last-checkpoint/trainer_state.json

{
  "best_metric": 0.9353803992271423,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.2803738317757009,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009345794392523364,
      "eval_loss": 2.1153156757354736,
      "eval_runtime": 3.3554,
      "eval_samples_per_second": 26.822,
      "eval_steps_per_second": 6.855,
      "step": 1
    },
    {
      "epoch": 0.028037383177570093,
      "grad_norm": 4.232261657714844,
      "learning_rate": 0.00012,
      "loss": 1.1125,
      "step": 3
    },
    {
      "epoch": 0.04672897196261682,
      "eval_loss": 1.4172121286392212,
      "eval_runtime": 3.3594,
      "eval_samples_per_second": 26.79,
      "eval_steps_per_second": 6.846,
      "step": 5
    },
    {
      "epoch": 0.056074766355140186,
      "grad_norm": 0.7302444577217102,
      "learning_rate": 0.0001992114701314478,
      "loss": 0.9971,
      "step": 6
    },
    {
      "epoch": 0.08411214953271028,
      "grad_norm": 0.7908813953399658,
      "learning_rate": 0.00018763066800438636,
      "loss": 0.9315,
      "step": 9
    },
    {
      "epoch": 0.09345794392523364,
      "eval_loss": 1.0517429113388062,
      "eval_runtime": 3.3591,
      "eval_samples_per_second": 26.793,
      "eval_steps_per_second": 6.847,
      "step": 10
    },
    {
      "epoch": 0.11214953271028037,
      "grad_norm": 0.7828400731086731,
      "learning_rate": 0.000163742398974869,
      "loss": 0.8625,
      "step": 12
    },
    {
      "epoch": 0.14018691588785046,
      "grad_norm": 0.8065340518951416,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.8771,
      "step": 15
    },
    {
      "epoch": 0.14018691588785046,
      "eval_loss": 0.989932656288147,
      "eval_runtime": 3.3614,
      "eval_samples_per_second": 26.774,
      "eval_steps_per_second": 6.842,
      "step": 15
    },
    {
      "epoch": 0.16822429906542055,
      "grad_norm": 0.8578646183013916,
      "learning_rate": 9.372094804706867e-05,
      "loss": 0.9057,
      "step": 18
    },
    {
      "epoch": 0.18691588785046728,
      "eval_loss": 0.9378935098648071,
      "eval_runtime": 3.3635,
      "eval_samples_per_second": 26.758,
      "eval_steps_per_second": 6.838,
      "step": 20
    },
    {
      "epoch": 0.19626168224299065,
      "grad_norm": 0.9750715494155884,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 0.84,
      "step": 21
    },
    {
      "epoch": 0.22429906542056074,
      "grad_norm": 1.1634858846664429,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 1.007,
      "step": 24
    },
    {
      "epoch": 0.2336448598130841,
      "eval_loss": 0.9214831590652466,
      "eval_runtime": 3.3654,
      "eval_samples_per_second": 26.743,
      "eval_steps_per_second": 6.834,
      "step": 25
    },
    {
      "epoch": 0.2523364485981308,
      "grad_norm": 0.7800555229187012,
      "learning_rate": 7.022351411174866e-06,
      "loss": 1.2721,
      "step": 27
    },
    {
      "epoch": 0.2803738317757009,
      "grad_norm": 0.6685587167739868,
      "learning_rate": 0.0,
      "loss": 0.7286,
      "step": 30
    },
    {
      "epoch": 0.2803738317757009,
      "eval_loss": 0.9353803992271423,
      "eval_runtime": 3.3644,
      "eval_samples_per_second": 26.751,
      "eval_steps_per_second": 6.836,
      "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": 6232849401249792.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}