last-checkpoint/trainer_state.json

{
  "best_metric": 1.5044535398483276,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.04643962848297214,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0015479876160990713,
      "eval_loss": 1.805627465248108,
      "eval_runtime": 94.7382,
      "eval_samples_per_second": 5.753,
      "eval_steps_per_second": 1.446,
      "step": 1
    },
    {
      "epoch": 0.0046439628482972135,
      "grad_norm": 0.9872960448265076,
      "learning_rate": 0.00012,
      "loss": 3.3352,
      "step": 3
    },
    {
      "epoch": 0.007739938080495356,
      "eval_loss": 1.7955187559127808,
      "eval_runtime": 95.5839,
      "eval_samples_per_second": 5.702,
      "eval_steps_per_second": 1.433,
      "step": 5
    },
    {
      "epoch": 0.009287925696594427,
      "grad_norm": 0.7129471302032471,
      "learning_rate": 0.0001992114701314478,
      "loss": 4.1967,
      "step": 6
    },
    {
      "epoch": 0.01393188854489164,
      "grad_norm": 0.6288610100746155,
      "learning_rate": 0.00018763066800438636,
      "loss": 4.4998,
      "step": 9
    },
    {
      "epoch": 0.015479876160990712,
      "eval_loss": 1.694563388824463,
      "eval_runtime": 96.3013,
      "eval_samples_per_second": 5.659,
      "eval_steps_per_second": 1.423,
      "step": 10
    },
    {
      "epoch": 0.018575851393188854,
      "grad_norm": 0.9878631234169006,
      "learning_rate": 0.000163742398974869,
      "loss": 5.1968,
      "step": 12
    },
    {
      "epoch": 0.02321981424148607,
      "grad_norm": 1.2192689180374146,
      "learning_rate": 0.00013090169943749476,
      "loss": 5.5031,
      "step": 15
    },
    {
      "epoch": 0.02321981424148607,
      "eval_loss": 1.5759881734848022,
      "eval_runtime": 95.0326,
      "eval_samples_per_second": 5.735,
      "eval_steps_per_second": 1.442,
      "step": 15
    },
    {
      "epoch": 0.02786377708978328,
      "grad_norm": 1.1136505603790283,
      "learning_rate": 9.372094804706867e-05,
      "loss": 5.7087,
      "step": 18
    },
    {
      "epoch": 0.030959752321981424,
      "eval_loss": 1.5170910358428955,
      "eval_runtime": 95.7178,
      "eval_samples_per_second": 5.694,
      "eval_steps_per_second": 1.431,
      "step": 20
    },
    {
      "epoch": 0.032507739938080496,
      "grad_norm": 1.0437849760055542,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 7.9916,
      "step": 21
    },
    {
      "epoch": 0.03715170278637771,
      "grad_norm": 1.031005620956421,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 8.3096,
      "step": 24
    },
    {
      "epoch": 0.03869969040247678,
      "eval_loss": 1.5103068351745605,
      "eval_runtime": 96.2893,
      "eval_samples_per_second": 5.66,
      "eval_steps_per_second": 1.423,
      "step": 25
    },
    {
      "epoch": 0.04179566563467492,
      "grad_norm": 1.2108943462371826,
      "learning_rate": 7.022351411174866e-06,
      "loss": 7.874,
      "step": 27
    },
    {
      "epoch": 0.04643962848297214,
      "grad_norm": 1.2310171127319336,
      "learning_rate": 0.0,
      "loss": 8.7045,
      "step": 30
    },
    {
      "epoch": 0.04643962848297214,
      "eval_loss": 1.5044535398483276,
      "eval_runtime": 96.2779,
      "eval_samples_per_second": 5.661,
      "eval_steps_per_second": 1.423,
      "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": 2.4995022646542336e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}