trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 121,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08264462809917356,
      "grad_norm": 7.750270843505859,
      "learning_rate": 0.000199658449300667,
      "loss": 0.5852,
      "step": 10
    },
    {
      "epoch": 0.1652892561983471,
      "grad_norm": 23.40735626220703,
      "learning_rate": 0.0001936511241197055,
      "loss": 0.3072,
      "step": 20
    },
    {
      "epoch": 0.24793388429752067,
      "grad_norm": 24.60139274597168,
      "learning_rate": 0.00018057651056609784,
      "loss": 0.2754,
      "step": 30
    },
    {
      "epoch": 0.3305785123966942,
      "grad_norm": 0.9646787047386169,
      "learning_rate": 0.0001614212712689668,
      "loss": 0.1879,
      "step": 40
    },
    {
      "epoch": 0.4132231404958678,
      "grad_norm": 0.9788209199905396,
      "learning_rate": 0.00013763093719478358,
      "loss": 0.1493,
      "step": 50
    },
    {
      "epoch": 0.49586776859504134,
      "grad_norm": 0.7880584597587585,
      "learning_rate": 0.00011100082209940795,
      "loss": 0.1321,
      "step": 60
    },
    {
      "epoch": 0.5785123966942148,
      "grad_norm": 0.5986640453338623,
      "learning_rate": 8.35405409719266e-05,
      "loss": 0.1109,
      "step": 70
    },
    {
      "epoch": 0.6611570247933884,
      "grad_norm": 0.9021563529968262,
      "learning_rate": 5.732235645035964e-05,
      "loss": 0.1011,
      "step": 80
    },
    {
      "epoch": 0.743801652892562,
      "grad_norm": 0.5953593254089355,
      "learning_rate": 3.4324797595226565e-05,
      "loss": 0.0918,
      "step": 90
    },
    {
      "epoch": 0.8264462809917356,
      "grad_norm": 0.3122101128101349,
      "learning_rate": 1.6283352173747145e-05,
      "loss": 0.0749,
      "step": 100
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.42104968428611755,
      "learning_rate": 4.559499812049251e-06,
      "loss": 0.0831,
      "step": 110
    },
    {
      "epoch": 0.9917355371900827,
      "grad_norm": 0.40868669748306274,
      "learning_rate": 3.796929750485845e-08,
      "loss": 0.0733,
      "step": 120
    },
    {
      "epoch": 1.0,
      "step": 121,
      "total_flos": 1.7516975778360288e+16,
      "train_loss": 0.1801821660281213,
      "train_runtime": 186.5904,
      "train_samples_per_second": 41.412,
      "train_steps_per_second": 0.648
    }
  ],
  "logging_steps": 10,
  "max_steps": 121,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.7516975778360288e+16,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}