last-checkpoint/trainer_state.json

{
  "best_metric": 2.368725299835205,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.005196154845414394,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001732051615138131,
      "eval_loss": 8.650031089782715,
      "eval_runtime": 353.3612,
      "eval_samples_per_second": 6.88,
      "eval_steps_per_second": 3.441,
      "step": 1
    },
    {
      "epoch": 0.0005196154845414394,
      "grad_norm": 9.004079818725586,
      "learning_rate": 0.00012,
      "loss": 6.4558,
      "step": 3
    },
    {
      "epoch": 0.0008660258075690655,
      "eval_loss": 6.17396879196167,
      "eval_runtime": 356.3946,
      "eval_samples_per_second": 6.821,
      "eval_steps_per_second": 3.412,
      "step": 5
    },
    {
      "epoch": 0.0010392309690828788,
      "grad_norm": 18.178464889526367,
      "learning_rate": 0.0001992114701314478,
      "loss": 5.7051,
      "step": 6
    },
    {
      "epoch": 0.001558846453624318,
      "grad_norm": 26.80777931213379,
      "learning_rate": 0.00018763066800438636,
      "loss": 3.9092,
      "step": 9
    },
    {
      "epoch": 0.001732051615138131,
      "eval_loss": 2.6880009174346924,
      "eval_runtime": 356.8594,
      "eval_samples_per_second": 6.812,
      "eval_steps_per_second": 3.408,
      "step": 10
    },
    {
      "epoch": 0.0020784619381657575,
      "grad_norm": 4.757950305938721,
      "learning_rate": 0.000163742398974869,
      "loss": 2.4351,
      "step": 12
    },
    {
      "epoch": 0.002598077422707197,
      "grad_norm": 3.0368690490722656,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.4886,
      "step": 15
    },
    {
      "epoch": 0.002598077422707197,
      "eval_loss": 2.514369249343872,
      "eval_runtime": 356.622,
      "eval_samples_per_second": 6.817,
      "eval_steps_per_second": 3.41,
      "step": 15
    },
    {
      "epoch": 0.003117692907248636,
      "grad_norm": 3.3173792362213135,
      "learning_rate": 9.372094804706867e-05,
      "loss": 2.5876,
      "step": 18
    },
    {
      "epoch": 0.003464103230276262,
      "eval_loss": 2.4166297912597656,
      "eval_runtime": 356.3483,
      "eval_samples_per_second": 6.822,
      "eval_steps_per_second": 3.412,
      "step": 20
    },
    {
      "epoch": 0.0036373083917900753,
      "grad_norm": 3.117248058319092,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 2.2366,
      "step": 21
    },
    {
      "epoch": 0.004156923876331515,
      "grad_norm": 2.577366590499878,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 2.4647,
      "step": 24
    },
    {
      "epoch": 0.004330129037845328,
      "eval_loss": 2.3770086765289307,
      "eval_runtime": 356.25,
      "eval_samples_per_second": 6.824,
      "eval_steps_per_second": 3.413,
      "step": 25
    },
    {
      "epoch": 0.004676539360872954,
      "grad_norm": 4.037468910217285,
      "learning_rate": 7.022351411174866e-06,
      "loss": 2.3905,
      "step": 27
    },
    {
      "epoch": 0.005196154845414394,
      "grad_norm": 2.5198121070861816,
      "learning_rate": 0.0,
      "loss": 2.1613,
      "step": 30
    },
    {
      "epoch": 0.005196154845414394,
      "eval_loss": 2.368725299835205,
      "eval_runtime": 356.3348,
      "eval_samples_per_second": 6.822,
      "eval_steps_per_second": 3.413,
      "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": 1.150341542313984e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}