last-checkpoint/trainer_state.json

{
  "best_metric": 11.5,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.6002400960384153,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0012004801920768306,
      "eval_loss": 11.5,
      "eval_runtime": 9.2958,
      "eval_samples_per_second": 150.929,
      "eval_steps_per_second": 37.759,
      "step": 1
    },
    {
      "epoch": 0.060024009603841535,
      "grad_norm": 0.0005615451955236495,
      "learning_rate": 0.000108,
      "loss": 92.0,
      "step": 50
    },
    {
      "epoch": 0.12004801920768307,
      "grad_norm": 0.002014897530898452,
      "learning_rate": 0.000216,
      "loss": 92.0,
      "step": 100
    },
    {
      "epoch": 0.18007202881152462,
      "grad_norm": 0.00805481057614088,
      "learning_rate": 0.00020777898951121896,
      "loss": 92.0,
      "step": 150
    },
    {
      "epoch": 0.24009603841536614,
      "grad_norm": 0.007082858122885227,
      "learning_rate": 0.00018436753236814713,
      "loss": 92.0,
      "step": 200
    },
    {
      "epoch": 0.30012004801920766,
      "grad_norm": 0.0037972754798829556,
      "learning_rate": 0.0001493298106954297,
      "loss": 92.0,
      "step": 250
    },
    {
      "epoch": 0.36014405762304924,
      "grad_norm": 0.0060953060165047646,
      "learning_rate": 0.000108,
      "loss": 92.0,
      "step": 300
    },
    {
      "epoch": 0.42016806722689076,
      "grad_norm": 0.008572332561016083,
      "learning_rate": 6.667018930457031e-05,
      "loss": 92.0,
      "step": 350
    },
    {
      "epoch": 0.4801920768307323,
      "grad_norm": 0.0030469526536762714,
      "learning_rate": 3.1632467631852876e-05,
      "loss": 92.0,
      "step": 400
    },
    {
      "epoch": 0.5402160864345739,
      "grad_norm": 0.0042664664797484875,
      "learning_rate": 8.221010488781032e-06,
      "loss": 92.0,
      "step": 450
    },
    {
      "epoch": 0.6002400960384153,
      "grad_norm": 0.0034124753437936306,
      "learning_rate": 0.0,
      "loss": 92.0,
      "step": 500
    },
    {
      "epoch": 0.6002400960384153,
      "eval_loss": 11.5,
      "eval_runtime": 9.3471,
      "eval_samples_per_second": 150.1,
      "eval_steps_per_second": 37.552,
      "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": 80396156928000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}