last-checkpoint/trainer_state.json

{
  "best_metric": 1.2900954484939575,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.0005930670462295762,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.930670462295763e-05,
      "grad_norm": 4.366586208343506,
      "learning_rate": 1e-05,
      "loss": 5.4323,
      "step": 1
    },
    {
      "epoch": 5.930670462295763e-05,
      "eval_loss": 1.4202075004577637,
      "eval_runtime": 1425.4057,
      "eval_samples_per_second": 4.981,
      "eval_steps_per_second": 2.491,
      "step": 1
    },
    {
      "epoch": 0.00011861340924591526,
      "grad_norm": 3.5335845947265625,
      "learning_rate": 2e-05,
      "loss": 5.7816,
      "step": 2
    },
    {
      "epoch": 0.00017792011386887289,
      "grad_norm": 3.675875425338745,
      "learning_rate": 3e-05,
      "loss": 5.2777,
      "step": 3
    },
    {
      "epoch": 0.00023722681849183051,
      "grad_norm": 3.669605255126953,
      "learning_rate": 4e-05,
      "loss": 4.786,
      "step": 4
    },
    {
      "epoch": 0.0002965335231147881,
      "grad_norm": 3.8144474029541016,
      "learning_rate": 5e-05,
      "loss": 5.1725,
      "step": 5
    },
    {
      "epoch": 0.0002965335231147881,
      "eval_loss": 1.4089925289154053,
      "eval_runtime": 1427.833,
      "eval_samples_per_second": 4.973,
      "eval_steps_per_second": 2.486,
      "step": 5
    },
    {
      "epoch": 0.00035584022773774577,
      "grad_norm": 5.1732892990112305,
      "learning_rate": 6e-05,
      "loss": 6.6594,
      "step": 6
    },
    {
      "epoch": 0.00041514693236070337,
      "grad_norm": 5.111558437347412,
      "learning_rate": 7e-05,
      "loss": 7.1659,
      "step": 7
    },
    {
      "epoch": 0.00047445363698366103,
      "grad_norm": 5.365387439727783,
      "learning_rate": 8e-05,
      "loss": 5.7353,
      "step": 8
    },
    {
      "epoch": 0.0005337603416066186,
      "grad_norm": 4.601907253265381,
      "learning_rate": 9e-05,
      "loss": 5.4603,
      "step": 9
    },
    {
      "epoch": 0.0005930670462295762,
      "grad_norm": 5.3217997550964355,
      "learning_rate": 0.0001,
      "loss": 6.4354,
      "step": 10
    },
    {
      "epoch": 0.0005930670462295762,
      "eval_loss": 1.2900954484939575,
      "eval_runtime": 1425.9569,
      "eval_samples_per_second": 4.979,
      "eval_steps_per_second": 2.49,
      "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": 2972437973041152.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}