last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0007669446841146582,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.669446841146582e-05,
      "grad_norm": 1.4482876062393188,
      "learning_rate": 2e-05,
      "loss": 1.3976,
      "step": 1
    },
    {
      "epoch": 7.669446841146582e-05,
      "eval_loss": 1.512182354927063,
      "eval_runtime": 227.7076,
      "eval_samples_per_second": 24.11,
      "eval_steps_per_second": 12.055,
      "step": 1
    },
    {
      "epoch": 0.00015338893682293164,
      "grad_norm": 2.7365329265594482,
      "learning_rate": 4e-05,
      "loss": 2.0117,
      "step": 2
    },
    {
      "epoch": 0.00023008340523439746,
      "grad_norm": 2.1841118335723877,
      "learning_rate": 6e-05,
      "loss": 1.4039,
      "step": 3
    },
    {
      "epoch": 0.00023008340523439746,
      "eval_loss": 1.4867808818817139,
      "eval_runtime": 228.027,
      "eval_samples_per_second": 24.076,
      "eval_steps_per_second": 12.038,
      "step": 3
    },
    {
      "epoch": 0.0003067778736458633,
      "grad_norm": 2.4965789318084717,
      "learning_rate": 8e-05,
      "loss": 1.2481,
      "step": 4
    },
    {
      "epoch": 0.0003834723420573291,
      "grad_norm": 1.5910840034484863,
      "learning_rate": 0.0001,
      "loss": 1.2168,
      "step": 5
    },
    {
      "epoch": 0.0004601668104687949,
      "grad_norm": 1.5498541593551636,
      "learning_rate": 0.00012,
      "loss": 1.4143,
      "step": 6
    },
    {
      "epoch": 0.0004601668104687949,
      "eval_loss": 1.1717259883880615,
      "eval_runtime": 228.4675,
      "eval_samples_per_second": 24.03,
      "eval_steps_per_second": 12.015,
      "step": 6
    },
    {
      "epoch": 0.0005368612788802608,
      "grad_norm": 1.8883832693099976,
      "learning_rate": 0.00014,
      "loss": 0.6472,
      "step": 7
    },
    {
      "epoch": 0.0006135557472917265,
      "grad_norm": 2.3763439655303955,
      "learning_rate": 0.00016,
      "loss": 0.9165,
      "step": 8
    },
    {
      "epoch": 0.0006902502157031924,
      "grad_norm": 2.173048734664917,
      "learning_rate": 0.00018,
      "loss": 0.3821,
      "step": 9
    },
    {
      "epoch": 0.0006902502157031924,
      "eval_loss": 0.5749387145042419,
      "eval_runtime": 229.2601,
      "eval_samples_per_second": 23.947,
      "eval_steps_per_second": 11.973,
      "step": 9
    },
    {
      "epoch": 0.0007669446841146582,
      "grad_norm": 1.0589267015457153,
      "learning_rate": 0.0002,
      "loss": 0.3088,
      "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": 1250574214103040.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}