last-checkpoint/trainer_state.json

{
  "best_metric": 2.1441922187805176,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.07416563658838071,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002472187886279357,
      "eval_loss": 4.246246337890625,
      "eval_runtime": 19.0216,
      "eval_samples_per_second": 8.99,
      "eval_steps_per_second": 4.521,
      "step": 1
    },
    {
      "epoch": 0.007416563658838072,
      "grad_norm": 10.726256370544434,
      "learning_rate": 6e-05,
      "loss": 4.0187,
      "step": 3
    },
    {
      "epoch": 0.012360939431396786,
      "eval_loss": 3.4326891899108887,
      "eval_runtime": 19.2672,
      "eval_samples_per_second": 8.875,
      "eval_steps_per_second": 4.464,
      "step": 5
    },
    {
      "epoch": 0.014833127317676144,
      "grad_norm": 3.003781795501709,
      "learning_rate": 9.96057350657239e-05,
      "loss": 2.6233,
      "step": 6
    },
    {
      "epoch": 0.022249690976514216,
      "grad_norm": 4.652129650115967,
      "learning_rate": 9.381533400219318e-05,
      "loss": 2.6825,
      "step": 9
    },
    {
      "epoch": 0.024721878862793572,
      "eval_loss": 2.6831576824188232,
      "eval_runtime": 19.4466,
      "eval_samples_per_second": 8.793,
      "eval_steps_per_second": 4.422,
      "step": 10
    },
    {
      "epoch": 0.029666254635352288,
      "grad_norm": 3.498692512512207,
      "learning_rate": 8.18711994874345e-05,
      "loss": 2.3456,
      "step": 12
    },
    {
      "epoch": 0.037082818294190356,
      "grad_norm": 2.6216788291931152,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.2626,
      "step": 15
    },
    {
      "epoch": 0.037082818294190356,
      "eval_loss": 2.3840250968933105,
      "eval_runtime": 19.4798,
      "eval_samples_per_second": 8.778,
      "eval_steps_per_second": 4.415,
      "step": 15
    },
    {
      "epoch": 0.04449938195302843,
      "grad_norm": 5.1422119140625,
      "learning_rate": 4.6860474023534335e-05,
      "loss": 2.3753,
      "step": 18
    },
    {
      "epoch": 0.049443757725587144,
      "eval_loss": 2.2322804927825928,
      "eval_runtime": 19.4705,
      "eval_samples_per_second": 8.783,
      "eval_steps_per_second": 4.417,
      "step": 20
    },
    {
      "epoch": 0.0519159456118665,
      "grad_norm": 3.4997880458831787,
      "learning_rate": 2.8711035421746367e-05,
      "loss": 2.1201,
      "step": 21
    },
    {
      "epoch": 0.059332509270704575,
      "grad_norm": 2.5502889156341553,
      "learning_rate": 1.3551568628929434e-05,
      "loss": 2.2191,
      "step": 24
    },
    {
      "epoch": 0.06180469715698393,
      "eval_loss": 2.1556434631347656,
      "eval_runtime": 19.5005,
      "eval_samples_per_second": 8.769,
      "eval_steps_per_second": 4.41,
      "step": 25
    },
    {
      "epoch": 0.06674907292954264,
      "grad_norm": 2.8522839546203613,
      "learning_rate": 3.511175705587433e-06,
      "loss": 2.1255,
      "step": 27
    },
    {
      "epoch": 0.07416563658838071,
      "grad_norm": 3.1214613914489746,
      "learning_rate": 0.0,
      "loss": 2.0176,
      "step": 30
    },
    {
      "epoch": 0.07416563658838071,
      "eval_loss": 2.1441922187805176,
      "eval_runtime": 19.3607,
      "eval_samples_per_second": 8.832,
      "eval_steps_per_second": 4.442,
      "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": 6148595908608000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}