checkpoint-110/trainer_state.json

{
  "best_metric": 7.869668006896973,
  "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/fict-full-lstm-42/checkpoints/checkpoint-110",
  "epoch": 0.88,
  "eval_steps": 10,
  "global_step": 110,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "learning_rate": 4.600000000000001e-05,
      "loss": 10.8138,
      "step": 10
    },
    {
      "epoch": 0.08,
      "eval_loss": 10.804121971130371,
      "eval_runtime": 2.7698,
      "eval_samples_per_second": 361.038,
      "eval_steps_per_second": 45.13,
      "step": 10
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.2e-05,
      "loss": 10.7943,
      "step": 20
    },
    {
      "epoch": 0.16,
      "eval_loss": 10.77995491027832,
      "eval_runtime": 2.844,
      "eval_samples_per_second": 351.614,
      "eval_steps_per_second": 43.952,
      "step": 20
    },
    {
      "epoch": 0.24,
      "learning_rate": 3.8e-05,
      "loss": 10.7591,
      "step": 30
    },
    {
      "epoch": 0.24,
      "eval_loss": 10.717215538024902,
      "eval_runtime": 2.744,
      "eval_samples_per_second": 364.436,
      "eval_steps_per_second": 45.554,
      "step": 30
    },
    {
      "epoch": 0.32,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 10.6049,
      "step": 40
    },
    {
      "epoch": 0.32,
      "eval_loss": 10.266470909118652,
      "eval_runtime": 2.7349,
      "eval_samples_per_second": 365.65,
      "eval_steps_per_second": 45.706,
      "step": 40
    },
    {
      "epoch": 0.4,
      "learning_rate": 3e-05,
      "loss": 9.8537,
      "step": 50
    },
    {
      "epoch": 0.4,
      "eval_loss": 9.23794937133789,
      "eval_runtime": 2.8879,
      "eval_samples_per_second": 346.272,
      "eval_steps_per_second": 43.284,
      "step": 50
    },
    {
      "epoch": 0.48,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 9.0545,
      "step": 60
    },
    {
      "epoch": 0.48,
      "eval_loss": 8.647107124328613,
      "eval_runtime": 2.8395,
      "eval_samples_per_second": 352.175,
      "eval_steps_per_second": 44.022,
      "step": 60
    },
    {
      "epoch": 0.56,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 8.5764,
      "step": 70
    },
    {
      "epoch": 0.56,
      "eval_loss": 8.326546669006348,
      "eval_runtime": 2.7246,
      "eval_samples_per_second": 367.023,
      "eval_steps_per_second": 45.878,
      "step": 70
    },
    {
      "epoch": 0.64,
      "learning_rate": 1.8e-05,
      "loss": 8.3924,
      "step": 80
    },
    {
      "epoch": 0.64,
      "eval_loss": 8.13099479675293,
      "eval_runtime": 2.785,
      "eval_samples_per_second": 359.073,
      "eval_steps_per_second": 44.884,
      "step": 80
    },
    {
      "epoch": 0.72,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 8.2474,
      "step": 90
    },
    {
      "epoch": 0.72,
      "eval_loss": 8.003149032592773,
      "eval_runtime": 2.752,
      "eval_samples_per_second": 363.374,
      "eval_steps_per_second": 45.422,
      "step": 90
    },
    {
      "epoch": 0.8,
      "learning_rate": 1e-05,
      "loss": 8.1181,
      "step": 100
    },
    {
      "epoch": 0.8,
      "eval_loss": 7.92080545425415,
      "eval_runtime": 2.7817,
      "eval_samples_per_second": 359.489,
      "eval_steps_per_second": 44.936,
      "step": 100
    },
    {
      "epoch": 0.88,
      "learning_rate": 6e-06,
      "loss": 8.0602,
      "step": 110
    },
    {
      "epoch": 0.88,
      "eval_loss": 7.869668006896973,
      "eval_runtime": 2.8251,
      "eval_samples_per_second": 353.965,
      "eval_steps_per_second": 44.246,
      "step": 110
    }
  ],
  "logging_steps": 10,
  "max_steps": 125,
  "num_train_epochs": 1,
  "save_steps": 10,
  "total_flos": 7737277014720.0,
  "trial_name": null,
  "trial_params": null
}