last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.047232472324723246,
  "eval_steps": 2,
  "global_step": 4,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011808118081180811,
      "grad_norm": 5.35214376449585,
      "learning_rate": 1e-05,
      "loss": 4.262,
      "step": 1
    },
    {
      "epoch": 0.011808118081180811,
      "eval_loss": 4.50460958480835,
      "eval_runtime": 94.2273,
      "eval_samples_per_second": 1.518,
      "eval_steps_per_second": 0.764,
      "step": 1
    },
    {
      "epoch": 0.023616236162361623,
      "grad_norm": 5.474025726318359,
      "learning_rate": 2e-05,
      "loss": 4.6155,
      "step": 2
    },
    {
      "epoch": 0.023616236162361623,
      "eval_loss": 4.437295913696289,
      "eval_runtime": 3.65,
      "eval_samples_per_second": 39.178,
      "eval_steps_per_second": 19.726,
      "step": 2
    },
    {
      "epoch": 0.035424354243542434,
      "grad_norm": 5.545555591583252,
      "learning_rate": 3e-05,
      "loss": 4.277,
      "step": 3
    },
    {
      "epoch": 0.047232472324723246,
      "grad_norm": 5.9043288230896,
      "learning_rate": 4e-05,
      "loss": 4.2889,
      "step": 4
    },
    {
      "epoch": 0.047232472324723246,
      "eval_loss": 4.217742443084717,
      "eval_runtime": 3.6648,
      "eval_samples_per_second": 39.02,
      "eval_steps_per_second": 19.646,
      "step": 4
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3057746266030080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}