last-checkpoint/trainer_state.json

{
  "best_metric": 1.002984881401062,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0015586034912718205,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.195344970906068e-05,
      "eval_loss": 1.5982962846755981,
      "eval_runtime": 2536.1931,
      "eval_samples_per_second": 3.196,
      "eval_steps_per_second": 1.598,
      "step": 1
    },
    {
      "epoch": 0.00015586034912718204,
      "grad_norm": 0.5278963446617126,
      "learning_rate": 6e-05,
      "loss": 6.4835,
      "step": 3
    },
    {
      "epoch": 0.0002597672485453034,
      "eval_loss": 1.5611845254898071,
      "eval_runtime": 2546.3108,
      "eval_samples_per_second": 3.183,
      "eval_steps_per_second": 1.592,
      "step": 5
    },
    {
      "epoch": 0.0003117206982543641,
      "grad_norm": 0.7231905460357666,
      "learning_rate": 0.00012,
      "loss": 6.4329,
      "step": 6
    },
    {
      "epoch": 0.0004675810473815461,
      "grad_norm": 0.7111061811447144,
      "learning_rate": 0.00018,
      "loss": 5.9363,
      "step": 9
    },
    {
      "epoch": 0.0005195344970906068,
      "eval_loss": 1.3349263668060303,
      "eval_runtime": 2545.6626,
      "eval_samples_per_second": 3.184,
      "eval_steps_per_second": 1.592,
      "step": 10
    },
    {
      "epoch": 0.0006234413965087282,
      "grad_norm": 1.9805951118469238,
      "learning_rate": 0.00019510565162951537,
      "loss": 5.1102,
      "step": 12
    },
    {
      "epoch": 0.0007793017456359103,
      "grad_norm": 1.0474853515625,
      "learning_rate": 0.00017071067811865476,
      "loss": 4.9768,
      "step": 15
    },
    {
      "epoch": 0.0007793017456359103,
      "eval_loss": 1.1523114442825317,
      "eval_runtime": 2547.2055,
      "eval_samples_per_second": 3.182,
      "eval_steps_per_second": 1.591,
      "step": 15
    },
    {
      "epoch": 0.0009351620947630922,
      "grad_norm": 0.9892725348472595,
      "learning_rate": 0.00013090169943749476,
      "loss": 4.5857,
      "step": 18
    },
    {
      "epoch": 0.0010390689941812137,
      "eval_loss": 1.0497976541519165,
      "eval_runtime": 2546.9723,
      "eval_samples_per_second": 3.182,
      "eval_steps_per_second": 1.591,
      "step": 20
    },
    {
      "epoch": 0.0010910224438902742,
      "grad_norm": 1.0282012224197388,
      "learning_rate": 8.435655349597689e-05,
      "loss": 4.3566,
      "step": 21
    },
    {
      "epoch": 0.0012468827930174563,
      "grad_norm": 1.050193428993225,
      "learning_rate": 4.12214747707527e-05,
      "loss": 4.1911,
      "step": 24
    },
    {
      "epoch": 0.001298836242726517,
      "eval_loss": 1.0107142925262451,
      "eval_runtime": 2544.8712,
      "eval_samples_per_second": 3.185,
      "eval_steps_per_second": 1.593,
      "step": 25
    },
    {
      "epoch": 0.0014027431421446384,
      "grad_norm": 1.007144570350647,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 4.0247,
      "step": 27
    },
    {
      "epoch": 0.0015586034912718205,
      "grad_norm": 0.9790642261505127,
      "learning_rate": 0.0,
      "loss": 3.8987,
      "step": 30
    },
    {
      "epoch": 0.0015586034912718205,
      "eval_loss": 1.002984881401062,
      "eval_runtime": 2546.0806,
      "eval_samples_per_second": 3.183,
      "eval_steps_per_second": 1.592,
      "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": 3.473863178452992e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}