last-checkpoint/trainer_state.json

{
  "best_metric": 12.990397453308105,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.24551927326295114,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004910385465259023,
      "eval_loss": 8.885814666748047,
      "eval_runtime": 238.0058,
      "eval_samples_per_second": 14.411,
      "eval_steps_per_second": 3.605,
      "step": 1
    },
    {
      "epoch": 0.024551927326295114,
      "grad_norm": 42008307564544.0,
      "learning_rate": 0.000106,
      "loss": 8.5743,
      "step": 50
    },
    {
      "epoch": 0.04910385465259023,
      "grad_norm": 557210992640.0,
      "learning_rate": 0.000212,
      "loss": 7.9517,
      "step": 100
    },
    {
      "epoch": 0.07365578197888534,
      "grad_norm": 6631273791488.0,
      "learning_rate": 0.0002039312304461964,
      "loss": 10.2486,
      "step": 150
    },
    {
      "epoch": 0.09820770930518045,
      "grad_norm": 4286375424.0,
      "learning_rate": 0.00018095331880577404,
      "loss": 15.7423,
      "step": 200
    },
    {
      "epoch": 0.12275963663147557,
      "grad_norm": 14081196032000.0,
      "learning_rate": 0.00014656444383069953,
      "loss": 13.472,
      "step": 250
    },
    {
      "epoch": 0.14731156395777067,
      "grad_norm": 2926234566656.0,
      "learning_rate": 0.000106,
      "loss": 13.7329,
      "step": 300
    },
    {
      "epoch": 0.1718634912840658,
      "grad_norm": 20068786176.0,
      "learning_rate": 6.543555616930049e-05,
      "loss": 13.4434,
      "step": 350
    },
    {
      "epoch": 0.1964154186103609,
      "grad_norm": 5454654464.0,
      "learning_rate": 3.104668119422597e-05,
      "loss": 12.9573,
      "step": 400
    },
    {
      "epoch": 0.22096734593665604,
      "grad_norm": 4763621888.0,
      "learning_rate": 8.068769553803605e-06,
      "loss": 13.2059,
      "step": 450
    },
    {
      "epoch": 0.24551927326295114,
      "grad_norm": 1581244481536.0,
      "learning_rate": 0.0,
      "loss": 13.1652,
      "step": 500
    },
    {
      "epoch": 0.24551927326295114,
      "eval_loss": 12.990397453308105,
      "eval_runtime": 238.0138,
      "eval_samples_per_second": 14.411,
      "eval_steps_per_second": 3.605,
      "step": 500
    }
  ],
  "logging_steps": 50,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": 3.77695431032832e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}