last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0020930354246245617,
  "eval_steps": 8,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00020930354246245618,
      "eval_loss": 1.9980238676071167,
      "eval_runtime": 382.1313,
      "eval_samples_per_second": 5.265,
      "eval_steps_per_second": 2.633,
      "step": 1
    },
    {
      "epoch": 0.0006279106273873685,
      "grad_norm": 0.5501781105995178,
      "learning_rate": 6e-05,
      "loss": 1.9814,
      "step": 3
    },
    {
      "epoch": 0.001255821254774737,
      "grad_norm": 0.6605830788612366,
      "learning_rate": 0.00012,
      "loss": 1.9938,
      "step": 6
    },
    {
      "epoch": 0.0016744283396996494,
      "eval_loss": 1.7701950073242188,
      "eval_runtime": 384.4451,
      "eval_samples_per_second": 5.234,
      "eval_steps_per_second": 2.617,
      "step": 8
    },
    {
      "epoch": 0.0018837318821621056,
      "grad_norm": 0.38709595799446106,
      "learning_rate": 0.00018,
      "loss": 1.8724,
      "step": 9
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5040842641244160.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}