last-checkpoint/trainer_state.json

{
  "best_metric": 2.168490409851074,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.009116462812428778,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00030388209374762593,
      "eval_loss": 3.856945514678955,
      "eval_runtime": 179.2781,
      "eval_samples_per_second": 7.731,
      "eval_steps_per_second": 3.866,
      "step": 1
    },
    {
      "epoch": 0.0009116462812428777,
      "grad_norm": 3.076671838760376,
      "learning_rate": 0.00012,
      "loss": 3.565,
      "step": 3
    },
    {
      "epoch": 0.0015194104687381296,
      "eval_loss": 3.1825942993164062,
      "eval_runtime": 181.5578,
      "eval_samples_per_second": 7.634,
      "eval_steps_per_second": 3.817,
      "step": 5
    },
    {
      "epoch": 0.0018232925624857555,
      "grad_norm": 5.403068542480469,
      "learning_rate": 0.0001992114701314478,
      "loss": 3.1723,
      "step": 6
    },
    {
      "epoch": 0.002734938843728633,
      "grad_norm": 7.90291166305542,
      "learning_rate": 0.00018763066800438636,
      "loss": 2.582,
      "step": 9
    },
    {
      "epoch": 0.003038820937476259,
      "eval_loss": 2.435781478881836,
      "eval_runtime": 180.493,
      "eval_samples_per_second": 7.679,
      "eval_steps_per_second": 3.839,
      "step": 10
    },
    {
      "epoch": 0.003646585124971511,
      "grad_norm": 3.3128092288970947,
      "learning_rate": 0.000163742398974869,
      "loss": 2.0211,
      "step": 12
    },
    {
      "epoch": 0.004558231406214389,
      "grad_norm": 2.446349859237671,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.2164,
      "step": 15
    },
    {
      "epoch": 0.004558231406214389,
      "eval_loss": 2.297067403793335,
      "eval_runtime": 181.3469,
      "eval_samples_per_second": 7.643,
      "eval_steps_per_second": 3.821,
      "step": 15
    },
    {
      "epoch": 0.005469877687457266,
      "grad_norm": 3.5906927585601807,
      "learning_rate": 9.372094804706867e-05,
      "loss": 2.1964,
      "step": 18
    },
    {
      "epoch": 0.006077641874952518,
      "eval_loss": 2.206324815750122,
      "eval_runtime": 181.3223,
      "eval_samples_per_second": 7.644,
      "eval_steps_per_second": 3.822,
      "step": 20
    },
    {
      "epoch": 0.0063815239687001445,
      "grad_norm": 2.3398468494415283,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 2.2411,
      "step": 21
    },
    {
      "epoch": 0.007293170249943022,
      "grad_norm": 2.6244406700134277,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 2.0876,
      "step": 24
    },
    {
      "epoch": 0.007597052343690648,
      "eval_loss": 2.176274538040161,
      "eval_runtime": 181.6842,
      "eval_samples_per_second": 7.629,
      "eval_steps_per_second": 3.814,
      "step": 25
    },
    {
      "epoch": 0.0082048165311859,
      "grad_norm": 3.688023328781128,
      "learning_rate": 7.022351411174866e-06,
      "loss": 2.1679,
      "step": 27
    },
    {
      "epoch": 0.009116462812428778,
      "grad_norm": 3.1167757511138916,
      "learning_rate": 0.0,
      "loss": 2.0348,
      "step": 30
    },
    {
      "epoch": 0.009116462812428778,
      "eval_loss": 2.168490409851074,
      "eval_runtime": 181.2847,
      "eval_samples_per_second": 7.645,
      "eval_steps_per_second": 3.823,
      "step": 30
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.112830925340672e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}