last-checkpoint/trainer_state.json

{
  "best_metric": 1.5659117698669434,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.0021369804466289132,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00021369804466289135,
      "grad_norm": 0.7776347994804382,
      "learning_rate": 2e-05,
      "loss": 1.6473,
      "step": 1
    },
    {
      "epoch": 0.00021369804466289135,
      "eval_loss": 1.8470208644866943,
      "eval_runtime": 275.941,
      "eval_samples_per_second": 7.143,
      "eval_steps_per_second": 3.573,
      "step": 1
    },
    {
      "epoch": 0.0004273960893257827,
      "grad_norm": 0.9071603417396545,
      "learning_rate": 4e-05,
      "loss": 1.8389,
      "step": 2
    },
    {
      "epoch": 0.000641094133988674,
      "grad_norm": 0.9546608328819275,
      "learning_rate": 6e-05,
      "loss": 1.8896,
      "step": 3
    },
    {
      "epoch": 0.0008547921786515654,
      "grad_norm": 0.8853360414505005,
      "learning_rate": 8e-05,
      "loss": 1.9434,
      "step": 4
    },
    {
      "epoch": 0.0010684902233144566,
      "grad_norm": 0.9135332703590393,
      "learning_rate": 0.0001,
      "loss": 1.8046,
      "step": 5
    },
    {
      "epoch": 0.0010684902233144566,
      "eval_loss": 1.8170785903930664,
      "eval_runtime": 274.4552,
      "eval_samples_per_second": 7.182,
      "eval_steps_per_second": 3.593,
      "step": 5
    },
    {
      "epoch": 0.001282188267977348,
      "grad_norm": 0.9748033881187439,
      "learning_rate": 0.00012,
      "loss": 1.8187,
      "step": 6
    },
    {
      "epoch": 0.0014958863126402393,
      "grad_norm": 1.0681061744689941,
      "learning_rate": 0.00014,
      "loss": 1.7537,
      "step": 7
    },
    {
      "epoch": 0.0017095843573031308,
      "grad_norm": 0.9694352746009827,
      "learning_rate": 0.00016,
      "loss": 1.7455,
      "step": 8
    },
    {
      "epoch": 0.001923282401966022,
      "grad_norm": 0.8963027596473694,
      "learning_rate": 0.00018,
      "loss": 1.6952,
      "step": 9
    },
    {
      "epoch": 0.0021369804466289132,
      "grad_norm": 0.9051772952079773,
      "learning_rate": 0.0002,
      "loss": 1.6015,
      "step": 10
    },
    {
      "epoch": 0.0021369804466289132,
      "eval_loss": 1.5659117698669434,
      "eval_runtime": 275.0012,
      "eval_samples_per_second": 7.167,
      "eval_steps_per_second": 3.585,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": 1628733135912960.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}