last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01010611419909045,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001010611419909045,
      "grad_norm": 0.8601729869842529,
      "learning_rate": 2e-05,
      "loss": 43.4108,
      "step": 1
    },
    {
      "epoch": 0.001010611419909045,
      "eval_loss": 10.859463691711426,
      "eval_runtime": 1.1281,
      "eval_samples_per_second": 369.645,
      "eval_steps_per_second": 185.266,
      "step": 1
    },
    {
      "epoch": 0.00202122283981809,
      "grad_norm": 0.9037514925003052,
      "learning_rate": 4e-05,
      "loss": 43.4688,
      "step": 2
    },
    {
      "epoch": 0.003031834259727135,
      "grad_norm": 0.9492448568344116,
      "learning_rate": 6e-05,
      "loss": 43.4276,
      "step": 3
    },
    {
      "epoch": 0.003031834259727135,
      "eval_loss": 10.859204292297363,
      "eval_runtime": 1.1395,
      "eval_samples_per_second": 365.949,
      "eval_steps_per_second": 183.413,
      "step": 3
    },
    {
      "epoch": 0.00404244567963618,
      "grad_norm": 0.9523076415061951,
      "learning_rate": 8e-05,
      "loss": 43.4389,
      "step": 4
    },
    {
      "epoch": 0.005053057099545225,
      "grad_norm": 0.8827975392341614,
      "learning_rate": 0.0001,
      "loss": 43.4484,
      "step": 5
    },
    {
      "epoch": 0.00606366851945427,
      "grad_norm": 0.8885377645492554,
      "learning_rate": 0.00012,
      "loss": 43.4533,
      "step": 6
    },
    {
      "epoch": 0.00606366851945427,
      "eval_loss": 10.857632637023926,
      "eval_runtime": 1.191,
      "eval_samples_per_second": 350.112,
      "eval_steps_per_second": 175.476,
      "step": 6
    },
    {
      "epoch": 0.007074279939363315,
      "grad_norm": 0.8492110967636108,
      "learning_rate": 0.00014,
      "loss": 43.4244,
      "step": 7
    },
    {
      "epoch": 0.00808489135927236,
      "grad_norm": 0.873717188835144,
      "learning_rate": 0.00016,
      "loss": 43.4247,
      "step": 8
    },
    {
      "epoch": 0.009095502779181405,
      "grad_norm": 0.9080751538276672,
      "learning_rate": 0.00018,
      "loss": 43.4278,
      "step": 9
    },
    {
      "epoch": 0.009095502779181405,
      "eval_loss": 10.854981422424316,
      "eval_runtime": 1.1223,
      "eval_samples_per_second": 371.562,
      "eval_steps_per_second": 186.227,
      "step": 9
    },
    {
      "epoch": 0.01010611419909045,
      "grad_norm": 0.827238917350769,
      "learning_rate": 0.0002,
      "loss": 43.4163,
      "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": 423414988800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}