last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02852388875683385,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009507962918944616,
      "eval_loss": 11.763189315795898,
      "eval_runtime": 2.0449,
      "eval_samples_per_second": 216.641,
      "eval_steps_per_second": 108.565,
      "step": 1
    },
    {
      "epoch": 0.0028523888756833847,
      "grad_norm": 0.039515238255262375,
      "learning_rate": 3e-05,
      "loss": 11.7618,
      "step": 3
    },
    {
      "epoch": 0.004753981459472308,
      "eval_loss": 11.763093948364258,
      "eval_runtime": 2.024,
      "eval_samples_per_second": 218.871,
      "eval_steps_per_second": 109.682,
      "step": 5
    },
    {
      "epoch": 0.0057047777513667694,
      "grad_norm": 0.04526564106345177,
      "learning_rate": 6e-05,
      "loss": 11.7598,
      "step": 6
    },
    {
      "epoch": 0.008557166627050155,
      "grad_norm": 0.03885379061102867,
      "learning_rate": 9e-05,
      "loss": 11.7616,
      "step": 9
    },
    {
      "epoch": 0.009507962918944617,
      "eval_loss": 11.762765884399414,
      "eval_runtime": 2.0221,
      "eval_samples_per_second": 219.083,
      "eval_steps_per_second": 109.789,
      "step": 10
    },
    {
      "epoch": 0.011409555502733539,
      "grad_norm": 0.040299348533153534,
      "learning_rate": 9.755282581475769e-05,
      "loss": 11.7613,
      "step": 12
    },
    {
      "epoch": 0.014261944378416925,
      "grad_norm": 0.044069357216358185,
      "learning_rate": 8.535533905932738e-05,
      "loss": 11.7623,
      "step": 15
    },
    {
      "epoch": 0.014261944378416925,
      "eval_loss": 11.762299537658691,
      "eval_runtime": 2.0611,
      "eval_samples_per_second": 214.93,
      "eval_steps_per_second": 107.708,
      "step": 15
    },
    {
      "epoch": 0.01711433325410031,
      "grad_norm": 0.04311707988381386,
      "learning_rate": 6.545084971874738e-05,
      "loss": 11.761,
      "step": 18
    },
    {
      "epoch": 0.019015925837889233,
      "eval_loss": 11.76194953918457,
      "eval_runtime": 2.1131,
      "eval_samples_per_second": 209.647,
      "eval_steps_per_second": 105.06,
      "step": 20
    },
    {
      "epoch": 0.019966722129783693,
      "grad_norm": 0.04312145337462425,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 11.7611,
      "step": 21
    },
    {
      "epoch": 0.022819111005467078,
      "grad_norm": 0.04996311292052269,
      "learning_rate": 2.061073738537635e-05,
      "loss": 11.7617,
      "step": 24
    },
    {
      "epoch": 0.02376990729736154,
      "eval_loss": 11.761777877807617,
      "eval_runtime": 2.0759,
      "eval_samples_per_second": 213.399,
      "eval_steps_per_second": 106.94,
      "step": 25
    },
    {
      "epoch": 0.025671499881150462,
      "grad_norm": 0.041388753801584244,
      "learning_rate": 5.449673790581611e-06,
      "loss": 11.7614,
      "step": 27
    },
    {
      "epoch": 0.02852388875683385,
      "grad_norm": 0.043048761785030365,
      "learning_rate": 0.0,
      "loss": 11.7594,
      "step": 30
    },
    {
      "epoch": 0.02852388875683385,
      "eval_loss": 11.761744499206543,
      "eval_runtime": 2.0399,
      "eval_samples_per_second": 217.168,
      "eval_steps_per_second": 108.829,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3055500656640.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}