last-checkpoint/trainer_state.json

{
  "best_metric": 11.018196105957031,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.18518518518518517,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006172839506172839,
      "eval_loss": 11.094608306884766,
      "eval_runtime": 0.7155,
      "eval_samples_per_second": 96.44,
      "eval_steps_per_second": 48.919,
      "step": 1
    },
    {
      "epoch": 0.018518518518518517,
      "grad_norm": 1.146418809890747,
      "learning_rate": 6e-05,
      "loss": 44.3908,
      "step": 3
    },
    {
      "epoch": 0.030864197530864196,
      "eval_loss": 11.090897560119629,
      "eval_runtime": 0.3536,
      "eval_samples_per_second": 195.159,
      "eval_steps_per_second": 98.994,
      "step": 5
    },
    {
      "epoch": 0.037037037037037035,
      "grad_norm": 1.2170488834381104,
      "learning_rate": 0.00012,
      "loss": 44.351,
      "step": 6
    },
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 1.3282305002212524,
      "learning_rate": 0.00018,
      "loss": 44.3677,
      "step": 9
    },
    {
      "epoch": 0.06172839506172839,
      "eval_loss": 11.076057434082031,
      "eval_runtime": 0.3482,
      "eval_samples_per_second": 198.139,
      "eval_steps_per_second": 100.505,
      "step": 10
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 1.4536323547363281,
      "learning_rate": 0.00019510565162951537,
      "loss": 44.2973,
      "step": 12
    },
    {
      "epoch": 0.09259259259259259,
      "grad_norm": 1.4778214693069458,
      "learning_rate": 0.00017071067811865476,
      "loss": 44.2606,
      "step": 15
    },
    {
      "epoch": 0.09259259259259259,
      "eval_loss": 11.052154541015625,
      "eval_runtime": 0.3719,
      "eval_samples_per_second": 185.525,
      "eval_steps_per_second": 94.107,
      "step": 15
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 1.3547159433364868,
      "learning_rate": 0.00013090169943749476,
      "loss": 44.1819,
      "step": 18
    },
    {
      "epoch": 0.12345679012345678,
      "eval_loss": 11.031575202941895,
      "eval_runtime": 0.3552,
      "eval_samples_per_second": 194.253,
      "eval_steps_per_second": 98.534,
      "step": 20
    },
    {
      "epoch": 0.12962962962962962,
      "grad_norm": 1.6233855485916138,
      "learning_rate": 8.435655349597689e-05,
      "loss": 44.1295,
      "step": 21
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 1.518567681312561,
      "learning_rate": 4.12214747707527e-05,
      "loss": 44.1,
      "step": 24
    },
    {
      "epoch": 0.15432098765432098,
      "eval_loss": 11.02023983001709,
      "eval_runtime": 0.3468,
      "eval_samples_per_second": 198.98,
      "eval_steps_per_second": 100.932,
      "step": 25
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 1.5110942125320435,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 44.0644,
      "step": 27
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 1.5533232688903809,
      "learning_rate": 0.0,
      "loss": 44.0723,
      "step": 30
    },
    {
      "epoch": 0.18518518518518517,
      "eval_loss": 11.018196105957031,
      "eval_runtime": 0.3627,
      "eval_samples_per_second": 190.225,
      "eval_steps_per_second": 96.491,
      "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": 623986606080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}