last-checkpoint/trainer_state.json

{
  "best_metric": 2.5815908908843994,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.22018348623853212,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007339449541284404,
      "eval_loss": 3.7485382556915283,
      "eval_runtime": 3.3127,
      "eval_samples_per_second": 34.714,
      "eval_steps_per_second": 8.754,
      "step": 1
    },
    {
      "epoch": 0.022018348623853212,
      "grad_norm": 4.114450454711914,
      "learning_rate": 0.00012,
      "loss": 3.4035,
      "step": 3
    },
    {
      "epoch": 0.03669724770642202,
      "eval_loss": 3.4415414333343506,
      "eval_runtime": 2.6948,
      "eval_samples_per_second": 42.675,
      "eval_steps_per_second": 10.761,
      "step": 5
    },
    {
      "epoch": 0.044036697247706424,
      "grad_norm": 1.2108731269836426,
      "learning_rate": 0.0001992114701314478,
      "loss": 3.1586,
      "step": 6
    },
    {
      "epoch": 0.06605504587155964,
      "grad_norm": 1.4439945220947266,
      "learning_rate": 0.00018763066800438636,
      "loss": 2.9599,
      "step": 9
    },
    {
      "epoch": 0.07339449541284404,
      "eval_loss": 3.118781328201294,
      "eval_runtime": 2.6954,
      "eval_samples_per_second": 42.665,
      "eval_steps_per_second": 10.759,
      "step": 10
    },
    {
      "epoch": 0.08807339449541285,
      "grad_norm": 1.8563435077667236,
      "learning_rate": 0.000163742398974869,
      "loss": 2.9979,
      "step": 12
    },
    {
      "epoch": 0.11009174311926606,
      "grad_norm": 1.7265347242355347,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.8441,
      "step": 15
    },
    {
      "epoch": 0.11009174311926606,
      "eval_loss": 2.881464719772339,
      "eval_runtime": 2.7172,
      "eval_samples_per_second": 42.323,
      "eval_steps_per_second": 10.673,
      "step": 15
    },
    {
      "epoch": 0.13211009174311927,
      "grad_norm": 1.7133402824401855,
      "learning_rate": 9.372094804706867e-05,
      "loss": 2.9017,
      "step": 18
    },
    {
      "epoch": 0.14678899082568808,
      "eval_loss": 2.697143793106079,
      "eval_runtime": 2.7176,
      "eval_samples_per_second": 42.316,
      "eval_steps_per_second": 10.671,
      "step": 20
    },
    {
      "epoch": 0.15412844036697249,
      "grad_norm": 1.463902473449707,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 3.0289,
      "step": 21
    },
    {
      "epoch": 0.1761467889908257,
      "grad_norm": 1.6114941835403442,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 2.8876,
      "step": 24
    },
    {
      "epoch": 0.1834862385321101,
      "eval_loss": 2.6056313514709473,
      "eval_runtime": 2.7128,
      "eval_samples_per_second": 42.392,
      "eval_steps_per_second": 10.69,
      "step": 25
    },
    {
      "epoch": 0.1981651376146789,
      "grad_norm": 1.7031934261322021,
      "learning_rate": 7.022351411174866e-06,
      "loss": 2.769,
      "step": 27
    },
    {
      "epoch": 0.22018348623853212,
      "grad_norm": 1.8348661661148071,
      "learning_rate": 0.0,
      "loss": 2.8255,
      "step": 30
    },
    {
      "epoch": 0.22018348623853212,
      "eval_loss": 2.5815908908843994,
      "eval_runtime": 2.7124,
      "eval_samples_per_second": 42.397,
      "eval_steps_per_second": 10.692,
      "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": 939612570648576.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}