last-checkpoint/trainer_state.json

{
  "best_metric": 2.075848340988159,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.14018691588785046,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004672897196261682,
      "eval_loss": 2.919769525527954,
      "eval_runtime": 5.8335,
      "eval_samples_per_second": 15.6,
      "eval_steps_per_second": 7.885,
      "step": 1
    },
    {
      "epoch": 0.014018691588785047,
      "grad_norm": 1.5106477737426758,
      "learning_rate": 0.00012,
      "loss": 2.9451,
      "step": 3
    },
    {
      "epoch": 0.02336448598130841,
      "eval_loss": 2.5764288902282715,
      "eval_runtime": 5.2723,
      "eval_samples_per_second": 17.26,
      "eval_steps_per_second": 8.725,
      "step": 5
    },
    {
      "epoch": 0.028037383177570093,
      "grad_norm": 1.4866009950637817,
      "learning_rate": 0.0001992114701314478,
      "loss": 2.6873,
      "step": 6
    },
    {
      "epoch": 0.04205607476635514,
      "grad_norm": 1.3173651695251465,
      "learning_rate": 0.00018763066800438636,
      "loss": 2.4428,
      "step": 9
    },
    {
      "epoch": 0.04672897196261682,
      "eval_loss": 2.2354156970977783,
      "eval_runtime": 5.2644,
      "eval_samples_per_second": 17.286,
      "eval_steps_per_second": 8.738,
      "step": 10
    },
    {
      "epoch": 0.056074766355140186,
      "grad_norm": 1.0673582553863525,
      "learning_rate": 0.000163742398974869,
      "loss": 2.2537,
      "step": 12
    },
    {
      "epoch": 0.07009345794392523,
      "grad_norm": 0.9949750304222107,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.2227,
      "step": 15
    },
    {
      "epoch": 0.07009345794392523,
      "eval_loss": 2.146998167037964,
      "eval_runtime": 5.2815,
      "eval_samples_per_second": 17.23,
      "eval_steps_per_second": 8.71,
      "step": 15
    },
    {
      "epoch": 0.08411214953271028,
      "grad_norm": 0.9237583875656128,
      "learning_rate": 9.372094804706867e-05,
      "loss": 2.0809,
      "step": 18
    },
    {
      "epoch": 0.09345794392523364,
      "eval_loss": 2.1007940769195557,
      "eval_runtime": 5.2667,
      "eval_samples_per_second": 17.278,
      "eval_steps_per_second": 8.734,
      "step": 20
    },
    {
      "epoch": 0.09813084112149532,
      "grad_norm": 0.9848313927650452,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 2.2051,
      "step": 21
    },
    {
      "epoch": 0.11214953271028037,
      "grad_norm": 0.990262508392334,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 2.1474,
      "step": 24
    },
    {
      "epoch": 0.11682242990654206,
      "eval_loss": 2.0803513526916504,
      "eval_runtime": 5.2891,
      "eval_samples_per_second": 17.205,
      "eval_steps_per_second": 8.697,
      "step": 25
    },
    {
      "epoch": 0.1261682242990654,
      "grad_norm": 0.9509544968605042,
      "learning_rate": 7.022351411174866e-06,
      "loss": 2.0368,
      "step": 27
    },
    {
      "epoch": 0.14018691588785046,
      "grad_norm": 0.9084644317626953,
      "learning_rate": 0.0,
      "loss": 2.0899,
      "step": 30
    },
    {
      "epoch": 0.14018691588785046,
      "eval_loss": 2.075848340988159,
      "eval_runtime": 5.2707,
      "eval_samples_per_second": 17.265,
      "eval_steps_per_second": 8.728,
      "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": 1.112830925340672e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}