last-checkpoint/trainer_state.json

{
  "best_metric": 2.2043137550354004,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.0038218994840435697,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00019109497420217848,
      "eval_loss": 2.308932304382324,
      "eval_runtime": 327.2834,
      "eval_samples_per_second": 6.734,
      "eval_steps_per_second": 3.367,
      "step": 1
    },
    {
      "epoch": 0.0005732849226065354,
      "grad_norm": 0.5690717697143555,
      "learning_rate": 6e-05,
      "loss": 2.252,
      "step": 3
    },
    {
      "epoch": 0.0009554748710108924,
      "eval_loss": 2.3020167350769043,
      "eval_runtime": 329.8913,
      "eval_samples_per_second": 6.681,
      "eval_steps_per_second": 3.34,
      "step": 5
    },
    {
      "epoch": 0.0011465698452130708,
      "grad_norm": 0.46486157178878784,
      "learning_rate": 0.00012,
      "loss": 2.3379,
      "step": 6
    },
    {
      "epoch": 0.0017198547678196063,
      "grad_norm": 0.52753746509552,
      "learning_rate": 0.00018,
      "loss": 2.2368,
      "step": 9
    },
    {
      "epoch": 0.0019109497420217848,
      "eval_loss": 2.249831199645996,
      "eval_runtime": 329.8514,
      "eval_samples_per_second": 6.682,
      "eval_steps_per_second": 3.341,
      "step": 10
    },
    {
      "epoch": 0.0022931396904261416,
      "grad_norm": 0.6293866634368896,
      "learning_rate": 0.00019510565162951537,
      "loss": 2.2827,
      "step": 12
    },
    {
      "epoch": 0.0028664246130326774,
      "grad_norm": 0.7618629336357117,
      "learning_rate": 0.00017071067811865476,
      "loss": 2.2086,
      "step": 15
    },
    {
      "epoch": 0.0028664246130326774,
      "eval_loss": 2.2161858081817627,
      "eval_runtime": 329.7855,
      "eval_samples_per_second": 6.683,
      "eval_steps_per_second": 3.342,
      "step": 15
    },
    {
      "epoch": 0.0034397095356392127,
      "grad_norm": 0.5426533222198486,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.2097,
      "step": 18
    },
    {
      "epoch": 0.0038218994840435697,
      "eval_loss": 2.2043137550354004,
      "eval_runtime": 329.4295,
      "eval_samples_per_second": 6.69,
      "eval_steps_per_second": 3.345,
      "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": 8346231940055040.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}