last-checkpoint/trainer_state.json

{
  "best_metric": 2.5440735816955566,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.029404557706444498,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00098015192354815,
      "eval_loss": 2.7682464122772217,
      "eval_runtime": 3.9445,
      "eval_samples_per_second": 109.014,
      "eval_steps_per_second": 54.507,
      "step": 1
    },
    {
      "epoch": 0.00294045577064445,
      "grad_norm": 1.7165231704711914,
      "learning_rate": 6e-05,
      "loss": 2.6436,
      "step": 3
    },
    {
      "epoch": 0.00490075961774075,
      "eval_loss": 2.7519423961639404,
      "eval_runtime": 3.8098,
      "eval_samples_per_second": 112.866,
      "eval_steps_per_second": 56.433,
      "step": 5
    },
    {
      "epoch": 0.0058809115412889,
      "grad_norm": 0.9223698973655701,
      "learning_rate": 9.96057350657239e-05,
      "loss": 2.7135,
      "step": 6
    },
    {
      "epoch": 0.008821367311933349,
      "grad_norm": 0.8616958260536194,
      "learning_rate": 9.381533400219318e-05,
      "loss": 2.6707,
      "step": 9
    },
    {
      "epoch": 0.0098015192354815,
      "eval_loss": 2.6647682189941406,
      "eval_runtime": 4.134,
      "eval_samples_per_second": 104.014,
      "eval_steps_per_second": 52.007,
      "step": 10
    },
    {
      "epoch": 0.0117618230825778,
      "grad_norm": 0.5657535791397095,
      "learning_rate": 8.18711994874345e-05,
      "loss": 2.4843,
      "step": 12
    },
    {
      "epoch": 0.014702278853222249,
      "grad_norm": 0.7222481966018677,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.5581,
      "step": 15
    },
    {
      "epoch": 0.014702278853222249,
      "eval_loss": 2.601343870162964,
      "eval_runtime": 4.0133,
      "eval_samples_per_second": 107.145,
      "eval_steps_per_second": 53.572,
      "step": 15
    },
    {
      "epoch": 0.017642734623866698,
      "grad_norm": 0.8338580131530762,
      "learning_rate": 4.6860474023534335e-05,
      "loss": 2.5049,
      "step": 18
    },
    {
      "epoch": 0.019603038470963,
      "eval_loss": 2.5634732246398926,
      "eval_runtime": 3.9308,
      "eval_samples_per_second": 109.392,
      "eval_steps_per_second": 54.696,
      "step": 20
    },
    {
      "epoch": 0.02058319039451115,
      "grad_norm": 0.8678022623062134,
      "learning_rate": 2.8711035421746367e-05,
      "loss": 2.6216,
      "step": 21
    },
    {
      "epoch": 0.0235236461651556,
      "grad_norm": 0.7674933075904846,
      "learning_rate": 1.3551568628929434e-05,
      "loss": 2.4564,
      "step": 24
    },
    {
      "epoch": 0.02450379808870375,
      "eval_loss": 2.547071933746338,
      "eval_runtime": 3.9551,
      "eval_samples_per_second": 108.72,
      "eval_steps_per_second": 54.36,
      "step": 25
    },
    {
      "epoch": 0.02646410193580005,
      "grad_norm": 0.7818556427955627,
      "learning_rate": 3.511175705587433e-06,
      "loss": 2.5608,
      "step": 27
    },
    {
      "epoch": 0.029404557706444498,
      "grad_norm": 0.6539798974990845,
      "learning_rate": 0.0,
      "loss": 2.5075,
      "step": 30
    },
    {
      "epoch": 0.029404557706444498,
      "eval_loss": 2.5440735816955566,
      "eval_runtime": 3.9731,
      "eval_samples_per_second": 108.228,
      "eval_steps_per_second": 54.114,
      "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": 208256379125760.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}