checkpoint-713/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 1000,
  "global_step": 713,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 0.7893231290578843,
      "epoch": 0.07012622720897616,
      "grad_norm": 1.1326932907104492,
      "learning_rate": 0.00018625525946704068,
      "loss": 0.883,
      "mean_token_accuracy": 0.8367647039890289,
      "num_tokens": 51200.0,
      "step": 50
    },
    {
      "entropy": 0.604653742313385,
      "epoch": 0.1402524544179523,
      "grad_norm": 1.4008318185806274,
      "learning_rate": 0.00017223001402524545,
      "loss": 0.6207,
      "mean_token_accuracy": 0.8560980391502381,
      "num_tokens": 102400.0,
      "step": 100
    },
    {
      "entropy": 0.552680384516716,
      "epoch": 0.21037868162692847,
      "grad_norm": 1.2125327587127686,
      "learning_rate": 0.00015820476858345023,
      "loss": 0.5688,
      "mean_token_accuracy": 0.8681372570991516,
      "num_tokens": 153600.0,
      "step": 150
    },
    {
      "entropy": 0.5870230662822723,
      "epoch": 0.2805049088359046,
      "grad_norm": 1.0003958940505981,
      "learning_rate": 0.000144179523141655,
      "loss": 0.6044,
      "mean_token_accuracy": 0.8610000038146972,
      "num_tokens": 204800.0,
      "step": 200
    },
    {
      "entropy": 0.5841648465394974,
      "epoch": 0.3506311360448808,
      "grad_norm": 1.2221473455429077,
      "learning_rate": 0.00013015427769985974,
      "loss": 0.5942,
      "mean_token_accuracy": 0.8643529415130615,
      "num_tokens": 256000.0,
      "step": 250
    },
    {
      "entropy": 0.5446552008390426,
      "epoch": 0.42075736325385693,
      "grad_norm": 0.8246455788612366,
      "learning_rate": 0.00011612903225806453,
      "loss": 0.5693,
      "mean_token_accuracy": 0.8707843124866486,
      "num_tokens": 307200.0,
      "step": 300
    },
    {
      "entropy": 0.5239044934511184,
      "epoch": 0.4908835904628331,
      "grad_norm": 1.022056221961975,
      "learning_rate": 0.00010210378681626929,
      "loss": 0.5433,
      "mean_token_accuracy": 0.8759215676784515,
      "num_tokens": 358400.0,
      "step": 350
    },
    {
      "entropy": 0.516560555100441,
      "epoch": 0.5610098176718092,
      "grad_norm": 1.1696139574050903,
      "learning_rate": 8.807854137447405e-05,
      "loss": 0.5267,
      "mean_token_accuracy": 0.877607843875885,
      "num_tokens": 409600.0,
      "step": 400
    },
    {
      "entropy": 0.5230421105027199,
      "epoch": 0.6311360448807855,
      "grad_norm": 0.8299864530563354,
      "learning_rate": 7.405329593267882e-05,
      "loss": 0.5232,
      "mean_token_accuracy": 0.879117648601532,
      "num_tokens": 460800.0,
      "step": 450
    },
    {
      "entropy": 0.5555241489410401,
      "epoch": 0.7012622720897616,
      "grad_norm": 1.1203019618988037,
      "learning_rate": 6.002805049088359e-05,
      "loss": 0.568,
      "mean_token_accuracy": 0.8681960797309876,
      "num_tokens": 512000.0,
      "step": 500
    },
    {
      "entropy": 0.5119614934921265,
      "epoch": 0.7713884992987378,
      "grad_norm": 1.3243024349212646,
      "learning_rate": 4.600280504908836e-05,
      "loss": 0.517,
      "mean_token_accuracy": 0.8799803924560546,
      "num_tokens": 563200.0,
      "step": 550
    },
    {
      "entropy": 0.4760155099630356,
      "epoch": 0.8415147265077139,
      "grad_norm": 0.8521648049354553,
      "learning_rate": 3.197755960729313e-05,
      "loss": 0.4854,
      "mean_token_accuracy": 0.8899803864955902,
      "num_tokens": 614400.0,
      "step": 600
    },
    {
      "entropy": 0.45049646943807603,
      "epoch": 0.9116409537166901,
      "grad_norm": 0.7379061579704285,
      "learning_rate": 1.7952314165497897e-05,
      "loss": 0.4515,
      "mean_token_accuracy": 0.8959019601345062,
      "num_tokens": 665600.0,
      "step": 650
    },
    {
      "entropy": 0.49310168087482453,
      "epoch": 0.9817671809256662,
      "grad_norm": 1.3646042346954346,
      "learning_rate": 3.927068723702665e-06,
      "loss": 0.508,
      "mean_token_accuracy": 0.8815882337093354,
      "num_tokens": 716800.0,
      "step": 700
    }
  ],
  "logging_steps": 50,
  "max_steps": 713,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 464916248985600.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}