last-checkpoint/trainer_state.json

{
  "best_metric": 1.4081313610076904,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.00260061114361875,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001300305571809375,
      "eval_loss": 1.5946362018585205,
      "eval_runtime": 270.7667,
      "eval_samples_per_second": 23.921,
      "eval_steps_per_second": 5.983,
      "step": 1
    },
    {
      "epoch": 0.0003900916715428126,
      "grad_norm": 0.26214665174484253,
      "learning_rate": 0.00012,
      "loss": 1.4882,
      "step": 3
    },
    {
      "epoch": 0.0006501527859046876,
      "eval_loss": 1.5178037881851196,
      "eval_runtime": 272.158,
      "eval_samples_per_second": 23.799,
      "eval_steps_per_second": 5.952,
      "step": 5
    },
    {
      "epoch": 0.0007801833430856252,
      "grad_norm": 0.18134617805480957,
      "learning_rate": 0.0001992114701314478,
      "loss": 1.4564,
      "step": 6
    },
    {
      "epoch": 0.0011702750146284377,
      "grad_norm": 0.16104453802108765,
      "learning_rate": 0.00018763066800438636,
      "loss": 1.4299,
      "step": 9
    },
    {
      "epoch": 0.001300305571809375,
      "eval_loss": 1.4525096416473389,
      "eval_runtime": 272.3762,
      "eval_samples_per_second": 23.78,
      "eval_steps_per_second": 5.948,
      "step": 10
    },
    {
      "epoch": 0.0015603666861712503,
      "grad_norm": 0.16580092906951904,
      "learning_rate": 0.000163742398974869,
      "loss": 1.408,
      "step": 12
    },
    {
      "epoch": 0.0019504583577140628,
      "grad_norm": 0.15052564442157745,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.3837,
      "step": 15
    },
    {
      "epoch": 0.0019504583577140628,
      "eval_loss": 1.4265315532684326,
      "eval_runtime": 272.3667,
      "eval_samples_per_second": 23.78,
      "eval_steps_per_second": 5.948,
      "step": 15
    },
    {
      "epoch": 0.0023405500292568754,
      "grad_norm": 0.24706414341926575,
      "learning_rate": 9.372094804706867e-05,
      "loss": 1.3752,
      "step": 18
    },
    {
      "epoch": 0.00260061114361875,
      "eval_loss": 1.4081313610076904,
      "eval_runtime": 272.3861,
      "eval_samples_per_second": 23.779,
      "eval_steps_per_second": 5.947,
      "step": 20
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2645194394566656.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}