checkpoint-63/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 63,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "grad_norm": 1.6024624109268188,
      "learning_rate": 0.000199522988805313,
      "loss": 2.0529,
      "mean_token_accuracy": 0.559639161452651,
      "num_tokens": 64985.0,
      "step": 5
    },
    {
      "epoch": 0.16,
      "grad_norm": 1.0667455196380615,
      "learning_rate": 0.00019421451371364444,
      "loss": 1.5192,
      "mean_token_accuracy": 0.6313199333846569,
      "num_tokens": 132654.0,
      "step": 10
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.6989722847938538,
      "learning_rate": 0.00018335255037651302,
      "loss": 1.2651,
      "mean_token_accuracy": 0.66771609634161,
      "num_tokens": 200863.0,
      "step": 15
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.49305838346481323,
      "learning_rate": 0.0001676533860828358,
      "loss": 1.1965,
      "mean_token_accuracy": 0.6907071858644486,
      "num_tokens": 265471.0,
      "step": 20
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.3976356089115143,
      "learning_rate": 0.0001481522951638875,
      "loss": 1.1184,
      "mean_token_accuracy": 0.7011254012584687,
      "num_tokens": 335362.0,
      "step": 25
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.32982659339904785,
      "learning_rate": 0.00012613526829296622,
      "loss": 1.0825,
      "mean_token_accuracy": 0.7074193194508552,
      "num_tokens": 403159.0,
      "step": 30
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.3139457404613495,
      "learning_rate": 0.00010305420840860182,
      "loss": 1.1136,
      "mean_token_accuracy": 0.7029193982481956,
      "num_tokens": 465862.0,
      "step": 35
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.3034254312515259,
      "learning_rate": 8.043118562802488e-05,
      "loss": 1.0445,
      "mean_token_accuracy": 0.7117198631167412,
      "num_tokens": 535415.0,
      "step": 40
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.3687556982040405,
      "learning_rate": 5.9758065017582185e-05,
      "loss": 1.0445,
      "mean_token_accuracy": 0.7163990259170532,
      "num_tokens": 600630.0,
      "step": 45
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.2981916069984436,
      "learning_rate": 4.2398126221653236e-05,
      "loss": 1.0519,
      "mean_token_accuracy": 0.7169259950518608,
      "num_tokens": 669353.0,
      "step": 50
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.324988454580307,
      "learning_rate": 2.949616259940842e-05,
      "loss": 1.0491,
      "mean_token_accuracy": 0.7140479609370232,
      "num_tokens": 735759.0,
      "step": 55
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.31940364837646484,
      "learning_rate": 2.19029883414178e-05,
      "loss": 1.0886,
      "mean_token_accuracy": 0.7087796837091446,
      "num_tokens": 799409.0,
      "step": 60
    }
  ],
  "logging_steps": 5,
  "max_steps": 63,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 1.0164973639893696e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}