last-checkpoint/trainer_state.json

{
  "best_metric": 1.2236804962158203,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.005141828777101723,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001713942925700574,
      "eval_loss": 1.3596421480178833,
      "eval_runtime": 583.9591,
      "eval_samples_per_second": 4.207,
      "eval_steps_per_second": 2.105,
      "step": 1
    },
    {
      "epoch": 0.0005141828777101723,
      "grad_norm": 5.756150722503662,
      "learning_rate": 6e-05,
      "loss": 5.3785,
      "step": 3
    },
    {
      "epoch": 0.0008569714628502871,
      "eval_loss": 1.350292682647705,
      "eval_runtime": 590.0216,
      "eval_samples_per_second": 4.164,
      "eval_steps_per_second": 2.083,
      "step": 5
    },
    {
      "epoch": 0.0010283657554203446,
      "grad_norm": 3711.65625,
      "learning_rate": 9.96057350657239e-05,
      "loss": 4.7408,
      "step": 6
    },
    {
      "epoch": 0.0015425486331305167,
      "grad_norm": 7608.09375,
      "learning_rate": 9.381533400219318e-05,
      "loss": 5.116,
      "step": 9
    },
    {
      "epoch": 0.0017139429257005741,
      "eval_loss": 1.3284010887145996,
      "eval_runtime": 587.3458,
      "eval_samples_per_second": 4.183,
      "eval_steps_per_second": 2.092,
      "step": 10
    },
    {
      "epoch": 0.002056731510840689,
      "grad_norm": 10.381022453308105,
      "learning_rate": 8.18711994874345e-05,
      "loss": 5.3987,
      "step": 12
    },
    {
      "epoch": 0.0025709143885508613,
      "grad_norm": 1.8296691179275513,
      "learning_rate": 6.545084971874738e-05,
      "loss": 4.907,
      "step": 15
    },
    {
      "epoch": 0.0025709143885508613,
      "eval_loss": 1.2899432182312012,
      "eval_runtime": 587.3318,
      "eval_samples_per_second": 4.183,
      "eval_steps_per_second": 2.093,
      "step": 15
    },
    {
      "epoch": 0.0030850972662610334,
      "grad_norm": 1.917513132095337,
      "learning_rate": 4.6860474023534335e-05,
      "loss": 5.0149,
      "step": 18
    },
    {
      "epoch": 0.0034278858514011482,
      "eval_loss": 1.2484335899353027,
      "eval_runtime": 587.2531,
      "eval_samples_per_second": 4.184,
      "eval_steps_per_second": 2.093,
      "step": 20
    },
    {
      "epoch": 0.003599280143971206,
      "grad_norm": 1.8467648029327393,
      "learning_rate": 2.8711035421746367e-05,
      "loss": 4.9633,
      "step": 21
    },
    {
      "epoch": 0.004113463021681378,
      "grad_norm": 1.0094811916351318,
      "learning_rate": 1.3551568628929434e-05,
      "loss": 4.9854,
      "step": 24
    },
    {
      "epoch": 0.004284857314251435,
      "eval_loss": 1.2274752855300903,
      "eval_runtime": 589.1454,
      "eval_samples_per_second": 4.17,
      "eval_steps_per_second": 2.086,
      "step": 25
    },
    {
      "epoch": 0.0046276458993915505,
      "grad_norm": 1.3172191381454468,
      "learning_rate": 3.511175705587433e-06,
      "loss": 4.8362,
      "step": 27
    },
    {
      "epoch": 0.005141828777101723,
      "grad_norm": 5.663494110107422,
      "learning_rate": 0.0,
      "loss": 4.8685,
      "step": 30
    },
    {
      "epoch": 0.005141828777101723,
      "eval_loss": 1.2236804962158203,
      "eval_runtime": 587.2261,
      "eval_samples_per_second": 4.184,
      "eval_steps_per_second": 2.093,
      "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": 2.0935906689024e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}