last-checkpoint/trainer_state.json

{
  "best_metric": 1.71920645236969,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.27906976744186046,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009302325581395349,
      "eval_loss": 2.347416877746582,
      "eval_runtime": 21.61,
      "eval_samples_per_second": 4.211,
      "eval_steps_per_second": 1.064,
      "step": 1
    },
    {
      "epoch": 0.027906976744186046,
      "grad_norm": 0.4165973365306854,
      "learning_rate": 0.00012,
      "loss": 2.1624,
      "step": 3
    },
    {
      "epoch": 0.046511627906976744,
      "eval_loss": 2.2866299152374268,
      "eval_runtime": 21.4311,
      "eval_samples_per_second": 4.246,
      "eval_steps_per_second": 1.073,
      "step": 5
    },
    {
      "epoch": 0.05581395348837209,
      "grad_norm": 0.8082454204559326,
      "learning_rate": 0.0001992114701314478,
      "loss": 2.1885,
      "step": 6
    },
    {
      "epoch": 0.08372093023255814,
      "grad_norm": 0.919445276260376,
      "learning_rate": 0.00018763066800438636,
      "loss": 2.0357,
      "step": 9
    },
    {
      "epoch": 0.09302325581395349,
      "eval_loss": 1.9224990606307983,
      "eval_runtime": 21.4873,
      "eval_samples_per_second": 4.235,
      "eval_steps_per_second": 1.07,
      "step": 10
    },
    {
      "epoch": 0.11162790697674418,
      "grad_norm": 0.5291640758514404,
      "learning_rate": 0.000163742398974869,
      "loss": 1.9079,
      "step": 12
    },
    {
      "epoch": 0.13953488372093023,
      "grad_norm": 0.4846174418926239,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.7631,
      "step": 15
    },
    {
      "epoch": 0.13953488372093023,
      "eval_loss": 1.8105331659317017,
      "eval_runtime": 21.5003,
      "eval_samples_per_second": 4.232,
      "eval_steps_per_second": 1.07,
      "step": 15
    },
    {
      "epoch": 0.16744186046511628,
      "grad_norm": 0.5171637535095215,
      "learning_rate": 9.372094804706867e-05,
      "loss": 1.7568,
      "step": 18
    },
    {
      "epoch": 0.18604651162790697,
      "eval_loss": 1.7479033470153809,
      "eval_runtime": 21.5065,
      "eval_samples_per_second": 4.231,
      "eval_steps_per_second": 1.069,
      "step": 20
    },
    {
      "epoch": 0.19534883720930232,
      "grad_norm": 0.5440554022789001,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 1.8117,
      "step": 21
    },
    {
      "epoch": 0.22325581395348837,
      "grad_norm": 0.6222204566001892,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 1.8081,
      "step": 24
    },
    {
      "epoch": 0.23255813953488372,
      "eval_loss": 1.7246214151382446,
      "eval_runtime": 21.4867,
      "eval_samples_per_second": 4.235,
      "eval_steps_per_second": 1.07,
      "step": 25
    },
    {
      "epoch": 0.25116279069767444,
      "grad_norm": 0.3558702766895294,
      "learning_rate": 7.022351411174866e-06,
      "loss": 1.8349,
      "step": 27
    },
    {
      "epoch": 0.27906976744186046,
      "grad_norm": 0.42415860295295715,
      "learning_rate": 0.0,
      "loss": 1.6276,
      "step": 30
    },
    {
      "epoch": 0.27906976744186046,
      "eval_loss": 1.71920645236969,
      "eval_runtime": 21.4466,
      "eval_samples_per_second": 4.243,
      "eval_steps_per_second": 1.072,
      "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": 3.79944651718656e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}