last-checkpoint/trainer_state.json

{
  "best_metric": 0.30269354581832886,
  "best_model_checkpoint": "./opt_trained/checkpoint-2898",
  "epoch": 9.0,
  "eval_steps": 500,
  "global_step": 2898,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.34622922539711,
      "eval_runtime": 144.337,
      "eval_samples_per_second": 19.787,
      "eval_steps_per_second": 4.947,
      "step": 322
    },
    {
      "epoch": 1.5540856031128405,
      "grad_norm": 2.789034128189087,
      "learning_rate": 4.61214953271028e-05,
      "loss": 0.3568,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.31846198439598083,
      "eval_runtime": 144.4556,
      "eval_samples_per_second": 19.771,
      "eval_steps_per_second": 4.943,
      "step": 644
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.3117474913597107,
      "eval_runtime": 144.2852,
      "eval_samples_per_second": 19.794,
      "eval_steps_per_second": 4.949,
      "step": 966
    },
    {
      "epoch": 3.1058365758754864,
      "grad_norm": 3.2271311283111572,
      "learning_rate": 4.222741433021807e-05,
      "loss": 0.3157,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.3092747926712036,
      "eval_runtime": 144.5498,
      "eval_samples_per_second": 19.758,
      "eval_steps_per_second": 4.939,
      "step": 1288
    },
    {
      "epoch": 4.659922178988327,
      "grad_norm": 2.2325267791748047,
      "learning_rate": 3.8333333333333334e-05,
      "loss": 0.3082,
      "step": 1500
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.3064902424812317,
      "eval_runtime": 144.1384,
      "eval_samples_per_second": 19.814,
      "eval_steps_per_second": 4.954,
      "step": 1610
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.3062432110309601,
      "eval_runtime": 144.3779,
      "eval_samples_per_second": 19.781,
      "eval_steps_per_second": 4.945,
      "step": 1932
    },
    {
      "epoch": 6.211673151750973,
      "grad_norm": 1.4930099248886108,
      "learning_rate": 3.4439252336448605e-05,
      "loss": 0.3042,
      "step": 2000
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.30498865246772766,
      "eval_runtime": 144.6547,
      "eval_samples_per_second": 19.744,
      "eval_steps_per_second": 4.936,
      "step": 2254
    },
    {
      "epoch": 7.765758754863813,
      "grad_norm": 2.2369720935821533,
      "learning_rate": 3.054517133956387e-05,
      "loss": 0.3023,
      "step": 2500
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.3037343919277191,
      "eval_runtime": 144.6161,
      "eval_samples_per_second": 19.749,
      "eval_steps_per_second": 4.937,
      "step": 2576
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.30269354581832886,
      "eval_runtime": 144.5227,
      "eval_samples_per_second": 19.762,
      "eval_steps_per_second": 4.94,
      "step": 2898
    }
  ],
  "logging_steps": 500,
  "max_steps": 6420,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2085017772032e+17,
  "train_batch_size": 10,
  "trial_name": null,
  "trial_params": null
}