last-checkpoint/trainer_state.json

{
  "best_metric": 1.1307181119918823,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0023987526486227164,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.995842162075721e-05,
      "eval_loss": 1.3536641597747803,
      "eval_runtime": 2161.7269,
      "eval_samples_per_second": 2.436,
      "eval_steps_per_second": 1.218,
      "step": 1
    },
    {
      "epoch": 0.00023987526486227162,
      "grad_norm": 0.3365182876586914,
      "learning_rate": 6e-05,
      "loss": 5.524,
      "step": 3
    },
    {
      "epoch": 0.000399792108103786,
      "eval_loss": 1.3460044860839844,
      "eval_runtime": 2174.9102,
      "eval_samples_per_second": 2.421,
      "eval_steps_per_second": 1.211,
      "step": 5
    },
    {
      "epoch": 0.00047975052972454323,
      "grad_norm": 0.40158727765083313,
      "learning_rate": 9.96057350657239e-05,
      "loss": 4.8264,
      "step": 6
    },
    {
      "epoch": 0.0007196257945868149,
      "grad_norm": 0.8357996344566345,
      "learning_rate": 9.381533400219318e-05,
      "loss": 5.6176,
      "step": 9
    },
    {
      "epoch": 0.000799584216207572,
      "eval_loss": 1.2629597187042236,
      "eval_runtime": 2186.0862,
      "eval_samples_per_second": 2.409,
      "eval_steps_per_second": 1.204,
      "step": 10
    },
    {
      "epoch": 0.0009595010594490865,
      "grad_norm": 0.5372483730316162,
      "learning_rate": 8.18711994874345e-05,
      "loss": 4.3763,
      "step": 12
    },
    {
      "epoch": 0.0011993763243113582,
      "grad_norm": 1.4813607931137085,
      "learning_rate": 6.545084971874738e-05,
      "loss": 5.0135,
      "step": 15
    },
    {
      "epoch": 0.0011993763243113582,
      "eval_loss": 1.1908265352249146,
      "eval_runtime": 2180.4244,
      "eval_samples_per_second": 2.415,
      "eval_steps_per_second": 1.208,
      "step": 15
    },
    {
      "epoch": 0.0014392515891736297,
      "grad_norm": 0.6947051882743835,
      "learning_rate": 4.6860474023534335e-05,
      "loss": 4.6265,
      "step": 18
    },
    {
      "epoch": 0.001599168432415144,
      "eval_loss": 1.1513779163360596,
      "eval_runtime": 2167.3564,
      "eval_samples_per_second": 2.43,
      "eval_steps_per_second": 1.215,
      "step": 20
    },
    {
      "epoch": 0.0016791268540359014,
      "grad_norm": 1.2085144519805908,
      "learning_rate": 2.8711035421746367e-05,
      "loss": 4.9104,
      "step": 21
    },
    {
      "epoch": 0.001919002118898173,
      "grad_norm": 0.8079568147659302,
      "learning_rate": 1.3551568628929434e-05,
      "loss": 4.8164,
      "step": 24
    },
    {
      "epoch": 0.00199896054051893,
      "eval_loss": 1.1340821981430054,
      "eval_runtime": 2173.8469,
      "eval_samples_per_second": 2.422,
      "eval_steps_per_second": 1.211,
      "step": 25
    },
    {
      "epoch": 0.0021588773837604444,
      "grad_norm": 1.210515022277832,
      "learning_rate": 3.511175705587433e-06,
      "loss": 4.4874,
      "step": 27
    },
    {
      "epoch": 0.0023987526486227164,
      "grad_norm": 0.7460294365882874,
      "learning_rate": 0.0,
      "loss": 4.2342,
      "step": 30
    },
    {
      "epoch": 0.0023987526486227164,
      "eval_loss": 1.1307181119918823,
      "eval_runtime": 2174.342,
      "eval_samples_per_second": 2.422,
      "eval_steps_per_second": 1.211,
      "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": 4.275523911942144e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}