last-checkpoint/trainer_state.json

{
  "best_metric": 1.500829815864563,
  "best_model_checkpoint": "./outputs/checkpoint-400",
  "epoch": 0.5333333333333333,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 1.4574,
      "step": 100
    },
    {
      "epoch": 0.13,
      "eval_loss": 1.5645889043807983,
      "eval_runtime": 93.6488,
      "eval_samples_per_second": 15.494,
      "eval_steps_per_second": 1.943,
      "step": 100
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 1.2971,
      "step": 200
    },
    {
      "epoch": 0.27,
      "eval_loss": 1.5321934223175049,
      "eval_runtime": 93.3383,
      "eval_samples_per_second": 15.546,
      "eval_steps_per_second": 1.95,
      "step": 200
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 1.2756,
      "step": 300
    },
    {
      "epoch": 0.4,
      "eval_loss": 1.5133259296417236,
      "eval_runtime": 93.2652,
      "eval_samples_per_second": 15.558,
      "eval_steps_per_second": 1.951,
      "step": 300
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 1.2661,
      "step": 400
    },
    {
      "epoch": 0.53,
      "eval_loss": 1.500829815864563,
      "eval_runtime": 93.3122,
      "eval_samples_per_second": 15.55,
      "eval_steps_per_second": 1.95,
      "step": 400
    }
  ],
  "logging_steps": 100,
  "max_steps": 2250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 2.340946069733376e+16,
  "trial_name": null,
  "trial_params": null
}