last-checkpoint/trainer_state.json

{
  "best_metric": 2.727842330932617,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.13969732246798602,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004656577415599534,
      "eval_loss": 4.233518600463867,
      "eval_runtime": 17.914,
      "eval_samples_per_second": 5.08,
      "eval_steps_per_second": 2.568,
      "step": 1
    },
    {
      "epoch": 0.013969732246798603,
      "grad_norm": 2.3055834770202637,
      "learning_rate": 6e-05,
      "loss": 4.35,
      "step": 3
    },
    {
      "epoch": 0.023282887077997673,
      "eval_loss": 3.9945688247680664,
      "eval_runtime": 17.7238,
      "eval_samples_per_second": 5.134,
      "eval_steps_per_second": 2.595,
      "step": 5
    },
    {
      "epoch": 0.027939464493597205,
      "grad_norm": 2.185933828353882,
      "learning_rate": 0.00012,
      "loss": 4.1682,
      "step": 6
    },
    {
      "epoch": 0.04190919674039581,
      "grad_norm": 2.1223950386047363,
      "learning_rate": 0.00018,
      "loss": 3.6847,
      "step": 9
    },
    {
      "epoch": 0.046565774155995346,
      "eval_loss": 3.121283531188965,
      "eval_runtime": 17.8061,
      "eval_samples_per_second": 5.111,
      "eval_steps_per_second": 2.583,
      "step": 10
    },
    {
      "epoch": 0.05587892898719441,
      "grad_norm": 3.1581156253814697,
      "learning_rate": 0.00019510565162951537,
      "loss": 3.2589,
      "step": 12
    },
    {
      "epoch": 0.06984866123399301,
      "grad_norm": 2.3886799812316895,
      "learning_rate": 0.00017071067811865476,
      "loss": 3.203,
      "step": 15
    },
    {
      "epoch": 0.06984866123399301,
      "eval_loss": 2.916701316833496,
      "eval_runtime": 17.8176,
      "eval_samples_per_second": 5.107,
      "eval_steps_per_second": 2.582,
      "step": 15
    },
    {
      "epoch": 0.08381839348079162,
      "grad_norm": 2.401080846786499,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.9009,
      "step": 18
    },
    {
      "epoch": 0.09313154831199069,
      "eval_loss": 2.768876075744629,
      "eval_runtime": 17.7942,
      "eval_samples_per_second": 5.114,
      "eval_steps_per_second": 2.585,
      "step": 20
    },
    {
      "epoch": 0.09778812572759023,
      "grad_norm": 2.3748066425323486,
      "learning_rate": 8.435655349597689e-05,
      "loss": 2.9547,
      "step": 21
    },
    {
      "epoch": 0.11175785797438882,
      "grad_norm": 1.8192694187164307,
      "learning_rate": 4.12214747707527e-05,
      "loss": 2.8456,
      "step": 24
    },
    {
      "epoch": 0.11641443538998836,
      "eval_loss": 2.73561429977417,
      "eval_runtime": 17.7904,
      "eval_samples_per_second": 5.115,
      "eval_steps_per_second": 2.586,
      "step": 25
    },
    {
      "epoch": 0.12572759022118743,
      "grad_norm": 2.1935503482818604,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 2.8691,
      "step": 27
    },
    {
      "epoch": 0.13969732246798602,
      "grad_norm": 1.8655444383621216,
      "learning_rate": 0.0,
      "loss": 2.7834,
      "step": 30
    },
    {
      "epoch": 0.13969732246798602,
      "eval_loss": 2.727842330932617,
      "eval_runtime": 17.8081,
      "eval_samples_per_second": 5.11,
      "eval_steps_per_second": 2.583,
      "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": 1.9043369091072e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}