last-checkpoint/trainer_state.json

{
  "best_metric": 3.018038034439087,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.007144898542440698,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002857959416976279,
      "eval_loss": 4.963686466217041,
      "eval_runtime": 296.5888,
      "eval_samples_per_second": 1.244,
      "eval_steps_per_second": 0.624,
      "step": 1
    },
    {
      "epoch": 0.0008573878250928837,
      "grad_norm": 2.6134703159332275,
      "learning_rate": 6e-05,
      "loss": 5.0445,
      "step": 3
    },
    {
      "epoch": 0.0014289797084881394,
      "eval_loss": 4.825920581817627,
      "eval_runtime": 299.1976,
      "eval_samples_per_second": 1.233,
      "eval_steps_per_second": 0.618,
      "step": 5
    },
    {
      "epoch": 0.0017147756501857674,
      "grad_norm": 3.211954355239868,
      "learning_rate": 0.00012,
      "loss": 4.6684,
      "step": 6
    },
    {
      "epoch": 0.002572163475278651,
      "grad_norm": 2.1706066131591797,
      "learning_rate": 0.00018,
      "loss": 4.2696,
      "step": 9
    },
    {
      "epoch": 0.002857959416976279,
      "eval_loss": 3.896904230117798,
      "eval_runtime": 298.3189,
      "eval_samples_per_second": 1.237,
      "eval_steps_per_second": 0.62,
      "step": 10
    },
    {
      "epoch": 0.003429551300371535,
      "grad_norm": 3.820838689804077,
      "learning_rate": 0.0001913545457642601,
      "loss": 3.7342,
      "step": 12
    },
    {
      "epoch": 0.004286939125464418,
      "grad_norm": 5.012720108032227,
      "learning_rate": 0.00015000000000000001,
      "loss": 3.0239,
      "step": 15
    },
    {
      "epoch": 0.004286939125464418,
      "eval_loss": 3.110426425933838,
      "eval_runtime": 296.7733,
      "eval_samples_per_second": 1.243,
      "eval_steps_per_second": 0.623,
      "step": 15
    },
    {
      "epoch": 0.005144326950557302,
      "grad_norm": 3.8188817501068115,
      "learning_rate": 8.954715367323468e-05,
      "loss": 3.3092,
      "step": 18
    },
    {
      "epoch": 0.005715918833952558,
      "eval_loss": 3.0547516345977783,
      "eval_runtime": 299.4253,
      "eval_samples_per_second": 1.232,
      "eval_steps_per_second": 0.618,
      "step": 20
    },
    {
      "epoch": 0.006001714775650186,
      "grad_norm": 8.518135070800781,
      "learning_rate": 3.308693936411421e-05,
      "loss": 2.9221,
      "step": 21
    },
    {
      "epoch": 0.00685910260074307,
      "grad_norm": 8.406867980957031,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 2.8685,
      "step": 24
    },
    {
      "epoch": 0.007144898542440698,
      "eval_loss": 3.018038034439087,
      "eval_runtime": 296.5175,
      "eval_samples_per_second": 1.244,
      "eval_steps_per_second": 0.624,
      "step": 25
    }
  ],
  "logging_steps": 3,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": 3967393726464000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}