checkpoint-154/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 154,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 1.0468935571610927,
      "epoch": 0.1309328968903437,
      "grad_norm": 0.17416474223136902,
      "learning_rate": 0.00019964456535631286,
      "loss": 0.9909916877746582,
      "mean_token_accuracy": 0.7388732366263866,
      "num_tokens": 1598328.0,
      "step": 10
    },
    {
      "entropy": 1.0232607774436473,
      "epoch": 0.2618657937806874,
      "grad_norm": 0.10969934612512589,
      "learning_rate": 0.00019567488620406983,
      "loss": 0.9136476516723633,
      "mean_token_accuracy": 0.7531854555010795,
      "num_tokens": 3266894.0,
      "step": 20
    },
    {
      "entropy": 1.010091096162796,
      "epoch": 0.39279869067103107,
      "grad_norm": 0.10629099607467651,
      "learning_rate": 0.0001874676489891461,
      "loss": 0.8976033210754395,
      "mean_token_accuracy": 0.756408640742302,
      "num_tokens": 4865150.0,
      "step": 30
    },
    {
      "entropy": 1.004666418582201,
      "epoch": 0.5237315875613748,
      "grad_norm": 0.10314613580703735,
      "learning_rate": 0.0001753863623146066,
      "loss": 0.8875059127807617,
      "mean_token_accuracy": 0.7579705864191055,
      "num_tokens": 6511070.0,
      "step": 40
    },
    {
      "entropy": 0.9716963268816471,
      "epoch": 0.6546644844517185,
      "grad_norm": 0.10347197204828262,
      "learning_rate": 0.00015996612118590603,
      "loss": 0.8659543037414551,
      "mean_token_accuracy": 0.7610714465379715,
      "num_tokens": 8163910.0,
      "step": 50
    },
    {
      "entropy": 0.9952918991446496,
      "epoch": 0.7855973813420621,
      "grad_norm": 0.11144387722015381,
      "learning_rate": 0.00014188990699676184,
      "loss": 0.894680118560791,
      "mean_token_accuracy": 0.7570059388875962,
      "num_tokens": 9787100.0,
      "step": 60
    },
    {
      "entropy": 0.9721599273383618,
      "epoch": 0.9165302782324058,
      "grad_norm": 0.1071121096611023,
      "learning_rate": 0.0001219583374454963,
      "loss": 0.8589889526367187,
      "mean_token_accuracy": 0.7641318537294864,
      "num_tokens": 11457806.0,
      "step": 70
    },
    {
      "entropy": 0.9639704402287801,
      "epoch": 1.039279869067103,
      "grad_norm": 0.11399766057729721,
      "learning_rate": 0.00010105420619515798,
      "loss": 0.8564103126525879,
      "mean_token_accuracy": 0.7631221461296082,
      "num_tokens": 12972132.0,
      "step": 80
    },
    {
      "entropy": 0.9393186651170253,
      "epoch": 1.1702127659574468,
      "grad_norm": 0.11741285771131516,
      "learning_rate": 8.010338285937006e-05,
      "loss": 0.8454008102416992,
      "mean_token_accuracy": 0.765296196937561,
      "num_tokens": 14591349.0,
      "step": 90
    },
    {
      "entropy": 0.939175833761692,
      "epoch": 1.3011456628477904,
      "grad_norm": 0.11117595434188843,
      "learning_rate": 6.0033805101491794e-05,
      "loss": 0.8312828063964843,
      "mean_token_accuracy": 0.7702119380235672,
      "num_tokens": 16314257.0,
      "step": 100
    },
    {
      "entropy": 0.9309360004961491,
      "epoch": 1.4320785597381342,
      "grad_norm": 0.10903246700763702,
      "learning_rate": 4.173437913732048e-05,
      "loss": 0.8263219833374024,
      "mean_token_accuracy": 0.771622458845377,
      "num_tokens": 17970258.0,
      "step": 110
    },
    {
      "entropy": 0.9086847320199013,
      "epoch": 1.563011456628478,
      "grad_norm": 0.10437027364969254,
      "learning_rate": 2.6015608988480955e-05,
      "loss": 0.8269096374511719,
      "mean_token_accuracy": 0.771278391033411,
      "num_tokens": 19625922.0,
      "step": 120
    },
    {
      "entropy": 0.9578615836799145,
      "epoch": 1.6939443535188214,
      "grad_norm": 0.10706261545419693,
      "learning_rate": 1.3573698265161683e-05,
      "loss": 0.8548309326171875,
      "mean_token_accuracy": 0.763871145248413,
      "num_tokens": 21260877.0,
      "step": 130
    },
    {
      "entropy": 0.9355579890310765,
      "epoch": 1.8248772504091653,
      "grad_norm": 0.12391113489866257,
      "learning_rate": 4.959714454271369e-06,
      "loss": 0.8470058441162109,
      "mean_token_accuracy": 0.7670461565256119,
      "num_tokens": 22841684.0,
      "step": 140
    },
    {
      "entropy": 0.936388584971428,
      "epoch": 1.955810147299509,
      "grad_norm": 0.12295228987932205,
      "learning_rate": 5.55181464516652e-07,
      "loss": 0.8386976242065429,
      "mean_token_accuracy": 0.7662878468632698,
      "num_tokens": 24488295.0,
      "step": 150
    }
  ],
  "logging_steps": 10,
  "max_steps": 154,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.088313897241805e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}