last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0002796655200380345,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.7966552003803452e-05,
      "grad_norm": 0.4715335965156555,
      "learning_rate": 2e-05,
      "loss": 1.3726,
      "step": 1
    },
    {
      "epoch": 2.7966552003803452e-05,
      "eval_loss": 1.5282303094863892,
      "eval_runtime": 476.4551,
      "eval_samples_per_second": 31.6,
      "eval_steps_per_second": 15.8,
      "step": 1
    },
    {
      "epoch": 5.5933104007606904e-05,
      "grad_norm": 0.5463367700576782,
      "learning_rate": 4e-05,
      "loss": 1.4697,
      "step": 2
    },
    {
      "epoch": 8.389965601141036e-05,
      "grad_norm": 0.5575423240661621,
      "learning_rate": 6e-05,
      "loss": 1.6219,
      "step": 3
    },
    {
      "epoch": 8.389965601141036e-05,
      "eval_loss": 1.520351529121399,
      "eval_runtime": 474.7549,
      "eval_samples_per_second": 31.713,
      "eval_steps_per_second": 15.857,
      "step": 3
    },
    {
      "epoch": 0.00011186620801521381,
      "grad_norm": 0.5257006287574768,
      "learning_rate": 8e-05,
      "loss": 1.5193,
      "step": 4
    },
    {
      "epoch": 0.00013983276001901726,
      "grad_norm": 0.6386916041374207,
      "learning_rate": 0.0001,
      "loss": 1.5173,
      "step": 5
    },
    {
      "epoch": 0.00016779931202282072,
      "grad_norm": 0.7082046270370483,
      "learning_rate": 0.00012,
      "loss": 1.5421,
      "step": 6
    },
    {
      "epoch": 0.00016779931202282072,
      "eval_loss": 1.4413247108459473,
      "eval_runtime": 474.1367,
      "eval_samples_per_second": 31.755,
      "eval_steps_per_second": 15.877,
      "step": 6
    },
    {
      "epoch": 0.00019576586402662415,
      "grad_norm": 0.7304009199142456,
      "learning_rate": 0.00014,
      "loss": 1.4453,
      "step": 7
    },
    {
      "epoch": 0.00022373241603042762,
      "grad_norm": 0.6770246028900146,
      "learning_rate": 0.00016,
      "loss": 1.3765,
      "step": 8
    },
    {
      "epoch": 0.0002516989680342311,
      "grad_norm": 0.609645664691925,
      "learning_rate": 0.00018,
      "loss": 1.4726,
      "step": 9
    },
    {
      "epoch": 0.0002516989680342311,
      "eval_loss": 1.239150047302246,
      "eval_runtime": 473.7301,
      "eval_samples_per_second": 31.782,
      "eval_steps_per_second": 15.891,
      "step": 9
    },
    {
      "epoch": 0.0002796655200380345,
      "grad_norm": 0.5743552446365356,
      "learning_rate": 0.0002,
      "loss": 1.1651,
      "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": 1647822923366400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}