last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0009238728750923873,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.238728750923873e-05,
      "grad_norm": 1.9452441930770874,
      "learning_rate": 2e-05,
      "loss": 2.8965,
      "step": 1
    },
    {
      "epoch": 9.238728750923873e-05,
      "eval_loss": 2.72082257270813,
      "eval_runtime": 193.625,
      "eval_samples_per_second": 23.54,
      "eval_steps_per_second": 11.77,
      "step": 1
    },
    {
      "epoch": 0.00018477457501847746,
      "grad_norm": 1.5764484405517578,
      "learning_rate": 4e-05,
      "loss": 2.3501,
      "step": 2
    },
    {
      "epoch": 0.0002771618625277162,
      "grad_norm": 1.4889730215072632,
      "learning_rate": 6e-05,
      "loss": 2.3164,
      "step": 3
    },
    {
      "epoch": 0.0002771618625277162,
      "eval_loss": 2.713813066482544,
      "eval_runtime": 192.3994,
      "eval_samples_per_second": 23.69,
      "eval_steps_per_second": 11.845,
      "step": 3
    },
    {
      "epoch": 0.0003695491500369549,
      "grad_norm": 1.3642616271972656,
      "learning_rate": 8e-05,
      "loss": 2.4042,
      "step": 4
    },
    {
      "epoch": 0.00046193643754619364,
      "grad_norm": 2.06803822517395,
      "learning_rate": 0.0001,
      "loss": 2.9043,
      "step": 5
    },
    {
      "epoch": 0.0005543237250554324,
      "grad_norm": 2.2044570446014404,
      "learning_rate": 0.00012,
      "loss": 2.7562,
      "step": 6
    },
    {
      "epoch": 0.0005543237250554324,
      "eval_loss": 2.5870378017425537,
      "eval_runtime": 192.5166,
      "eval_samples_per_second": 23.676,
      "eval_steps_per_second": 11.838,
      "step": 6
    },
    {
      "epoch": 0.0006467110125646711,
      "grad_norm": 2.6389575004577637,
      "learning_rate": 0.00014,
      "loss": 2.8696,
      "step": 7
    },
    {
      "epoch": 0.0007390983000739098,
      "grad_norm": 1.9302886724472046,
      "learning_rate": 0.00016,
      "loss": 2.0204,
      "step": 8
    },
    {
      "epoch": 0.0008314855875831486,
      "grad_norm": 2.129281997680664,
      "learning_rate": 0.00018,
      "loss": 2.2695,
      "step": 9
    },
    {
      "epoch": 0.0008314855875831486,
      "eval_loss": 2.262294292449951,
      "eval_runtime": 192.3493,
      "eval_samples_per_second": 23.696,
      "eval_steps_per_second": 11.848,
      "step": 9
    },
    {
      "epoch": 0.0009238728750923873,
      "grad_norm": 1.7490051984786987,
      "learning_rate": 0.0002,
      "loss": 2.0031,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2820585478422528.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}