checkpoint-80/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 7.804878048780488,
  "eval_steps": 5,
  "global_step": 80,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.975609756097561,
      "grad_norm": 0.07996653020381927,
      "learning_rate": 5e-05,
      "loss": 1.7701,
      "step": 10
    },
    {
      "epoch": 0.975609756097561,
      "eval_runtime": 48.4614,
      "eval_samples_per_second": 5.798,
      "eval_steps_per_second": 0.371,
      "step": 10
    },
    {
      "epoch": 1.951219512195122,
      "grad_norm": 0.10972072184085846,
      "learning_rate": 5e-05,
      "loss": 1.7133,
      "step": 20
    },
    {
      "epoch": 1.951219512195122,
      "eval_runtime": 48.1459,
      "eval_samples_per_second": 5.836,
      "eval_steps_per_second": 0.374,
      "step": 20
    },
    {
      "epoch": 2.926829268292683,
      "grad_norm": 0.13606426119804382,
      "learning_rate": 5e-05,
      "loss": 1.6303,
      "step": 30
    },
    {
      "epoch": 2.926829268292683,
      "eval_runtime": 47.77,
      "eval_samples_per_second": 5.882,
      "eval_steps_per_second": 0.377,
      "step": 30
    },
    {
      "epoch": 3.902439024390244,
      "grad_norm": 0.14128075540065765,
      "learning_rate": 5e-05,
      "loss": 1.518,
      "step": 40
    },
    {
      "epoch": 4.0,
      "eval_runtime": 47.8398,
      "eval_samples_per_second": 5.874,
      "eval_steps_per_second": 0.376,
      "step": 41
    },
    {
      "epoch": 4.878048780487805,
      "grad_norm": 0.15739107131958008,
      "learning_rate": 5e-05,
      "loss": 1.3721,
      "step": 50
    },
    {
      "epoch": 4.975609756097561,
      "eval_runtime": 47.8829,
      "eval_samples_per_second": 5.868,
      "eval_steps_per_second": 0.376,
      "step": 51
    },
    {
      "epoch": 5.853658536585366,
      "grad_norm": 0.2110830843448639,
      "learning_rate": 5e-05,
      "loss": 1.1977,
      "step": 60
    },
    {
      "epoch": 5.951219512195122,
      "eval_runtime": 47.753,
      "eval_samples_per_second": 5.884,
      "eval_steps_per_second": 0.377,
      "step": 61
    },
    {
      "epoch": 6.829268292682927,
      "grad_norm": 0.23082995414733887,
      "learning_rate": 5e-05,
      "loss": 0.9901,
      "step": 70
    },
    {
      "epoch": 6.926829268292683,
      "eval_runtime": 47.994,
      "eval_samples_per_second": 5.855,
      "eval_steps_per_second": 0.375,
      "step": 71
    },
    {
      "epoch": 7.804878048780488,
      "grad_norm": 0.2343471646308899,
      "learning_rate": 5e-05,
      "loss": 0.7701,
      "step": 80
    }
  ],
  "logging_steps": 10,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 20,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.0807020462473216e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}