checkpoint-105/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 13.133333333333333,
  "eval_steps": 500,
  "global_step": 105,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 2.1946465969085693,
      "eval_runtime": 17.2738,
      "eval_samples_per_second": 0.405,
      "eval_steps_per_second": 0.058,
      "step": 8
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.9301021099090576,
      "eval_runtime": 17.1725,
      "eval_samples_per_second": 0.408,
      "eval_steps_per_second": 0.058,
      "step": 16
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.8589046001434326,
      "eval_runtime": 18.5191,
      "eval_samples_per_second": 0.378,
      "eval_steps_per_second": 0.054,
      "step": 24
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.839167833328247,
      "eval_runtime": 17.3086,
      "eval_samples_per_second": 0.404,
      "eval_steps_per_second": 0.058,
      "step": 32
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.8779523372650146,
      "eval_runtime": 17.3997,
      "eval_samples_per_second": 0.402,
      "eval_steps_per_second": 0.057,
      "step": 40
    },
    {
      "epoch": 6.0,
      "eval_loss": 1.9238650798797607,
      "eval_runtime": 18.6686,
      "eval_samples_per_second": 0.375,
      "eval_steps_per_second": 0.054,
      "step": 48
    },
    {
      "epoch": 7.0,
      "eval_loss": 1.9594440460205078,
      "eval_runtime": 17.6292,
      "eval_samples_per_second": 0.397,
      "eval_steps_per_second": 0.057,
      "step": 56
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.9980494976043701,
      "eval_runtime": 17.4652,
      "eval_samples_per_second": 0.401,
      "eval_steps_per_second": 0.057,
      "step": 64
    },
    {
      "epoch": 9.0,
      "eval_loss": 2.038095712661743,
      "eval_runtime": 18.2047,
      "eval_samples_per_second": 0.385,
      "eval_steps_per_second": 0.055,
      "step": 72
    },
    {
      "epoch": 10.0,
      "eval_loss": 2.095003366470337,
      "eval_runtime": 18.5195,
      "eval_samples_per_second": 0.378,
      "eval_steps_per_second": 0.054,
      "step": 80
    },
    {
      "epoch": 11.0,
      "eval_loss": 2.120067834854126,
      "eval_runtime": 17.4162,
      "eval_samples_per_second": 0.402,
      "eval_steps_per_second": 0.057,
      "step": 88
    },
    {
      "epoch": 12.0,
      "eval_loss": 2.1349480152130127,
      "eval_runtime": 18.8636,
      "eval_samples_per_second": 0.371,
      "eval_steps_per_second": 0.053,
      "step": 96
    },
    {
      "epoch": 12.533333333333333,
      "grad_norm": 3.702388286590576,
      "learning_rate": 2.3809523809523808e-06,
      "loss": 0.9068,
      "step": 100
    },
    {
      "epoch": 13.0,
      "eval_loss": 2.1458475589752197,
      "eval_runtime": 17.4429,
      "eval_samples_per_second": 0.401,
      "eval_steps_per_second": 0.057,
      "step": 104
    }
  ],
  "logging_steps": 100,
  "max_steps": 105,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 15,
  "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": 202435500441600.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}