last-checkpoint/trainer_state.json

{
  "best_metric": 2.584866523742676,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.003699593044765076,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003699593044765076,
      "grad_norm": 1.5243043899536133,
      "learning_rate": 2e-05,
      "loss": 3.2261,
      "step": 1
    },
    {
      "epoch": 0.0003699593044765076,
      "eval_loss": 3.100375175476074,
      "eval_runtime": 208.6635,
      "eval_samples_per_second": 5.459,
      "eval_steps_per_second": 2.732,
      "step": 1
    },
    {
      "epoch": 0.0007399186089530152,
      "grad_norm": 1.4240329265594482,
      "learning_rate": 4e-05,
      "loss": 2.9361,
      "step": 2
    },
    {
      "epoch": 0.0011098779134295228,
      "grad_norm": 1.524584174156189,
      "learning_rate": 6e-05,
      "loss": 3.1426,
      "step": 3
    },
    {
      "epoch": 0.0014798372179060304,
      "grad_norm": 1.3952741622924805,
      "learning_rate": 8e-05,
      "loss": 3.0211,
      "step": 4
    },
    {
      "epoch": 0.001849796522382538,
      "grad_norm": 1.4822412729263306,
      "learning_rate": 0.0001,
      "loss": 3.0685,
      "step": 5
    },
    {
      "epoch": 0.001849796522382538,
      "eval_loss": 2.9944255352020264,
      "eval_runtime": 208.6838,
      "eval_samples_per_second": 5.458,
      "eval_steps_per_second": 2.731,
      "step": 5
    },
    {
      "epoch": 0.0022197558268590455,
      "grad_norm": 1.499148964881897,
      "learning_rate": 0.00012,
      "loss": 2.7608,
      "step": 6
    },
    {
      "epoch": 0.002589715131335553,
      "grad_norm": 1.3574713468551636,
      "learning_rate": 0.00014,
      "loss": 2.8229,
      "step": 7
    },
    {
      "epoch": 0.0029596744358120607,
      "grad_norm": 1.3877097368240356,
      "learning_rate": 0.00016,
      "loss": 2.8343,
      "step": 8
    },
    {
      "epoch": 0.003329633740288568,
      "grad_norm": 1.3273413181304932,
      "learning_rate": 0.00018,
      "loss": 2.7683,
      "step": 9
    },
    {
      "epoch": 0.003699593044765076,
      "grad_norm": 1.4110333919525146,
      "learning_rate": 0.0002,
      "loss": 2.695,
      "step": 10
    },
    {
      "epoch": 0.003699593044765076,
      "eval_loss": 2.584866523742676,
      "eval_runtime": 208.6062,
      "eval_samples_per_second": 5.46,
      "eval_steps_per_second": 2.732,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 500097330708480.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}