_norm": 6.834690570831299,
      "learning_rate": 0.00017071067811865476,
      "loss": 7.7133,
      "step": 15
    },
    {
      "epoch": 0.02682163611980331,
      "eval_loss": 1.80838942527771,
      "eval_runtime": 22.3548,
      "eval_samples_per_second": 10.557,
      "eval_steps_per_second": 5.279,
      "step": 15
    },
    {
      "epoch": 0.03218596334376397,
      "grad_norm": 7.706214904785156,
      "learning_rate": 0.00013090169943749476,
      "loss": 7.4598,
      "step": 18
    },
    {
      "epoch": 0.035762181493071074,
      "eval_loss": 1.6834994554519653,
      "eval_runtime": 22.3956,
      "eval_samples_per_second": 10.538,
      "eval_steps_per_second": 5.269,
      "step": 20
    },
    {
      "epoch": 0.03755029056772463,
      "grad_norm": 4.207357883453369,
      "learning_rate": 8.435655349597689e-05,
      "loss": 6.9531,
      "step": 21
    },
    {
      "epoch": 0.042914617791685296,
      "grad_norm": 6.524333953857422,
      "learning_rate": 4.12214747707527e-05,
      "loss": 6.6744,
      "step": 24
    },
    {
      "epoch": 0.044702726866338846,
      "eval_loss": 1.6509045362472534,
      "eval_runtime": 22.4185,
      "eval_samples_per_second": 10.527,
      "eval_steps_per_second": 5.264,
      "step": 25
    },
    {
      "epoch": 0.048278945015645953,
      "grad_norm": 5.440735816955566,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 6.4247,
      "step": 27
    },
    {
      "epoch": 0.05364327223960662,
      "grad_norm": 6.279931545257568,
      "learning_rate": 0.0,
      "loss": 6.1608,
      "step": 30
    },
    {
      "epoch": 0.05364327223960662,
      "eval_loss": 1.6414285898208618,
      "eval_runtime": 22.4499,
      "eval_samples_per_second": 10.512,
      "eval_steps_per_second": 5.256,
      "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": 8811139795968000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}