last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0008595680670463093,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.595680670463093e-05,
      "grad_norm": 20.497228622436523,
      "learning_rate": 2e-05,
      "loss": 16.756,
      "step": 1
    },
    {
      "epoch": 0.00017191361340926185,
      "grad_norm": 19.87226676940918,
      "learning_rate": 4e-05,
      "loss": 17.2255,
      "step": 2
    },
    {
      "epoch": 0.0002578704201138928,
      "grad_norm": 16.698732376098633,
      "learning_rate": 6e-05,
      "loss": 15.8207,
      "step": 3
    },
    {
      "epoch": 0.0002578704201138928,
      "eval_loss": 4.111976623535156,
      "eval_runtime": 149.7863,
      "eval_samples_per_second": 32.707,
      "eval_steps_per_second": 16.357,
      "step": 3
    },
    {
      "epoch": 0.0003438272268185237,
      "grad_norm": 20.95673179626465,
      "learning_rate": 8e-05,
      "loss": 18.2729,
      "step": 4
    },
    {
      "epoch": 0.00042978403352315463,
      "grad_norm": 18.295108795166016,
      "learning_rate": 0.0001,
      "loss": 16.4431,
      "step": 5
    },
    {
      "epoch": 0.0005157408402277856,
      "grad_norm": 20.75150489807129,
      "learning_rate": 0.00012,
      "loss": 17.5493,
      "step": 6
    },
    {
      "epoch": 0.0005157408402277856,
      "eval_loss": 3.6224875450134277,
      "eval_runtime": 157.5029,
      "eval_samples_per_second": 31.104,
      "eval_steps_per_second": 15.555,
      "step": 6
    },
    {
      "epoch": 0.0006016976469324165,
      "grad_norm": 18.490615844726562,
      "learning_rate": 0.00014,
      "loss": 14.4872,
      "step": 7
    },
    {
      "epoch": 0.0006876544536370474,
      "grad_norm": 22.34310531616211,
      "learning_rate": 0.00016,
      "loss": 14.1407,
      "step": 8
    },
    {
      "epoch": 0.0007736112603416783,
      "grad_norm": 17.5768985748291,
      "learning_rate": 0.00018,
      "loss": 11.6362,
      "step": 9
    },
    {
      "epoch": 0.0007736112603416783,
      "eval_loss": 2.661543130874634,
      "eval_runtime": 149.1061,
      "eval_samples_per_second": 32.856,
      "eval_steps_per_second": 16.431,
      "step": 9
    },
    {
      "epoch": 0.0008595680670463093,
      "grad_norm": 24.287752151489258,
      "learning_rate": 0.0002,
      "loss": 11.7875,
      "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": 298765642629120.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}