last-checkpoint/trainer_state.json

{
  "best_metric": 1.6721153259277344,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.40816326530612246,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02040816326530612,
      "eval_loss": 2.5419111251831055,
      "eval_runtime": 6.6857,
      "eval_samples_per_second": 6.282,
      "eval_steps_per_second": 1.645,
      "step": 1
    },
    {
      "epoch": 0.061224489795918366,
      "grad_norm": 2.320087432861328,
      "learning_rate": 0.00012,
      "loss": 2.0648,
      "step": 3
    },
    {
      "epoch": 0.10204081632653061,
      "eval_loss": 2.240957260131836,
      "eval_runtime": 6.2662,
      "eval_samples_per_second": 6.703,
      "eval_steps_per_second": 1.755,
      "step": 5
    },
    {
      "epoch": 0.12244897959183673,
      "grad_norm": 1.670237421989441,
      "learning_rate": 0.0001992114701314478,
      "loss": 2.3035,
      "step": 6
    },
    {
      "epoch": 0.1836734693877551,
      "grad_norm": 2.4471113681793213,
      "learning_rate": 0.00018763066800438636,
      "loss": 2.0249,
      "step": 9
    },
    {
      "epoch": 0.20408163265306123,
      "eval_loss": 1.7959092855453491,
      "eval_runtime": 6.2793,
      "eval_samples_per_second": 6.689,
      "eval_steps_per_second": 1.752,
      "step": 10
    },
    {
      "epoch": 0.24489795918367346,
      "grad_norm": 1.7679206132888794,
      "learning_rate": 0.000163742398974869,
      "loss": 2.013,
      "step": 12
    },
    {
      "epoch": 0.30612244897959184,
      "grad_norm": 1.0185257196426392,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.4636,
      "step": 15
    },
    {
      "epoch": 0.30612244897959184,
      "eval_loss": 1.7165956497192383,
      "eval_runtime": 6.3372,
      "eval_samples_per_second": 6.628,
      "eval_steps_per_second": 1.736,
      "step": 15
    },
    {
      "epoch": 0.3673469387755102,
      "grad_norm": 1.4117796421051025,
      "learning_rate": 9.372094804706867e-05,
      "loss": 1.6236,
      "step": 18
    },
    {
      "epoch": 0.40816326530612246,
      "eval_loss": 1.6721153259277344,
      "eval_runtime": 6.3285,
      "eval_samples_per_second": 6.637,
      "eval_steps_per_second": 1.738,
      "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": 1.695099842985984e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}