checkpoint-10/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,
      "eval_loss": 13.424697875976562,
      "eval_runtime": 2.2217,
      "eval_samples_per_second": 0.45,
      "eval_steps_per_second": 0.45,
      "step": 1
    },
    {
      "epoch": 2.0,
      "eval_loss": 12.29906940460205,
      "eval_runtime": 2.211,
      "eval_samples_per_second": 0.452,
      "eval_steps_per_second": 0.452,
      "step": 2
    },
    {
      "epoch": 3.0,
      "eval_loss": 11.366955757141113,
      "eval_runtime": 2.4749,
      "eval_samples_per_second": 0.404,
      "eval_steps_per_second": 0.404,
      "step": 3
    },
    {
      "epoch": 4.0,
      "eval_loss": 10.522193908691406,
      "eval_runtime": 2.3961,
      "eval_samples_per_second": 0.417,
      "eval_steps_per_second": 0.417,
      "step": 4
    },
    {
      "epoch": 5.0,
      "eval_loss": 9.74390697479248,
      "eval_runtime": 2.3214,
      "eval_samples_per_second": 0.431,
      "eval_steps_per_second": 0.431,
      "step": 5
    },
    {
      "epoch": 6.0,
      "eval_loss": 9.092266082763672,
      "eval_runtime": 2.2203,
      "eval_samples_per_second": 0.45,
      "eval_steps_per_second": 0.45,
      "step": 6
    },
    {
      "epoch": 7.0,
      "eval_loss": 8.59588623046875,
      "eval_runtime": 2.21,
      "eval_samples_per_second": 0.452,
      "eval_steps_per_second": 0.452,
      "step": 7
    },
    {
      "epoch": 8.0,
      "eval_loss": 8.250038146972656,
      "eval_runtime": 2.2672,
      "eval_samples_per_second": 0.441,
      "eval_steps_per_second": 0.441,
      "step": 8
    },
    {
      "epoch": 9.0,
      "eval_loss": 8.015463829040527,
      "eval_runtime": 2.3205,
      "eval_samples_per_second": 0.431,
      "eval_steps_per_second": 0.431,
      "step": 9
    },
    {
      "epoch": 10.0,
      "eval_loss": 7.904967308044434,
      "eval_runtime": 3.4819,
      "eval_samples_per_second": 0.287,
      "eval_steps_per_second": 0.287,
      "step": 10
    }
  ],
  "logging_steps": 50,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9134368358400.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}