checkpoint-13/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.04,
  "eval_steps": 4,
  "global_step": 13,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "grad_norm": 102.28898620605469,
      "learning_rate": 2e-05,
      "loss": 6.6367,
      "step": 1
    },
    {
      "epoch": 0.08,
      "eval_loss": 7.300913333892822,
      "eval_runtime": 1.3523,
      "eval_samples_per_second": 8.873,
      "eval_steps_per_second": 4.437,
      "step": 1
    },
    {
      "epoch": 0.16,
      "grad_norm": 103.4541015625,
      "learning_rate": 4e-05,
      "loss": 7.0616,
      "step": 2
    },
    {
      "epoch": 0.24,
      "grad_norm": 67.47515869140625,
      "learning_rate": 6e-05,
      "loss": 4.686,
      "step": 3
    },
    {
      "epoch": 0.32,
      "grad_norm": 72.36919403076172,
      "learning_rate": 8e-05,
      "loss": 2.3866,
      "step": 4
    },
    {
      "epoch": 0.32,
      "eval_loss": 0.7137572169303894,
      "eval_runtime": 1.3532,
      "eval_samples_per_second": 8.868,
      "eval_steps_per_second": 4.434,
      "step": 4
    },
    {
      "epoch": 0.4,
      "grad_norm": 16.83085060119629,
      "learning_rate": 0.0001,
      "loss": 0.6844,
      "step": 5
    },
    {
      "epoch": 0.48,
      "grad_norm": 25.897714614868164,
      "learning_rate": 0.00012,
      "loss": 0.914,
      "step": 6
    },
    {
      "epoch": 0.56,
      "grad_norm": 18.89151382446289,
      "learning_rate": 0.00014,
      "loss": 0.63,
      "step": 7
    },
    {
      "epoch": 0.64,
      "grad_norm": 27.15555763244629,
      "learning_rate": 0.00016,
      "loss": 0.948,
      "step": 8
    },
    {
      "epoch": 0.64,
      "eval_loss": 1.0445994138717651,
      "eval_runtime": 1.356,
      "eval_samples_per_second": 8.85,
      "eval_steps_per_second": 4.425,
      "step": 8
    },
    {
      "epoch": 0.72,
      "grad_norm": 20.812381744384766,
      "learning_rate": 0.00018,
      "loss": 1.0285,
      "step": 9
    },
    {
      "epoch": 0.8,
      "grad_norm": 56.3886604309082,
      "learning_rate": 0.0002,
      "loss": 1.3756,
      "step": 10
    },
    {
      "epoch": 0.88,
      "grad_norm": 6.24803352355957,
      "learning_rate": 0.00019981755542233177,
      "loss": 0.5178,
      "step": 11
    },
    {
      "epoch": 0.96,
      "grad_norm": 8.379430770874023,
      "learning_rate": 0.0001992708874098054,
      "loss": 0.6822,
      "step": 12
    },
    {
      "epoch": 0.96,
      "eval_loss": 1.3959709405899048,
      "eval_runtime": 1.3583,
      "eval_samples_per_second": 8.835,
      "eval_steps_per_second": 4.417,
      "step": 12
    },
    {
      "epoch": 1.04,
      "grad_norm": 20.744348526000977,
      "learning_rate": 0.00019836199069471437,
      "loss": 1.3762,
      "step": 13
    }
  ],
  "logging_steps": 1,
  "max_steps": 62,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 13,
  "total_flos": 1138234761412608.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}