last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.026595744680851064,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0026595744680851063,
      "grad_norm": 0.04255756735801697,
      "learning_rate": 2e-05,
      "loss": 10.3831,
      "step": 1
    },
    {
      "epoch": 0.005319148936170213,
      "grad_norm": 0.03450145572423935,
      "learning_rate": 4e-05,
      "loss": 10.3816,
      "step": 2
    },
    {
      "epoch": 0.007978723404255319,
      "grad_norm": 0.03032597154378891,
      "learning_rate": 6e-05,
      "loss": 10.3857,
      "step": 3
    },
    {
      "epoch": 0.007978723404255319,
      "eval_loss": 10.372939109802246,
      "eval_runtime": 2.4455,
      "eval_samples_per_second": 65.017,
      "eval_steps_per_second": 32.713,
      "step": 3
    },
    {
      "epoch": 0.010638297872340425,
      "grad_norm": 0.03801236301660538,
      "learning_rate": 8e-05,
      "loss": 10.3758,
      "step": 4
    },
    {
      "epoch": 0.013297872340425532,
      "grad_norm": 0.04011368006467819,
      "learning_rate": 0.0001,
      "loss": 10.3781,
      "step": 5
    },
    {
      "epoch": 0.015957446808510637,
      "grad_norm": 0.0383019782602787,
      "learning_rate": 0.00012,
      "loss": 10.3718,
      "step": 6
    },
    {
      "epoch": 0.015957446808510637,
      "eval_loss": 10.37285327911377,
      "eval_runtime": 2.801,
      "eval_samples_per_second": 56.765,
      "eval_steps_per_second": 28.561,
      "step": 6
    },
    {
      "epoch": 0.018617021276595744,
      "grad_norm": 0.05357980728149414,
      "learning_rate": 0.00014,
      "loss": 10.3758,
      "step": 7
    },
    {
      "epoch": 0.02127659574468085,
      "grad_norm": 0.04198058694601059,
      "learning_rate": 0.00016,
      "loss": 10.3611,
      "step": 8
    },
    {
      "epoch": 0.023936170212765957,
      "grad_norm": 0.03890116140246391,
      "learning_rate": 0.00018,
      "loss": 10.3736,
      "step": 9
    },
    {
      "epoch": 0.023936170212765957,
      "eval_loss": 10.37270736694336,
      "eval_runtime": 3.1299,
      "eval_samples_per_second": 50.801,
      "eval_steps_per_second": 25.56,
      "step": 9
    },
    {
      "epoch": 0.026595744680851064,
      "grad_norm": 0.05749232694506645,
      "learning_rate": 0.0002,
      "loss": 10.3787,
      "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": 193963622400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}