last-checkpoint/trainer_state.json

{
  "best_metric": 1.800808310508728,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.006347527109230362,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002115842369743454,
      "eval_loss": 2.2490975856781006,
      "eval_runtime": 492.1632,
      "eval_samples_per_second": 4.043,
      "eval_steps_per_second": 2.022,
      "step": 1
    },
    {
      "epoch": 0.0006347527109230362,
      "grad_norm": 0.5573651194572449,
      "learning_rate": 6e-05,
      "loss": 2.2336,
      "step": 3
    },
    {
      "epoch": 0.0010579211848717272,
      "eval_loss": 2.151787757873535,
      "eval_runtime": 494.8632,
      "eval_samples_per_second": 4.021,
      "eval_steps_per_second": 2.011,
      "step": 5
    },
    {
      "epoch": 0.0012695054218460724,
      "grad_norm": 0.5345481634140015,
      "learning_rate": 0.00012,
      "loss": 2.2414,
      "step": 6
    },
    {
      "epoch": 0.0019042581327691087,
      "grad_norm": 0.38476917147636414,
      "learning_rate": 0.00018,
      "loss": 2.0395,
      "step": 9
    },
    {
      "epoch": 0.0021158423697434543,
      "eval_loss": 2.026219367980957,
      "eval_runtime": 494.729,
      "eval_samples_per_second": 4.022,
      "eval_steps_per_second": 2.011,
      "step": 10
    },
    {
      "epoch": 0.0025390108436921448,
      "grad_norm": 0.6258363723754883,
      "learning_rate": 0.00019510565162951537,
      "loss": 2.0216,
      "step": 12
    },
    {
      "epoch": 0.003173763554615181,
      "grad_norm": 0.4679494798183441,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.8766,
      "step": 15
    },
    {
      "epoch": 0.003173763554615181,
      "eval_loss": 1.9061535596847534,
      "eval_runtime": 494.7695,
      "eval_samples_per_second": 4.022,
      "eval_steps_per_second": 2.011,
      "step": 15
    },
    {
      "epoch": 0.0038085162655382174,
      "grad_norm": 0.48406657576560974,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.9025,
      "step": 18
    },
    {
      "epoch": 0.004231684739486909,
      "eval_loss": 1.8435406684875488,
      "eval_runtime": 494.7878,
      "eval_samples_per_second": 4.022,
      "eval_steps_per_second": 2.011,
      "step": 20
    },
    {
      "epoch": 0.004443268976461253,
      "grad_norm": 0.5833864808082581,
      "learning_rate": 8.435655349597689e-05,
      "loss": 1.8511,
      "step": 21
    },
    {
      "epoch": 0.0050780216873842895,
      "grad_norm": 0.6056792736053467,
      "learning_rate": 4.12214747707527e-05,
      "loss": 1.9373,
      "step": 24
    },
    {
      "epoch": 0.005289605924358635,
      "eval_loss": 1.808415174484253,
      "eval_runtime": 494.8926,
      "eval_samples_per_second": 4.021,
      "eval_steps_per_second": 2.011,
      "step": 25
    },
    {
      "epoch": 0.005712774398307326,
      "grad_norm": 0.7835950255393982,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 1.8092,
      "step": 27
    },
    {
      "epoch": 0.006347527109230362,
      "grad_norm": 0.5311419367790222,
      "learning_rate": 0.0,
      "loss": 1.8405,
      "step": 30
    },
    {
      "epoch": 0.006347527109230362,
      "eval_loss": 1.800808310508728,
      "eval_runtime": 494.8249,
      "eval_samples_per_second": 4.022,
      "eval_steps_per_second": 2.011,
      "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": 3.63630692401152e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}