checkpoint-100/trainer_state.json

{
  "best_metric": 2.6393470764160156,
  "best_model_checkpoint": "./Qwen2-4B-Chat-hinglish-sft/checkpoint-100",
  "epoch": 0.3972194637537239,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "grad_norm": 1.1830133199691772,
      "learning_rate": 0.00019999629591162656,
      "loss": 4.7862,
      "step": 25
    },
    {
      "epoch": 0.1,
      "eval_loss": 4.098670482635498,
      "eval_runtime": 4.1063,
      "eval_samples_per_second": 2.679,
      "eval_steps_per_second": 2.679,
      "step": 25
    },
    {
      "epoch": 0.2,
      "grad_norm": 1.0619295835494995,
      "learning_rate": 0.00019932568492674144,
      "loss": 2.9161,
      "step": 50
    },
    {
      "epoch": 0.2,
      "eval_loss": 3.1406357288360596,
      "eval_runtime": 4.0777,
      "eval_samples_per_second": 2.698,
      "eval_steps_per_second": 2.698,
      "step": 50
    },
    {
      "epoch": 0.3,
      "grad_norm": 1.1028335094451904,
      "learning_rate": 0.0001975064532257195,
      "loss": 2.4282,
      "step": 75
    },
    {
      "epoch": 0.3,
      "eval_loss": 2.8003995418548584,
      "eval_runtime": 4.076,
      "eval_samples_per_second": 2.699,
      "eval_steps_per_second": 2.699,
      "step": 75
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.9855464100837708,
      "learning_rate": 0.00019455963874271426,
      "loss": 2.2815,
      "step": 100
    },
    {
      "epoch": 0.4,
      "eval_loss": 2.6393470764160156,
      "eval_runtime": 4.084,
      "eval_samples_per_second": 2.693,
      "eval_steps_per_second": 2.693,
      "step": 100
    }
  ],
  "logging_steps": 25,
  "max_steps": 753,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 25,
  "total_flos": 724268700426240.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}