trainer_state.json

{
  "best_metric": 0.62215256690979,
  "best_model_checkpoint": "out/checkpoint-10",
  "epoch": 0.015779092702169626,
  "eval_steps": 1,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "grad_norm": 3.933871030807495,
      "learning_rate": 0.0002,
      "loss": 1.9531,
      "step": 1
    },
    {
      "epoch": 0.0,
      "eval_loss": 1.4585089683532715,
      "eval_runtime": 771.2896,
      "eval_samples_per_second": 0.366,
      "eval_steps_per_second": 0.366,
      "step": 1
    },
    {
      "epoch": 0.0,
      "grad_norm": 3.870039701461792,
      "learning_rate": 0.0002,
      "loss": 1.636,
      "step": 2
    },
    {
      "epoch": 0.0,
      "eval_loss": 1.1349122524261475,
      "eval_runtime": 771.384,
      "eval_samples_per_second": 0.366,
      "eval_steps_per_second": 0.366,
      "step": 2
    },
    {
      "epoch": 0.0,
      "grad_norm": 3.2541444301605225,
      "learning_rate": 0.0002,
      "loss": 1.2164,
      "step": 3
    },
    {
      "epoch": 0.0,
      "eval_loss": 0.9079858064651489,
      "eval_runtime": 771.4502,
      "eval_samples_per_second": 0.366,
      "eval_steps_per_second": 0.366,
      "step": 3
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.9149177074432373,
      "learning_rate": 0.0002,
      "loss": 0.8732,
      "step": 4
    },
    {
      "epoch": 0.01,
      "eval_loss": 0.826586902141571,
      "eval_runtime": 771.3095,
      "eval_samples_per_second": 0.366,
      "eval_steps_per_second": 0.366,
      "step": 4
    },
    {
      "epoch": 0.01,
      "grad_norm": 2.3286924362182617,
      "learning_rate": 0.0002,
      "loss": 0.8159,
      "step": 5
    },
    {
      "epoch": 0.01,
      "eval_loss": 0.767815887928009,
      "eval_runtime": 771.3337,
      "eval_samples_per_second": 0.366,
      "eval_steps_per_second": 0.366,
      "step": 5
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.8554341197013855,
      "learning_rate": 0.0002,
      "loss": 0.7762,
      "step": 6
    },
    {
      "epoch": 0.01,
      "eval_loss": 0.72954261302948,
      "eval_runtime": 771.3481,
      "eval_samples_per_second": 0.366,
      "eval_steps_per_second": 0.366,
      "step": 6
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.7430621981620789,
      "learning_rate": 0.0002,
      "loss": 0.7681,
      "step": 7
    },
    {
      "epoch": 0.01,
      "eval_loss": 0.6940924525260925,
      "eval_runtime": 771.3451,
      "eval_samples_per_second": 0.366,
      "eval_steps_per_second": 0.366,
      "step": 7
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.754584789276123,
      "learning_rate": 0.0002,
      "loss": 0.7104,
      "step": 8
    },
    {
      "epoch": 0.01,
      "eval_loss": 0.6611207127571106,
      "eval_runtime": 771.3383,
      "eval_samples_per_second": 0.366,
      "eval_steps_per_second": 0.366,
      "step": 8
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.7047972679138184,
      "learning_rate": 0.0002,
      "loss": 0.6199,
      "step": 9
    },
    {
      "epoch": 0.01,
      "eval_loss": 0.6389196515083313,
      "eval_runtime": 771.3392,
      "eval_samples_per_second": 0.366,
      "eval_steps_per_second": 0.366,
      "step": 9
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.9041690826416016,
      "learning_rate": 0.0002,
      "loss": 0.6575,
      "step": 10
    },
    {
      "epoch": 0.02,
      "eval_loss": 0.62215256690979,
      "eval_runtime": 771.3182,
      "eval_samples_per_second": 0.366,
      "eval_steps_per_second": 0.366,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1,
  "total_flos": 1752669785948160.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}