last-checkpoint/trainer_state.json

{
  "best_metric": 1.9001489877700806,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.001828278903946797,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.141394519733986e-05,
      "eval_loss": 2.204296588897705,
      "eval_runtime": 1461.3328,
      "eval_samples_per_second": 3.153,
      "eval_steps_per_second": 1.577,
      "step": 1
    },
    {
      "epoch": 0.00027424183559201956,
      "grad_norm": 0.5886942744255066,
      "learning_rate": 3e-05,
      "loss": 2.2122,
      "step": 3
    },
    {
      "epoch": 0.00045706972598669925,
      "eval_loss": 2.177161931991577,
      "eval_runtime": 1464.7054,
      "eval_samples_per_second": 3.145,
      "eval_steps_per_second": 1.573,
      "step": 5
    },
    {
      "epoch": 0.0005484836711840391,
      "grad_norm": 0.5571932196617126,
      "learning_rate": 6e-05,
      "loss": 2.089,
      "step": 6
    },
    {
      "epoch": 0.0008227255067760587,
      "grad_norm": 0.5330421924591064,
      "learning_rate": 9e-05,
      "loss": 2.1463,
      "step": 9
    },
    {
      "epoch": 0.0009141394519733985,
      "eval_loss": 2.044189214706421,
      "eval_runtime": 1463.8478,
      "eval_samples_per_second": 3.147,
      "eval_steps_per_second": 1.574,
      "step": 10
    },
    {
      "epoch": 0.0010969673423680782,
      "grad_norm": 0.6598482728004456,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.0666,
      "step": 12
    },
    {
      "epoch": 0.0013712091779600978,
      "grad_norm": 0.5164814591407776,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.982,
      "step": 15
    },
    {
      "epoch": 0.0013712091779600978,
      "eval_loss": 1.9511953592300415,
      "eval_runtime": 1464.7107,
      "eval_samples_per_second": 3.145,
      "eval_steps_per_second": 1.573,
      "step": 15
    },
    {
      "epoch": 0.0016454510135521174,
      "grad_norm": 0.4864216148853302,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.9117,
      "step": 18
    },
    {
      "epoch": 0.001828278903946797,
      "eval_loss": 1.9001489877700806,
      "eval_runtime": 1463.8603,
      "eval_samples_per_second": 3.147,
      "eval_steps_per_second": 1.574,
      "step": 20
    }
  ],
  "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": 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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6132638865162240.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}