last-checkpoint/trainer_state.json

{
  "best_metric": 3.917762517929077,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.11142061281337047,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003714020427112349,
      "eval_loss": 4.782369613647461,
      "eval_runtime": 1.6798,
      "eval_samples_per_second": 67.864,
      "eval_steps_per_second": 33.932,
      "step": 1
    },
    {
      "epoch": 0.011142061281337047,
      "grad_norm": 54.0533561706543,
      "learning_rate": 6e-05,
      "loss": 19.5438,
      "step": 3
    },
    {
      "epoch": 0.018570102135561744,
      "eval_loss": 4.678945064544678,
      "eval_runtime": 1.5127,
      "eval_samples_per_second": 75.361,
      "eval_steps_per_second": 37.681,
      "step": 5
    },
    {
      "epoch": 0.022284122562674095,
      "grad_norm": 56.725921630859375,
      "learning_rate": 0.00012,
      "loss": 18.7701,
      "step": 6
    },
    {
      "epoch": 0.033426183844011144,
      "grad_norm": 71.2812271118164,
      "learning_rate": 0.00018,
      "loss": 17.9677,
      "step": 9
    },
    {
      "epoch": 0.03714020427112349,
      "eval_loss": 4.367871284484863,
      "eval_runtime": 1.5412,
      "eval_samples_per_second": 73.97,
      "eval_steps_per_second": 36.985,
      "step": 10
    },
    {
      "epoch": 0.04456824512534819,
      "grad_norm": 67.70091247558594,
      "learning_rate": 0.00019510565162951537,
      "loss": 17.368,
      "step": 12
    },
    {
      "epoch": 0.055710306406685235,
      "grad_norm": 54.72442626953125,
      "learning_rate": 0.00017071067811865476,
      "loss": 16.9793,
      "step": 15
    },
    {
      "epoch": 0.055710306406685235,
      "eval_loss": 4.158687591552734,
      "eval_runtime": 1.6037,
      "eval_samples_per_second": 71.087,
      "eval_steps_per_second": 35.543,
      "step": 15
    },
    {
      "epoch": 0.06685236768802229,
      "grad_norm": 56.00122833251953,
      "learning_rate": 0.00013090169943749476,
      "loss": 16.5656,
      "step": 18
    },
    {
      "epoch": 0.07428040854224698,
      "eval_loss": 4.013300895690918,
      "eval_runtime": 1.5399,
      "eval_samples_per_second": 74.033,
      "eval_steps_per_second": 37.016,
      "step": 20
    },
    {
      "epoch": 0.07799442896935933,
      "grad_norm": 57.77225875854492,
      "learning_rate": 8.435655349597689e-05,
      "loss": 15.3251,
      "step": 21
    },
    {
      "epoch": 0.08913649025069638,
      "grad_norm": 55.74565505981445,
      "learning_rate": 4.12214747707527e-05,
      "loss": 15.7606,
      "step": 24
    },
    {
      "epoch": 0.09285051067780872,
      "eval_loss": 3.9420642852783203,
      "eval_runtime": 1.5667,
      "eval_samples_per_second": 72.763,
      "eval_steps_per_second": 36.381,
      "step": 25
    },
    {
      "epoch": 0.10027855153203342,
      "grad_norm": 47.04991912841797,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 15.861,
      "step": 27
    },
    {
      "epoch": 0.11142061281337047,
      "grad_norm": 54.018978118896484,
      "learning_rate": 0.0,
      "loss": 15.701,
      "step": 30
    },
    {
      "epoch": 0.11142061281337047,
      "eval_loss": 3.917762517929077,
      "eval_runtime": 1.5431,
      "eval_samples_per_second": 73.876,
      "eval_steps_per_second": 36.938,
      "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
}