last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0009290658243136526,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.290658243136526e-05,
      "grad_norm": 42.913795471191406,
      "learning_rate": 2e-05,
      "loss": 13.8547,
      "step": 1
    },
    {
      "epoch": 0.00018581316486273051,
      "grad_norm": 37.62971878051758,
      "learning_rate": 4e-05,
      "loss": 13.9481,
      "step": 2
    },
    {
      "epoch": 0.00027871974729409577,
      "grad_norm": 43.87750244140625,
      "learning_rate": 6e-05,
      "loss": 13.5865,
      "step": 3
    },
    {
      "epoch": 0.00027871974729409577,
      "eval_loss": 3.4376113414764404,
      "eval_runtime": 118.0395,
      "eval_samples_per_second": 38.394,
      "eval_steps_per_second": 19.197,
      "step": 3
    },
    {
      "epoch": 0.00037162632972546103,
      "grad_norm": 50.38986587524414,
      "learning_rate": 8e-05,
      "loss": 13.6738,
      "step": 4
    },
    {
      "epoch": 0.0004645329121568263,
      "grad_norm": 51.37370681762695,
      "learning_rate": 0.0001,
      "loss": 15.8409,
      "step": 5
    },
    {
      "epoch": 0.0005574394945881915,
      "grad_norm": 65.8694839477539,
      "learning_rate": 0.00012,
      "loss": 13.3023,
      "step": 6
    },
    {
      "epoch": 0.0005574394945881915,
      "eval_loss": 3.433248519897461,
      "eval_runtime": 118.5003,
      "eval_samples_per_second": 38.245,
      "eval_steps_per_second": 19.122,
      "step": 6
    },
    {
      "epoch": 0.0006503460770195569,
      "grad_norm": 44.13718032836914,
      "learning_rate": 0.00014,
      "loss": 13.328,
      "step": 7
    },
    {
      "epoch": 0.0007432526594509221,
      "grad_norm": 52.688873291015625,
      "learning_rate": 0.00016,
      "loss": 13.0226,
      "step": 8
    },
    {
      "epoch": 0.0008361592418822874,
      "grad_norm": 60.45896911621094,
      "learning_rate": 0.00018,
      "loss": 13.8277,
      "step": 9
    },
    {
      "epoch": 0.0008361592418822874,
      "eval_loss": 3.415884494781494,
      "eval_runtime": 116.4689,
      "eval_samples_per_second": 38.912,
      "eval_steps_per_second": 19.456,
      "step": 9
    },
    {
      "epoch": 0.0009290658243136526,
      "grad_norm": 53.029144287109375,
      "learning_rate": 0.0002,
      "loss": 14.5572,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 92114994069504.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}