last-checkpoint/trainer_state.json

{
  "best_metric": 1.1647752523422241,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.010217113665389528,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00034057045551298427,
      "eval_loss": 1.4796850681304932,
      "eval_runtime": 77.2735,
      "eval_samples_per_second": 16.008,
      "eval_steps_per_second": 8.011,
      "step": 1
    },
    {
      "epoch": 0.0010217113665389529,
      "grad_norm": 0.3619253933429718,
      "learning_rate": 6e-05,
      "loss": 1.3417,
      "step": 3
    },
    {
      "epoch": 0.0017028522775649213,
      "eval_loss": 1.4528995752334595,
      "eval_runtime": 76.1685,
      "eval_samples_per_second": 16.24,
      "eval_steps_per_second": 8.127,
      "step": 5
    },
    {
      "epoch": 0.0020434227330779057,
      "grad_norm": 0.5582008361816406,
      "learning_rate": 0.00012,
      "loss": 1.2895,
      "step": 6
    },
    {
      "epoch": 0.0030651340996168583,
      "grad_norm": 0.46947911381721497,
      "learning_rate": 0.00018,
      "loss": 1.3007,
      "step": 9
    },
    {
      "epoch": 0.0034057045551298426,
      "eval_loss": 1.2965959310531616,
      "eval_runtime": 76.7936,
      "eval_samples_per_second": 16.108,
      "eval_steps_per_second": 8.061,
      "step": 10
    },
    {
      "epoch": 0.004086845466155811,
      "grad_norm": 0.5418891310691833,
      "learning_rate": 0.00019510565162951537,
      "loss": 1.2131,
      "step": 12
    },
    {
      "epoch": 0.005108556832694764,
      "grad_norm": 0.5988765358924866,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.3546,
      "step": 15
    },
    {
      "epoch": 0.005108556832694764,
      "eval_loss": 1.225139856338501,
      "eval_runtime": 76.1545,
      "eval_samples_per_second": 16.243,
      "eval_steps_per_second": 8.128,
      "step": 15
    },
    {
      "epoch": 0.006130268199233717,
      "grad_norm": 0.36577218770980835,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.1357,
      "step": 18
    },
    {
      "epoch": 0.006811409110259685,
      "eval_loss": 1.1818900108337402,
      "eval_runtime": 75.864,
      "eval_samples_per_second": 16.305,
      "eval_steps_per_second": 8.159,
      "step": 20
    },
    {
      "epoch": 0.007151979565772669,
      "grad_norm": 0.46006566286087036,
      "learning_rate": 8.435655349597689e-05,
      "loss": 1.038,
      "step": 21
    },
    {
      "epoch": 0.008173690932311623,
      "grad_norm": 0.3569260239601135,
      "learning_rate": 4.12214747707527e-05,
      "loss": 1.0024,
      "step": 24
    },
    {
      "epoch": 0.008514261387824606,
      "eval_loss": 1.16751229763031,
      "eval_runtime": 76.089,
      "eval_samples_per_second": 16.257,
      "eval_steps_per_second": 8.135,
      "step": 25
    },
    {
      "epoch": 0.009195402298850575,
      "grad_norm": 0.39700376987457275,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 1.1828,
      "step": 27
    },
    {
      "epoch": 0.010217113665389528,
      "grad_norm": 0.3018814027309418,
      "learning_rate": 0.0,
      "loss": 0.9282,
      "step": 30
    },
    {
      "epoch": 0.010217113665389528,
      "eval_loss": 1.1647752523422241,
      "eval_runtime": 76.0133,
      "eval_samples_per_second": 16.273,
      "eval_steps_per_second": 8.143,
      "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": 1.123859998703616e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}