last-checkpoint/trainer_state.json

{
  "best_metric": 1.2037712335586548,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.0017139429257005741,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001713942925700574,
      "grad_norm": 0.7002414464950562,
      "learning_rate": 2e-05,
      "loss": 5.3109,
      "step": 1
    },
    {
      "epoch": 0.0001713942925700574,
      "eval_loss": 1.2564200162887573,
      "eval_runtime": 431.1988,
      "eval_samples_per_second": 5.698,
      "eval_steps_per_second": 2.85,
      "step": 1
    },
    {
      "epoch": 0.0003427885851401148,
      "grad_norm": 0.5215798616409302,
      "learning_rate": 4e-05,
      "loss": 5.0649,
      "step": 2
    },
    {
      "epoch": 0.0005141828777101723,
      "grad_norm": 0.6687475442886353,
      "learning_rate": 6e-05,
      "loss": 4.807,
      "step": 3
    },
    {
      "epoch": 0.0006855771702802296,
      "grad_norm": 0.5465673208236694,
      "learning_rate": 8e-05,
      "loss": 4.2428,
      "step": 4
    },
    {
      "epoch": 0.0008569714628502871,
      "grad_norm": 0.593774139881134,
      "learning_rate": 0.0001,
      "loss": 4.5061,
      "step": 5
    },
    {
      "epoch": 0.0008569714628502871,
      "eval_loss": 1.2541313171386719,
      "eval_runtime": 431.491,
      "eval_samples_per_second": 5.694,
      "eval_steps_per_second": 2.848,
      "step": 5
    },
    {
      "epoch": 0.0010283657554203446,
      "grad_norm": 0.6595162153244019,
      "learning_rate": 0.00012,
      "loss": 4.7018,
      "step": 6
    },
    {
      "epoch": 0.0011997600479904018,
      "grad_norm": 0.6837590932846069,
      "learning_rate": 0.00014,
      "loss": 4.9708,
      "step": 7
    },
    {
      "epoch": 0.0013711543405604593,
      "grad_norm": 0.6360350847244263,
      "learning_rate": 0.00016,
      "loss": 4.8818,
      "step": 8
    },
    {
      "epoch": 0.0015425486331305167,
      "grad_norm": 0.7959117293357849,
      "learning_rate": 0.00018,
      "loss": 4.296,
      "step": 9
    },
    {
      "epoch": 0.0017139429257005741,
      "grad_norm": 1.0661449432373047,
      "learning_rate": 0.0002,
      "loss": 5.0696,
      "step": 10
    },
    {
      "epoch": 0.0017139429257005741,
      "eval_loss": 1.2037712335586548,
      "eval_runtime": 435.893,
      "eval_samples_per_second": 5.637,
      "eval_steps_per_second": 2.819,
      "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": 4246709207040000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}