last-checkpoint/trainer_state.json

{
  "best_metric": 1.1657742261886597,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.013637913399249914,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004545971133083305,
      "eval_loss": 3.485039472579956,
      "eval_runtime": 19.1059,
      "eval_samples_per_second": 48.519,
      "eval_steps_per_second": 24.286,
      "step": 1
    },
    {
      "epoch": 0.0013637913399249914,
      "grad_norm": 38.438690185546875,
      "learning_rate": 6e-05,
      "loss": 14.3659,
      "step": 3
    },
    {
      "epoch": 0.0022729855665416525,
      "eval_loss": 3.2369225025177,
      "eval_runtime": 18.2615,
      "eval_samples_per_second": 50.762,
      "eval_steps_per_second": 25.409,
      "step": 5
    },
    {
      "epoch": 0.002727582679849983,
      "grad_norm": 30.468904495239258,
      "learning_rate": 0.00012,
      "loss": 13.2861,
      "step": 6
    },
    {
      "epoch": 0.004091374019774974,
      "grad_norm": 41.03653335571289,
      "learning_rate": 0.00018,
      "loss": 11.8079,
      "step": 9
    },
    {
      "epoch": 0.004545971133083305,
      "eval_loss": 2.384409189224243,
      "eval_runtime": 18.5059,
      "eval_samples_per_second": 50.092,
      "eval_steps_per_second": 25.073,
      "step": 10
    },
    {
      "epoch": 0.005455165359699966,
      "grad_norm": 54.090476989746094,
      "learning_rate": 0.00019510565162951537,
      "loss": 8.9845,
      "step": 12
    },
    {
      "epoch": 0.006818956699624957,
      "grad_norm": 73.95587158203125,
      "learning_rate": 0.00017071067811865476,
      "loss": 7.8594,
      "step": 15
    },
    {
      "epoch": 0.006818956699624957,
      "eval_loss": 1.647464394569397,
      "eval_runtime": 18.413,
      "eval_samples_per_second": 50.345,
      "eval_steps_per_second": 25.2,
      "step": 15
    },
    {
      "epoch": 0.008182748039549948,
      "grad_norm": 69.89231872558594,
      "learning_rate": 0.00013090169943749476,
      "loss": 6.4651,
      "step": 18
    },
    {
      "epoch": 0.00909194226616661,
      "eval_loss": 1.32905113697052,
      "eval_runtime": 18.4232,
      "eval_samples_per_second": 50.317,
      "eval_steps_per_second": 25.186,
      "step": 20
    },
    {
      "epoch": 0.00954653937947494,
      "grad_norm": 73.37672424316406,
      "learning_rate": 8.435655349597689e-05,
      "loss": 5.3644,
      "step": 21
    },
    {
      "epoch": 0.010910330719399931,
      "grad_norm": 99.907470703125,
      "learning_rate": 4.12214747707527e-05,
      "loss": 5.429,
      "step": 24
    },
    {
      "epoch": 0.011364927832708262,
      "eval_loss": 1.1906145811080933,
      "eval_runtime": 18.3446,
      "eval_samples_per_second": 50.533,
      "eval_steps_per_second": 25.294,
      "step": 25
    },
    {
      "epoch": 0.012274122059324924,
      "grad_norm": 113.60340118408203,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 4.7822,
      "step": 27
    },
    {
      "epoch": 0.013637913399249914,
      "grad_norm": 84.72586059570312,
      "learning_rate": 0.0,
      "loss": 5.0929,
      "step": 30
    },
    {
      "epoch": 0.013637913399249914,
      "eval_loss": 1.1657742261886597,
      "eval_runtime": 18.4659,
      "eval_samples_per_second": 50.201,
      "eval_steps_per_second": 25.127,
      "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": 531009959362560.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}