last-checkpoint/trainer_state.json

{
  "best_metric": 2.087597370147705,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.030627871362940276,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0010209290454313426,
      "eval_loss": 3.0864973068237305,
      "eval_runtime": 52.0325,
      "eval_samples_per_second": 7.937,
      "eval_steps_per_second": 3.978,
      "step": 1
    },
    {
      "epoch": 0.0030627871362940277,
      "grad_norm": 24.415424346923828,
      "learning_rate": 0.00012,
      "loss": 12.7208,
      "step": 3
    },
    {
      "epoch": 0.005104645227156712,
      "eval_loss": 2.5484511852264404,
      "eval_runtime": 52.5279,
      "eval_samples_per_second": 7.862,
      "eval_steps_per_second": 3.941,
      "step": 5
    },
    {
      "epoch": 0.006125574272588055,
      "grad_norm": 24.095373153686523,
      "learning_rate": 0.0001992114701314478,
      "loss": 10.8247,
      "step": 6
    },
    {
      "epoch": 0.009188361408882083,
      "grad_norm": 14.555842399597168,
      "learning_rate": 0.00018763066800438636,
      "loss": 9.9244,
      "step": 9
    },
    {
      "epoch": 0.010209290454313425,
      "eval_loss": 2.232063055038452,
      "eval_runtime": 52.5941,
      "eval_samples_per_second": 7.853,
      "eval_steps_per_second": 3.936,
      "step": 10
    },
    {
      "epoch": 0.01225114854517611,
      "grad_norm": 18.837717056274414,
      "learning_rate": 0.000163742398974869,
      "loss": 8.848,
      "step": 12
    },
    {
      "epoch": 0.015313935681470138,
      "grad_norm": 14.514394760131836,
      "learning_rate": 0.00013090169943749476,
      "loss": 8.7625,
      "step": 15
    },
    {
      "epoch": 0.015313935681470138,
      "eval_loss": 2.162187099456787,
      "eval_runtime": 52.6223,
      "eval_samples_per_second": 7.848,
      "eval_steps_per_second": 3.934,
      "step": 15
    },
    {
      "epoch": 0.018376722817764167,
      "grad_norm": 15.687775611877441,
      "learning_rate": 9.372094804706867e-05,
      "loss": 9.2225,
      "step": 18
    },
    {
      "epoch": 0.02041858090862685,
      "eval_loss": 2.114116907119751,
      "eval_runtime": 52.6336,
      "eval_samples_per_second": 7.847,
      "eval_steps_per_second": 3.933,
      "step": 20
    },
    {
      "epoch": 0.021439509954058193,
      "grad_norm": 13.704133033752441,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 8.6983,
      "step": 21
    },
    {
      "epoch": 0.02450229709035222,
      "grad_norm": 15.463887214660645,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 8.0824,
      "step": 24
    },
    {
      "epoch": 0.025523226135783564,
      "eval_loss": 2.0934205055236816,
      "eval_runtime": 52.6375,
      "eval_samples_per_second": 7.846,
      "eval_steps_per_second": 3.933,
      "step": 25
    },
    {
      "epoch": 0.027565084226646247,
      "grad_norm": 12.577512741088867,
      "learning_rate": 7.022351411174866e-06,
      "loss": 7.9226,
      "step": 27
    },
    {
      "epoch": 0.030627871362940276,
      "grad_norm": 13.241372108459473,
      "learning_rate": 0.0,
      "loss": 8.4831,
      "step": 30
    },
    {
      "epoch": 0.030627871362940276,
      "eval_loss": 2.087597370147705,
      "eval_runtime": 52.6034,
      "eval_samples_per_second": 7.851,
      "eval_steps_per_second": 3.935,
      "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": 1.054694852001792e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}