last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.057927961381359076,
  "eval_steps": 13,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014853323431117712,
      "eval_loss": 0.44206228852272034,
      "eval_runtime": 6.4914,
      "eval_samples_per_second": 174.692,
      "eval_steps_per_second": 21.875,
      "step": 1
    },
    {
      "epoch": 0.007426661715558856,
      "grad_norm": 1.8116068840026855,
      "learning_rate": 5e-05,
      "loss": 0.3882,
      "step": 5
    },
    {
      "epoch": 0.014853323431117713,
      "grad_norm": 1.2223440408706665,
      "learning_rate": 0.0001,
      "loss": 0.288,
      "step": 10
    },
    {
      "epoch": 0.019309320460453028,
      "eval_loss": 0.030824489891529083,
      "eval_runtime": 6.4833,
      "eval_samples_per_second": 174.911,
      "eval_steps_per_second": 21.902,
      "step": 13
    },
    {
      "epoch": 0.02227998514667657,
      "grad_norm": 0.8314740657806396,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0695,
      "step": 15
    },
    {
      "epoch": 0.029706646862235425,
      "grad_norm": 0.18348777294158936,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0089,
      "step": 20
    },
    {
      "epoch": 0.03713330857779428,
      "grad_norm": 0.10115423798561096,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0029,
      "step": 25
    },
    {
      "epoch": 0.038618640920906055,
      "eval_loss": 0.0019636948127299547,
      "eval_runtime": 6.4581,
      "eval_samples_per_second": 175.594,
      "eval_steps_per_second": 21.988,
      "step": 26
    },
    {
      "epoch": 0.04455997029335314,
      "grad_norm": 0.027285493910312653,
      "learning_rate": 5e-05,
      "loss": 0.0019,
      "step": 30
    },
    {
      "epoch": 0.051986632008911994,
      "grad_norm": 0.12763981521129608,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.002,
      "step": 35
    },
    {
      "epoch": 0.057927961381359076,
      "eval_loss": 0.0011094427900388837,
      "eval_runtime": 6.4923,
      "eval_samples_per_second": 174.67,
      "eval_steps_per_second": 21.872,
      "step": 39
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1388995338567680.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}