last-checkpoint/trainer_state.json

{
  "best_metric": 1.2092185020446777,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.004100181091331534,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00013667270304438446,
      "eval_loss": 1.5182439088821411,
      "eval_runtime": 808.6093,
      "eval_samples_per_second": 3.81,
      "eval_steps_per_second": 1.906,
      "step": 1
    },
    {
      "epoch": 0.00041001810913315336,
      "grad_norm": 0.895489513874054,
      "learning_rate": 0.00012,
      "loss": 0.9062,
      "step": 3
    },
    {
      "epoch": 0.0006833635152219223,
      "eval_loss": 1.4582839012145996,
      "eval_runtime": 826.8135,
      "eval_samples_per_second": 3.726,
      "eval_steps_per_second": 1.864,
      "step": 5
    },
    {
      "epoch": 0.0008200362182663067,
      "grad_norm": 0.2634448707103729,
      "learning_rate": 0.0001992114701314478,
      "loss": 0.9164,
      "step": 6
    },
    {
      "epoch": 0.0012300543273994601,
      "grad_norm": 0.2708999812602997,
      "learning_rate": 0.00018763066800438636,
      "loss": 0.9311,
      "step": 9
    },
    {
      "epoch": 0.0013667270304438446,
      "eval_loss": 1.3295906782150269,
      "eval_runtime": 826.9871,
      "eval_samples_per_second": 3.726,
      "eval_steps_per_second": 1.863,
      "step": 10
    },
    {
      "epoch": 0.0016400724365326135,
      "grad_norm": 0.2799854874610901,
      "learning_rate": 0.000163742398974869,
      "loss": 0.8518,
      "step": 12
    },
    {
      "epoch": 0.002050090545665767,
      "grad_norm": 0.2093087136745453,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.9811,
      "step": 15
    },
    {
      "epoch": 0.002050090545665767,
      "eval_loss": 1.2553142309188843,
      "eval_runtime": 823.3936,
      "eval_samples_per_second": 3.742,
      "eval_steps_per_second": 1.872,
      "step": 15
    },
    {
      "epoch": 0.0024601086547989203,
      "grad_norm": 0.217794269323349,
      "learning_rate": 9.372094804706867e-05,
      "loss": 0.883,
      "step": 18
    },
    {
      "epoch": 0.002733454060887689,
      "eval_loss": 1.2255158424377441,
      "eval_runtime": 825.0334,
      "eval_samples_per_second": 3.734,
      "eval_steps_per_second": 1.868,
      "step": 20
    },
    {
      "epoch": 0.0028701267639320736,
      "grad_norm": 0.258678674697876,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 1.061,
      "step": 21
    },
    {
      "epoch": 0.003280144873065227,
      "grad_norm": 0.3215930759906769,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 0.9596,
      "step": 24
    },
    {
      "epoch": 0.0034168175761096113,
      "eval_loss": 1.2115516662597656,
      "eval_runtime": 826.0756,
      "eval_samples_per_second": 3.73,
      "eval_steps_per_second": 1.865,
      "step": 25
    },
    {
      "epoch": 0.0036901629821983802,
      "grad_norm": 0.26366937160491943,
      "learning_rate": 7.022351411174866e-06,
      "loss": 0.9283,
      "step": 27
    },
    {
      "epoch": 0.004100181091331534,
      "grad_norm": 0.3247816562652588,
      "learning_rate": 0.0,
      "loss": 1.1581,
      "step": 30
    },
    {
      "epoch": 0.004100181091331534,
      "eval_loss": 1.2092185020446777,
      "eval_runtime": 827.9915,
      "eval_samples_per_second": 3.721,
      "eval_steps_per_second": 1.861,
      "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": 1.677526321594368e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}