checkpoint-150/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.3076923076923075,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 222.5110626220703,
      "learning_rate": 7.950000000000002e-06,
      "loss": 6.9812,
      "step": 50
    },
    {
      "epoch": 0.7692307692307693,
      "eval_loss": 7.659696102142334,
      "eval_runtime": 13.2341,
      "eval_samples_per_second": 9.899,
      "eval_steps_per_second": 1.285,
      "step": 50
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 354.31988525390625,
      "learning_rate": 5.500000000000001e-06,
      "loss": 5.1829,
      "step": 100
    },
    {
      "epoch": 1.5384615384615383,
      "eval_loss": 7.435208320617676,
      "eval_runtime": 12.0118,
      "eval_samples_per_second": 10.906,
      "eval_steps_per_second": 1.415,
      "step": 100
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 373.4967346191406,
      "learning_rate": 3e-06,
      "loss": 4.5311,
      "step": 150
    },
    {
      "epoch": 2.3076923076923075,
      "eval_loss": 7.100094318389893,
      "eval_runtime": 11.9696,
      "eval_samples_per_second": 10.944,
      "eval_steps_per_second": 1.42,
      "step": 150
    }
  ],
  "logging_steps": 50,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.73364749312e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}