last-checkpoint/trainer_state.json

{
  "best_metric": 1.369350790977478,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0021247211303516414,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.082403767838805e-05,
      "eval_loss": 1.69896399974823,
      "eval_runtime": 352.0316,
      "eval_samples_per_second": 16.891,
      "eval_steps_per_second": 8.445,
      "step": 1
    },
    {
      "epoch": 0.00021247211303516414,
      "grad_norm": 0.5600340366363525,
      "learning_rate": 6e-05,
      "loss": 1.5525,
      "step": 3
    },
    {
      "epoch": 0.0003541201883919402,
      "eval_loss": 1.664231300354004,
      "eval_runtime": 351.4789,
      "eval_samples_per_second": 16.917,
      "eval_steps_per_second": 8.459,
      "step": 5
    },
    {
      "epoch": 0.00042494422607032827,
      "grad_norm": 0.4572010636329651,
      "learning_rate": 0.00012,
      "loss": 1.4799,
      "step": 6
    },
    {
      "epoch": 0.0006374163391054924,
      "grad_norm": 0.44883954524993896,
      "learning_rate": 0.00018,
      "loss": 1.4486,
      "step": 9
    },
    {
      "epoch": 0.0007082403767838804,
      "eval_loss": 1.5002901554107666,
      "eval_runtime": 351.693,
      "eval_samples_per_second": 16.907,
      "eval_steps_per_second": 8.453,
      "step": 10
    },
    {
      "epoch": 0.0008498884521406565,
      "grad_norm": 0.5659921169281006,
      "learning_rate": 0.00019510565162951537,
      "loss": 1.5074,
      "step": 12
    },
    {
      "epoch": 0.0010623605651758207,
      "grad_norm": 0.5782586336135864,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.4052,
      "step": 15
    },
    {
      "epoch": 0.0010623605651758207,
      "eval_loss": 1.426486611366272,
      "eval_runtime": 351.68,
      "eval_samples_per_second": 16.907,
      "eval_steps_per_second": 8.454,
      "step": 15
    },
    {
      "epoch": 0.0012748326782109848,
      "grad_norm": 0.4913944602012634,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.4415,
      "step": 18
    },
    {
      "epoch": 0.0014164807535677608,
      "eval_loss": 1.3844151496887207,
      "eval_runtime": 351.1479,
      "eval_samples_per_second": 16.933,
      "eval_steps_per_second": 8.467,
      "step": 20
    },
    {
      "epoch": 0.001487304791246149,
      "grad_norm": 0.5099649429321289,
      "learning_rate": 8.435655349597689e-05,
      "loss": 1.284,
      "step": 21
    },
    {
      "epoch": 0.001699776904281313,
      "grad_norm": 0.3888559639453888,
      "learning_rate": 4.12214747707527e-05,
      "loss": 1.2964,
      "step": 24
    },
    {
      "epoch": 0.0017706009419597012,
      "eval_loss": 1.3718374967575073,
      "eval_runtime": 351.7983,
      "eval_samples_per_second": 16.902,
      "eval_steps_per_second": 8.451,
      "step": 25
    },
    {
      "epoch": 0.0019122490173164772,
      "grad_norm": 0.4067215025424957,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 1.2082,
      "step": 27
    },
    {
      "epoch": 0.0021247211303516414,
      "grad_norm": 0.6029534339904785,
      "learning_rate": 0.0,
      "loss": 1.611,
      "step": 30
    },
    {
      "epoch": 0.0021247211303516414,
      "eval_loss": 1.369350790977478,
      "eval_runtime": 351.5987,
      "eval_samples_per_second": 16.911,
      "eval_steps_per_second": 8.456,
      "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": 1.049486910554112e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}