last-checkpoint/trainer_state.json

{
  "best_metric": 0.7860333323478699,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.11214953271028037,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003738317757009346,
      "eval_loss": 1.1981878280639648,
      "eval_runtime": 21.1159,
      "eval_samples_per_second": 5.351,
      "eval_steps_per_second": 2.699,
      "step": 1
    },
    {
      "epoch": 0.011214953271028037,
      "grad_norm": 10.674063682556152,
      "learning_rate": 0.00012,
      "loss": 4.8191,
      "step": 3
    },
    {
      "epoch": 0.018691588785046728,
      "eval_loss": 0.864096462726593,
      "eval_runtime": 23.2388,
      "eval_samples_per_second": 4.863,
      "eval_steps_per_second": 2.453,
      "step": 5
    },
    {
      "epoch": 0.022429906542056073,
      "grad_norm": 5.835250377655029,
      "learning_rate": 0.0001992114701314478,
      "loss": 4.0605,
      "step": 6
    },
    {
      "epoch": 0.03364485981308411,
      "grad_norm": 4.247188568115234,
      "learning_rate": 0.00018763066800438636,
      "loss": 3.2485,
      "step": 9
    },
    {
      "epoch": 0.037383177570093455,
      "eval_loss": 0.8075501918792725,
      "eval_runtime": 24.593,
      "eval_samples_per_second": 4.595,
      "eval_steps_per_second": 2.318,
      "step": 10
    },
    {
      "epoch": 0.044859813084112146,
      "grad_norm": 4.276338577270508,
      "learning_rate": 0.000163742398974869,
      "loss": 3.2567,
      "step": 12
    },
    {
      "epoch": 0.056074766355140186,
      "grad_norm": 6.961503505706787,
      "learning_rate": 0.00013090169943749476,
      "loss": 3.2903,
      "step": 15
    },
    {
      "epoch": 0.056074766355140186,
      "eval_loss": 0.7992917895317078,
      "eval_runtime": 25.1132,
      "eval_samples_per_second": 4.5,
      "eval_steps_per_second": 2.27,
      "step": 15
    },
    {
      "epoch": 0.06728971962616823,
      "grad_norm": 24.969470977783203,
      "learning_rate": 9.372094804706867e-05,
      "loss": 3.3394,
      "step": 18
    },
    {
      "epoch": 0.07476635514018691,
      "eval_loss": 0.7909897565841675,
      "eval_runtime": 25.3961,
      "eval_samples_per_second": 4.449,
      "eval_steps_per_second": 2.244,
      "step": 20
    },
    {
      "epoch": 0.07850467289719626,
      "grad_norm": 3.8463242053985596,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 3.1735,
      "step": 21
    },
    {
      "epoch": 0.08971962616822429,
      "grad_norm": 9.312294006347656,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 3.4073,
      "step": 24
    },
    {
      "epoch": 0.09345794392523364,
      "eval_loss": 0.7876268029212952,
      "eval_runtime": 25.1739,
      "eval_samples_per_second": 4.489,
      "eval_steps_per_second": 2.264,
      "step": 25
    },
    {
      "epoch": 0.10093457943925234,
      "grad_norm": 4.681221961975098,
      "learning_rate": 7.022351411174866e-06,
      "loss": 3.3088,
      "step": 27
    },
    {
      "epoch": 0.11214953271028037,
      "grad_norm": 6.044920444488525,
      "learning_rate": 0.0,
      "loss": 3.1179,
      "step": 30
    },
    {
      "epoch": 0.11214953271028037,
      "eval_loss": 0.7860333323478699,
      "eval_runtime": 24.9332,
      "eval_samples_per_second": 4.532,
      "eval_steps_per_second": 2.286,
      "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": 1.054694248022016e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}