last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.8444444444444446,
  "eval_steps": 60,
  "global_step": 960,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 1.293,
      "step": 60
    },
    {
      "epoch": 0.18,
      "eval_runtime": 313.4076,
      "eval_samples_per_second": 1.914,
      "eval_steps_per_second": 0.239,
      "step": 60
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 0.6736,
      "step": 120
    },
    {
      "epoch": 0.36,
      "eval_runtime": 313.3616,
      "eval_samples_per_second": 1.915,
      "eval_steps_per_second": 0.239,
      "step": 120
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 0.6332,
      "step": 180
    },
    {
      "epoch": 0.53,
      "eval_runtime": 313.7062,
      "eval_samples_per_second": 1.913,
      "eval_steps_per_second": 0.239,
      "step": 180
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002,
      "loss": 0.6116,
      "step": 240
    },
    {
      "epoch": 0.71,
      "eval_runtime": 313.0801,
      "eval_samples_per_second": 1.916,
      "eval_steps_per_second": 0.24,
      "step": 240
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002,
      "loss": 0.633,
      "step": 300
    },
    {
      "epoch": 0.89,
      "eval_runtime": 312.6613,
      "eval_samples_per_second": 1.919,
      "eval_steps_per_second": 0.24,
      "step": 300
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 0.5895,
      "step": 360
    },
    {
      "epoch": 1.07,
      "eval_runtime": 313.3051,
      "eval_samples_per_second": 1.915,
      "eval_steps_per_second": 0.239,
      "step": 360
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0002,
      "loss": 0.5845,
      "step": 420
    },
    {
      "epoch": 1.24,
      "eval_runtime": 313.2319,
      "eval_samples_per_second": 1.916,
      "eval_steps_per_second": 0.239,
      "step": 420
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0002,
      "loss": 0.5876,
      "step": 480
    },
    {
      "epoch": 1.42,
      "eval_runtime": 313.3956,
      "eval_samples_per_second": 1.915,
      "eval_steps_per_second": 0.239,
      "step": 480
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0002,
      "loss": 0.569,
      "step": 540
    },
    {
      "epoch": 1.6,
      "eval_runtime": 313.3538,
      "eval_samples_per_second": 1.915,
      "eval_steps_per_second": 0.239,
      "step": 540
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.0002,
      "loss": 0.5487,
      "step": 600
    },
    {
      "epoch": 1.78,
      "eval_runtime": 312.5543,
      "eval_samples_per_second": 1.92,
      "eval_steps_per_second": 0.24,
      "step": 600
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.0002,
      "loss": 0.5531,
      "step": 660
    },
    {
      "epoch": 1.96,
      "eval_runtime": 312.6322,
      "eval_samples_per_second": 1.919,
      "eval_steps_per_second": 0.24,
      "step": 660
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.0002,
      "loss": 0.5315,
      "step": 720
    },
    {
      "epoch": 2.13,
      "eval_runtime": 312.3646,
      "eval_samples_per_second": 1.921,
      "eval_steps_per_second": 0.24,
      "step": 720
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.0002,
      "loss": 0.5064,
      "step": 780
    },
    {
      "epoch": 2.31,
      "eval_runtime": 312.4619,
      "eval_samples_per_second": 1.92,
      "eval_steps_per_second": 0.24,
      "step": 780
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.0002,
      "loss": 0.5125,
      "step": 840
    },
    {
      "epoch": 2.49,
      "eval_runtime": 312.7044,
      "eval_samples_per_second": 1.919,
      "eval_steps_per_second": 0.24,
      "step": 840
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.0002,
      "loss": 0.476,
      "step": 900
    },
    {
      "epoch": 2.67,
      "eval_runtime": 312.5341,
      "eval_samples_per_second": 1.92,
      "eval_steps_per_second": 0.24,
      "step": 900
    },
    {
      "epoch": 2.84,
      "learning_rate": 0.0002,
      "loss": 0.5142,
      "step": 960
    },
    {
      "epoch": 2.84,
      "eval_runtime": 312.6866,
      "eval_samples_per_second": 1.919,
      "eval_steps_per_second": 0.24,
      "step": 960
    }
  ],
  "logging_steps": 60,
  "max_steps": 1011,
  "num_train_epochs": 3,
  "save_steps": 60,
  "total_flos": 1.5945703889043456e+17,
  "trial_name": null,
  "trial_params": null
}