last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0151187904967602,
  "eval_steps": 50,
  "global_step": 29,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03455723542116631,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.03455723542116631,
      "eval_loss": NaN,
      "eval_runtime": 1.8587,
      "eval_samples_per_second": 52.724,
      "eval_steps_per_second": 13.45,
      "step": 1
    },
    {
      "epoch": 0.06911447084233262,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.10367170626349892,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.13822894168466524,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.17278617710583152,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.20734341252699784,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.24190064794816415,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.27645788336933047,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.31101511879049676,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.34557235421166305,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.3801295896328294,
      "grad_norm": NaN,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.4146868250539957,
      "grad_norm": NaN,
      "learning_rate": 0.00019458172417006347,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.44924406047516197,
      "grad_norm": NaN,
      "learning_rate": 0.0001879473751206489,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.4838012958963283,
      "grad_norm": NaN,
      "learning_rate": 0.00017891405093963938,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.5183585313174947,
      "grad_norm": NaN,
      "learning_rate": 0.00016772815716257412,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.5529157667386609,
      "grad_norm": NaN,
      "learning_rate": 0.00015469481581224272,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.5874730021598272,
      "grad_norm": NaN,
      "learning_rate": 0.00014016954246529696,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.6220302375809935,
      "grad_norm": NaN,
      "learning_rate": 0.00012454854871407994,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.6565874730021598,
      "grad_norm": NaN,
      "learning_rate": 0.00010825793454723325,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.6911447084233261,
      "grad_norm": NaN,
      "learning_rate": 9.174206545276677e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.7257019438444925,
      "grad_norm": NaN,
      "learning_rate": 7.54514512859201e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.7602591792656588,
      "grad_norm": NaN,
      "learning_rate": 5.983045753470308e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.7948164146868251,
      "grad_norm": NaN,
      "learning_rate": 4.530518418775733e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.8293736501079914,
      "grad_norm": NaN,
      "learning_rate": 3.227184283742591e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.8639308855291576,
      "grad_norm": NaN,
      "learning_rate": 2.1085949060360654e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.8984881209503239,
      "grad_norm": NaN,
      "learning_rate": 1.2052624879351104e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.9330453563714903,
      "grad_norm": NaN,
      "learning_rate": 5.418275829936537e-06,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.9676025917926566,
      "grad_norm": NaN,
      "learning_rate": 1.3638696597277679e-06,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 1.0151187904967602,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 29
    }
  ],
  "logging_steps": 1,
  "max_steps": 29,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3686888720302080.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}