last-checkpoint/trainer_state.json

{
  "best_metric": 1.7267839908599854,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.046948356807511735,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001564945226917058,
      "eval_loss": 2.921564817428589,
      "eval_runtime": 34.5348,
      "eval_samples_per_second": 15.607,
      "eval_steps_per_second": 3.909,
      "step": 1
    },
    {
      "epoch": 0.004694835680751174,
      "grad_norm": 13.620658874511719,
      "learning_rate": 0.00012,
      "loss": 10.1715,
      "step": 3
    },
    {
      "epoch": 0.00782472613458529,
      "eval_loss": 2.223052740097046,
      "eval_runtime": 34.5871,
      "eval_samples_per_second": 15.584,
      "eval_steps_per_second": 3.903,
      "step": 5
    },
    {
      "epoch": 0.009389671361502348,
      "grad_norm": 12.163566589355469,
      "learning_rate": 0.0001992114701314478,
      "loss": 9.048,
      "step": 6
    },
    {
      "epoch": 0.014084507042253521,
      "grad_norm": 8.320079803466797,
      "learning_rate": 0.00018763066800438636,
      "loss": 7.957,
      "step": 9
    },
    {
      "epoch": 0.01564945226917058,
      "eval_loss": 1.9574483633041382,
      "eval_runtime": 34.6128,
      "eval_samples_per_second": 15.572,
      "eval_steps_per_second": 3.9,
      "step": 10
    },
    {
      "epoch": 0.018779342723004695,
      "grad_norm": 9.912591934204102,
      "learning_rate": 0.000163742398974869,
      "loss": 7.5866,
      "step": 12
    },
    {
      "epoch": 0.023474178403755867,
      "grad_norm": 8.794225692749023,
      "learning_rate": 0.00013090169943749476,
      "loss": 7.4394,
      "step": 15
    },
    {
      "epoch": 0.023474178403755867,
      "eval_loss": 1.855014443397522,
      "eval_runtime": 34.607,
      "eval_samples_per_second": 15.575,
      "eval_steps_per_second": 3.901,
      "step": 15
    },
    {
      "epoch": 0.028169014084507043,
      "grad_norm": 8.808883666992188,
      "learning_rate": 9.372094804706867e-05,
      "loss": 7.1421,
      "step": 18
    },
    {
      "epoch": 0.03129890453834116,
      "eval_loss": 1.7805674076080322,
      "eval_runtime": 34.6067,
      "eval_samples_per_second": 15.575,
      "eval_steps_per_second": 3.901,
      "step": 20
    },
    {
      "epoch": 0.03286384976525822,
      "grad_norm": 8.659530639648438,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 6.949,
      "step": 21
    },
    {
      "epoch": 0.03755868544600939,
      "grad_norm": 8.718548774719238,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 6.5662,
      "step": 24
    },
    {
      "epoch": 0.03912363067292645,
      "eval_loss": 1.7352848052978516,
      "eval_runtime": 34.6384,
      "eval_samples_per_second": 15.561,
      "eval_steps_per_second": 3.897,
      "step": 25
    },
    {
      "epoch": 0.04225352112676056,
      "grad_norm": 8.553363800048828,
      "learning_rate": 7.022351411174866e-06,
      "loss": 6.6039,
      "step": 27
    },
    {
      "epoch": 0.046948356807511735,
      "grad_norm": 9.443631172180176,
      "learning_rate": 0.0,
      "loss": 6.6292,
      "step": 30
    },
    {
      "epoch": 0.046948356807511735,
      "eval_loss": 1.7267839908599854,
      "eval_runtime": 34.6173,
      "eval_samples_per_second": 15.57,
      "eval_steps_per_second": 3.9,
      "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": 2.109388496044032e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}