last-checkpoint/trainer_state.json

{
  "best_metric": 0.5042169094085693,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.1366742596810934,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004555808656036446,
      "eval_loss": 0.6795058846473694,
      "eval_runtime": 15.6799,
      "eval_samples_per_second": 5.931,
      "eval_steps_per_second": 2.997,
      "step": 1
    },
    {
      "epoch": 0.01366742596810934,
      "grad_norm": 1.5004208087921143,
      "learning_rate": 6e-05,
      "loss": 2.8563,
      "step": 3
    },
    {
      "epoch": 0.022779043280182234,
      "eval_loss": 0.6548665165901184,
      "eval_runtime": 15.9971,
      "eval_samples_per_second": 5.814,
      "eval_steps_per_second": 2.938,
      "step": 5
    },
    {
      "epoch": 0.02733485193621868,
      "grad_norm": 1.222702145576477,
      "learning_rate": 9.96057350657239e-05,
      "loss": 2.6377,
      "step": 6
    },
    {
      "epoch": 0.04100227790432802,
      "grad_norm": 1.2079116106033325,
      "learning_rate": 9.381533400219318e-05,
      "loss": 2.425,
      "step": 9
    },
    {
      "epoch": 0.04555808656036447,
      "eval_loss": 0.5925781726837158,
      "eval_runtime": 16.4774,
      "eval_samples_per_second": 5.644,
      "eval_steps_per_second": 2.852,
      "step": 10
    },
    {
      "epoch": 0.05466970387243736,
      "grad_norm": 1.1079726219177246,
      "learning_rate": 8.18711994874345e-05,
      "loss": 2.3765,
      "step": 12
    },
    {
      "epoch": 0.0683371298405467,
      "grad_norm": 0.9152125120162964,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.1722,
      "step": 15
    },
    {
      "epoch": 0.0683371298405467,
      "eval_loss": 0.5529842972755432,
      "eval_runtime": 17.0438,
      "eval_samples_per_second": 5.457,
      "eval_steps_per_second": 2.758,
      "step": 15
    },
    {
      "epoch": 0.08200455580865604,
      "grad_norm": 1.1765227317810059,
      "learning_rate": 4.6860474023534335e-05,
      "loss": 2.0581,
      "step": 18
    },
    {
      "epoch": 0.09111617312072894,
      "eval_loss": 0.5212913155555725,
      "eval_runtime": 17.5468,
      "eval_samples_per_second": 5.3,
      "eval_steps_per_second": 2.679,
      "step": 20
    },
    {
      "epoch": 0.09567198177676538,
      "grad_norm": 1.2766376733779907,
      "learning_rate": 2.8711035421746367e-05,
      "loss": 2.1058,
      "step": 21
    },
    {
      "epoch": 0.10933940774487472,
      "grad_norm": 0.9969152808189392,
      "learning_rate": 1.3551568628929434e-05,
      "loss": 2.0709,
      "step": 24
    },
    {
      "epoch": 0.11389521640091116,
      "eval_loss": 0.5065757632255554,
      "eval_runtime": 17.9141,
      "eval_samples_per_second": 5.191,
      "eval_steps_per_second": 2.624,
      "step": 25
    },
    {
      "epoch": 0.12300683371298406,
      "grad_norm": 1.0334519147872925,
      "learning_rate": 3.511175705587433e-06,
      "loss": 1.9104,
      "step": 27
    },
    {
      "epoch": 0.1366742596810934,
      "grad_norm": 0.7895696759223938,
      "learning_rate": 0.0,
      "loss": 1.8227,
      "step": 30
    },
    {
      "epoch": 0.1366742596810934,
      "eval_loss": 0.5042169094085693,
      "eval_runtime": 18.0605,
      "eval_samples_per_second": 5.149,
      "eval_steps_per_second": 2.602,
      "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": 6907843156377600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}