last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004274417610600555,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00042744176106005556,
      "grad_norm": 0.7325186133384705,
      "learning_rate": 2e-05,
      "loss": 7.0581,
      "step": 1
    },
    {
      "epoch": 0.00042744176106005556,
      "eval_loss": 1.817090630531311,
      "eval_runtime": 88.7321,
      "eval_samples_per_second": 11.101,
      "eval_steps_per_second": 5.556,
      "step": 1
    },
    {
      "epoch": 0.0008548835221201111,
      "grad_norm": 0.7564229369163513,
      "learning_rate": 4e-05,
      "loss": 7.2666,
      "step": 2
    },
    {
      "epoch": 0.0012823252831801668,
      "grad_norm": 0.7250242233276367,
      "learning_rate": 6e-05,
      "loss": 7.309,
      "step": 3
    },
    {
      "epoch": 0.0012823252831801668,
      "eval_loss": 1.8166850805282593,
      "eval_runtime": 88.7598,
      "eval_samples_per_second": 11.097,
      "eval_steps_per_second": 5.554,
      "step": 3
    },
    {
      "epoch": 0.0017097670442402222,
      "grad_norm": 1.0189697742462158,
      "learning_rate": 8e-05,
      "loss": 6.5502,
      "step": 4
    },
    {
      "epoch": 0.0021372088053002777,
      "grad_norm": 0.8076102137565613,
      "learning_rate": 0.0001,
      "loss": 6.9798,
      "step": 5
    },
    {
      "epoch": 0.0025646505663603335,
      "grad_norm": 0.9094170928001404,
      "learning_rate": 0.00012,
      "loss": 7.7738,
      "step": 6
    },
    {
      "epoch": 0.0025646505663603335,
      "eval_loss": 1.8097198009490967,
      "eval_runtime": 88.8832,
      "eval_samples_per_second": 11.082,
      "eval_steps_per_second": 5.547,
      "step": 6
    },
    {
      "epoch": 0.002992092327420389,
      "grad_norm": 0.8319992423057556,
      "learning_rate": 0.00014,
      "loss": 6.8613,
      "step": 7
    },
    {
      "epoch": 0.0034195340884804444,
      "grad_norm": 0.9422582387924194,
      "learning_rate": 0.00016,
      "loss": 6.7223,
      "step": 8
    },
    {
      "epoch": 0.0038469758495405003,
      "grad_norm": 1.0702905654907227,
      "learning_rate": 0.00018,
      "loss": 7.6078,
      "step": 9
    },
    {
      "epoch": 0.0038469758495405003,
      "eval_loss": 1.7832024097442627,
      "eval_runtime": 88.9288,
      "eval_samples_per_second": 11.076,
      "eval_steps_per_second": 5.544,
      "step": 9
    },
    {
      "epoch": 0.004274417610600555,
      "grad_norm": 1.0944204330444336,
      "learning_rate": 0.0002,
      "loss": 7.08,
      "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": 6332408345395200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}