last-checkpoint/trainer_state.json

{
  "best_metric": 1.012827754020691,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.060240963855421686,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002008032128514056,
      "eval_loss": 1.3232147693634033,
      "eval_runtime": 72.9359,
      "eval_samples_per_second": 2.879,
      "eval_steps_per_second": 1.44,
      "step": 1
    },
    {
      "epoch": 0.006024096385542169,
      "grad_norm": 1.1903401613235474,
      "learning_rate": 6e-05,
      "loss": 5.3337,
      "step": 3
    },
    {
      "epoch": 0.010040160642570281,
      "eval_loss": 1.29500150680542,
      "eval_runtime": 73.686,
      "eval_samples_per_second": 2.85,
      "eval_steps_per_second": 1.425,
      "step": 5
    },
    {
      "epoch": 0.012048192771084338,
      "grad_norm": 3.233403444290161,
      "learning_rate": 9.96057350657239e-05,
      "loss": 5.3897,
      "step": 6
    },
    {
      "epoch": 0.018072289156626505,
      "grad_norm": 1.7138043642044067,
      "learning_rate": 9.381533400219318e-05,
      "loss": 4.3576,
      "step": 9
    },
    {
      "epoch": 0.020080321285140562,
      "eval_loss": 1.1749109029769897,
      "eval_runtime": 73.6686,
      "eval_samples_per_second": 2.851,
      "eval_steps_per_second": 1.425,
      "step": 10
    },
    {
      "epoch": 0.024096385542168676,
      "grad_norm": 1.7703816890716553,
      "learning_rate": 8.18711994874345e-05,
      "loss": 4.5346,
      "step": 12
    },
    {
      "epoch": 0.030120481927710843,
      "grad_norm": 8.211416244506836,
      "learning_rate": 6.545084971874738e-05,
      "loss": 4.7168,
      "step": 15
    },
    {
      "epoch": 0.030120481927710843,
      "eval_loss": 1.092099905014038,
      "eval_runtime": 73.6836,
      "eval_samples_per_second": 2.85,
      "eval_steps_per_second": 1.425,
      "step": 15
    },
    {
      "epoch": 0.03614457831325301,
      "grad_norm": 1.9411234855651855,
      "learning_rate": 4.6860474023534335e-05,
      "loss": 4.1431,
      "step": 18
    },
    {
      "epoch": 0.040160642570281124,
      "eval_loss": 1.0417708158493042,
      "eval_runtime": 73.76,
      "eval_samples_per_second": 2.847,
      "eval_steps_per_second": 1.424,
      "step": 20
    },
    {
      "epoch": 0.04216867469879518,
      "grad_norm": 1.9102998971939087,
      "learning_rate": 2.8711035421746367e-05,
      "loss": 4.5056,
      "step": 21
    },
    {
      "epoch": 0.04819277108433735,
      "grad_norm": 3.732218027114868,
      "learning_rate": 1.3551568628929434e-05,
      "loss": 4.1749,
      "step": 24
    },
    {
      "epoch": 0.050200803212851405,
      "eval_loss": 1.0177347660064697,
      "eval_runtime": 73.6595,
      "eval_samples_per_second": 2.851,
      "eval_steps_per_second": 1.425,
      "step": 25
    },
    {
      "epoch": 0.05421686746987952,
      "grad_norm": 2.0057742595672607,
      "learning_rate": 3.511175705587433e-06,
      "loss": 3.7961,
      "step": 27
    },
    {
      "epoch": 0.060240963855421686,
      "grad_norm": 3.3194940090179443,
      "learning_rate": 0.0,
      "loss": 4.241,
      "step": 30
    },
    {
      "epoch": 0.060240963855421686,
      "eval_loss": 1.012827754020691,
      "eval_runtime": 73.608,
      "eval_samples_per_second": 2.853,
      "eval_steps_per_second": 1.426,
      "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": 3.84041276669952e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}