trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 17.81055096288918,
      "learning_rate": 1e-05,
      "loss": 1.1097,
      "step": 1
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.1095243692398071,
      "eval_runtime": 2.808,
      "eval_samples_per_second": 17.806,
      "eval_steps_per_second": 0.356,
      "step": 1
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.2839224338531494,
      "eval_runtime": 2.6721,
      "eval_samples_per_second": 18.712,
      "eval_steps_per_second": 0.374,
      "step": 2
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.081336259841919,
      "eval_runtime": 2.6698,
      "eval_samples_per_second": 18.728,
      "eval_steps_per_second": 0.375,
      "step": 3
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.8745010495185852,
      "eval_runtime": 2.6731,
      "eval_samples_per_second": 18.705,
      "eval_steps_per_second": 0.374,
      "step": 4
    },
    {
      "epoch": 5.0,
      "grad_norm": 18.406465212856943,
      "learning_rate": 5.8682408883346535e-06,
      "loss": 1.0879,
      "step": 5
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.7450248599052429,
      "eval_runtime": 2.6675,
      "eval_samples_per_second": 18.744,
      "eval_steps_per_second": 0.375,
      "step": 5
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.6025453209877014,
      "eval_runtime": 2.6697,
      "eval_samples_per_second": 18.729,
      "eval_steps_per_second": 0.375,
      "step": 6
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.5167475938796997,
      "eval_runtime": 2.6908,
      "eval_samples_per_second": 18.582,
      "eval_steps_per_second": 0.372,
      "step": 7
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.45393621921539307,
      "eval_runtime": 2.6892,
      "eval_samples_per_second": 18.593,
      "eval_steps_per_second": 0.372,
      "step": 8
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.4190720021724701,
      "eval_runtime": 2.6866,
      "eval_samples_per_second": 18.611,
      "eval_steps_per_second": 0.372,
      "step": 9
    },
    {
      "epoch": 10.0,
      "grad_norm": 2.9824311781074426,
      "learning_rate": 0.0,
      "loss": 0.547,
      "step": 10
    },
    {
      "epoch": 10.0,
      "eval_loss": 0.408511757850647,
      "eval_runtime": 2.6822,
      "eval_samples_per_second": 18.641,
      "eval_steps_per_second": 0.373,
      "step": 10
    },
    {
      "epoch": 10.0,
      "step": 10,
      "total_flos": 8375186227200.0,
      "train_loss": 0.8196125388145447,
      "train_runtime": 303.2537,
      "train_samples_per_second": 1.649,
      "train_steps_per_second": 0.033
    }
  ],
  "logging_steps": 5,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8375186227200.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}