last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07797270955165692,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.015594541910331383,
      "grad_norm": 0.13151484727859497,
      "learning_rate": 1e-05,
      "loss": 10.3863,
      "step": 1
    },
    {
      "epoch": 0.015594541910331383,
      "eval_loss": NaN,
      "eval_runtime": 17.8618,
      "eval_samples_per_second": 6.102,
      "eval_steps_per_second": 3.079,
      "step": 1
    },
    {
      "epoch": 0.031189083820662766,
      "grad_norm": 0.1809103935956955,
      "learning_rate": 2e-05,
      "loss": 10.374,
      "step": 2
    },
    {
      "epoch": 0.031189083820662766,
      "eval_loss": NaN,
      "eval_runtime": 0.3669,
      "eval_samples_per_second": 297.047,
      "eval_steps_per_second": 149.886,
      "step": 2
    },
    {
      "epoch": 0.04678362573099415,
      "grad_norm": 0.1230270192027092,
      "learning_rate": 3e-05,
      "loss": 10.3889,
      "step": 3
    },
    {
      "epoch": 0.06237816764132553,
      "grad_norm": 0.16764244437217712,
      "learning_rate": 4e-05,
      "loss": 10.3611,
      "step": 4
    },
    {
      "epoch": 0.06237816764132553,
      "eval_loss": NaN,
      "eval_runtime": 0.3672,
      "eval_samples_per_second": 296.844,
      "eval_steps_per_second": 149.784,
      "step": 4
    },
    {
      "epoch": 0.07797270955165692,
      "grad_norm": 0.14769285917282104,
      "learning_rate": 5e-05,
      "loss": 10.3737,
      "step": 5
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 258618163200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}