last-checkpoint/trainer_state.json

{
  "best_metric": 0.8783676028251648,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.007804878048780488,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00026016260162601624,
      "eval_loss": 2.312877655029297,
      "eval_runtime": 388.1629,
      "eval_samples_per_second": 4.171,
      "eval_steps_per_second": 2.087,
      "step": 1
    },
    {
      "epoch": 0.0007804878048780488,
      "grad_norm": 0.5346828103065491,
      "learning_rate": 6e-05,
      "loss": 2.1201,
      "step": 3
    },
    {
      "epoch": 0.0013008130081300813,
      "eval_loss": 2.1864817142486572,
      "eval_runtime": 389.2423,
      "eval_samples_per_second": 4.159,
      "eval_steps_per_second": 2.081,
      "step": 5
    },
    {
      "epoch": 0.0015609756097560976,
      "grad_norm": 0.5996714234352112,
      "learning_rate": 9.96057350657239e-05,
      "loss": 1.9013,
      "step": 6
    },
    {
      "epoch": 0.0023414634146341463,
      "grad_norm": 0.8071907758712769,
      "learning_rate": 9.381533400219318e-05,
      "loss": 1.7837,
      "step": 9
    },
    {
      "epoch": 0.0026016260162601626,
      "eval_loss": 1.6352452039718628,
      "eval_runtime": 389.293,
      "eval_samples_per_second": 4.159,
      "eval_steps_per_second": 2.081,
      "step": 10
    },
    {
      "epoch": 0.0031219512195121953,
      "grad_norm": 0.8198975920677185,
      "learning_rate": 8.18711994874345e-05,
      "loss": 1.4937,
      "step": 12
    },
    {
      "epoch": 0.003902439024390244,
      "grad_norm": 0.8055070638656616,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.4355,
      "step": 15
    },
    {
      "epoch": 0.003902439024390244,
      "eval_loss": 1.1900770664215088,
      "eval_runtime": 389.8734,
      "eval_samples_per_second": 4.153,
      "eval_steps_per_second": 2.078,
      "step": 15
    },
    {
      "epoch": 0.0046829268292682925,
      "grad_norm": 0.759701132774353,
      "learning_rate": 4.6860474023534335e-05,
      "loss": 1.0329,
      "step": 18
    },
    {
      "epoch": 0.005203252032520325,
      "eval_loss": 0.9712910652160645,
      "eval_runtime": 390.0118,
      "eval_samples_per_second": 4.151,
      "eval_steps_per_second": 2.077,
      "step": 20
    },
    {
      "epoch": 0.005463414634146341,
      "grad_norm": 0.5658571124076843,
      "learning_rate": 2.8711035421746367e-05,
      "loss": 0.7111,
      "step": 21
    },
    {
      "epoch": 0.006243902439024391,
      "grad_norm": 0.6791040301322937,
      "learning_rate": 1.3551568628929434e-05,
      "loss": 0.8109,
      "step": 24
    },
    {
      "epoch": 0.0065040650406504065,
      "eval_loss": 0.8912465572357178,
      "eval_runtime": 389.6568,
      "eval_samples_per_second": 4.155,
      "eval_steps_per_second": 2.079,
      "step": 25
    },
    {
      "epoch": 0.007024390243902439,
      "grad_norm": 0.6968145966529846,
      "learning_rate": 3.511175705587433e-06,
      "loss": 0.6507,
      "step": 27
    },
    {
      "epoch": 0.007804878048780488,
      "grad_norm": 0.5855252146720886,
      "learning_rate": 0.0,
      "loss": 0.7571,
      "step": 30
    },
    {
      "epoch": 0.007804878048780488,
      "eval_loss": 0.8783676028251648,
      "eval_runtime": 389.5073,
      "eval_samples_per_second": 4.157,
      "eval_steps_per_second": 2.08,
      "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": 2.097116079980544e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}