trainer_state.json

{
  "best_metric": 1.1247614622116089,
  "best_model_checkpoint": "food-recipe-generation/checkpoint-25",
  "epoch": 0.014691478942213516,
  "eval_steps": 5,
  "global_step": 45,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 4.9185667752443e-05,
      "loss": 1.1526,
      "step": 5
    },
    {
      "epoch": 0.0,
      "eval_loss": 1.142299771308899,
      "eval_runtime": 18.2229,
      "eval_samples_per_second": 109.752,
      "eval_steps_per_second": 1.756,
      "step": 5
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.8371335504885994e-05,
      "loss": 1.2427,
      "step": 10
    },
    {
      "epoch": 0.0,
      "eval_loss": 1.1404472589492798,
      "eval_runtime": 17.9113,
      "eval_samples_per_second": 111.662,
      "eval_steps_per_second": 1.787,
      "step": 10
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.9185667752443e-05,
      "loss": 1.1104,
      "step": 15
    },
    {
      "epoch": 0.0,
      "eval_loss": 1.1525651216506958,
      "eval_runtime": 18.2243,
      "eval_samples_per_second": 109.744,
      "eval_steps_per_second": 1.756,
      "step": 15
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.8371335504885994e-05,
      "loss": 1.0834,
      "step": 20
    },
    {
      "epoch": 0.01,
      "eval_loss": 1.152503490447998,
      "eval_runtime": 17.9261,
      "eval_samples_per_second": 111.569,
      "eval_steps_per_second": 1.785,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.9185667752443e-05,
      "loss": 1.1478,
      "step": 25
    },
    {
      "epoch": 0.01,
      "eval_loss": 1.1247614622116089,
      "eval_runtime": 18.0737,
      "eval_samples_per_second": 110.658,
      "eval_steps_per_second": 1.771,
      "step": 25
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.8371335504885994e-05,
      "loss": 1.1589,
      "step": 30
    },
    {
      "epoch": 0.01,
      "eval_loss": 1.1252552270889282,
      "eval_runtime": 17.9015,
      "eval_samples_per_second": 111.722,
      "eval_steps_per_second": 1.788,
      "step": 30
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.755700325732899e-05,
      "loss": 1.1235,
      "step": 35
    },
    {
      "epoch": 0.01,
      "eval_loss": 1.1276049613952637,
      "eval_runtime": 17.7961,
      "eval_samples_per_second": 112.384,
      "eval_steps_per_second": 1.798,
      "step": 35
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.6742671009771985e-05,
      "loss": 1.2209,
      "step": 40
    },
    {
      "epoch": 0.01,
      "eval_loss": 1.1258747577667236,
      "eval_runtime": 17.8768,
      "eval_samples_per_second": 111.877,
      "eval_steps_per_second": 1.79,
      "step": 40
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.592833876221499e-05,
      "loss": 1.16,
      "step": 45
    },
    {
      "epoch": 0.01,
      "eval_loss": 1.124158501625061,
      "eval_runtime": 17.8962,
      "eval_samples_per_second": 111.756,
      "eval_steps_per_second": 1.788,
      "step": 45
    }
  ],
  "logging_steps": 5,
  "max_steps": 307,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "total_flos": 94065131520000.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}