last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0002800610533096215,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.800610533096215e-05,
      "grad_norm": 1.021116018295288,
      "learning_rate": 2e-05,
      "loss": 2.54,
      "step": 1
    },
    {
      "epoch": 2.800610533096215e-05,
      "eval_loss": 2.40675687789917,
      "eval_runtime": 397.6977,
      "eval_samples_per_second": 37.805,
      "eval_steps_per_second": 18.904,
      "step": 1
    },
    {
      "epoch": 5.60122106619243e-05,
      "grad_norm": 0.6487351059913635,
      "learning_rate": 4e-05,
      "loss": 2.129,
      "step": 2
    },
    {
      "epoch": 8.401831599288645e-05,
      "grad_norm": 0.778297483921051,
      "learning_rate": 6e-05,
      "loss": 2.2438,
      "step": 3
    },
    {
      "epoch": 8.401831599288645e-05,
      "eval_loss": 2.4010744094848633,
      "eval_runtime": 395.9316,
      "eval_samples_per_second": 37.974,
      "eval_steps_per_second": 18.988,
      "step": 3
    },
    {
      "epoch": 0.0001120244213238486,
      "grad_norm": 0.6593923568725586,
      "learning_rate": 8e-05,
      "loss": 1.7131,
      "step": 4
    },
    {
      "epoch": 0.00014003052665481074,
      "grad_norm": 0.8522772192955017,
      "learning_rate": 0.0001,
      "loss": 1.944,
      "step": 5
    },
    {
      "epoch": 0.0001680366319857729,
      "grad_norm": 1.0690536499023438,
      "learning_rate": 0.00012,
      "loss": 2.1539,
      "step": 6
    },
    {
      "epoch": 0.0001680366319857729,
      "eval_loss": 2.3031768798828125,
      "eval_runtime": 396.1156,
      "eval_samples_per_second": 37.956,
      "eval_steps_per_second": 18.979,
      "step": 6
    },
    {
      "epoch": 0.00019604273731673504,
      "grad_norm": 1.080163836479187,
      "learning_rate": 0.00014,
      "loss": 2.5934,
      "step": 7
    },
    {
      "epoch": 0.0002240488426476972,
      "grad_norm": 1.0863776206970215,
      "learning_rate": 0.00016,
      "loss": 2.1382,
      "step": 8
    },
    {
      "epoch": 0.00025205494797865937,
      "grad_norm": 1.2536139488220215,
      "learning_rate": 0.00018,
      "loss": 2.4422,
      "step": 9
    },
    {
      "epoch": 0.00025205494797865937,
      "eval_loss": 1.988196849822998,
      "eval_runtime": 395.9618,
      "eval_samples_per_second": 37.971,
      "eval_steps_per_second": 18.987,
      "step": 9
    },
    {
      "epoch": 0.0002800610533096215,
      "grad_norm": 1.1703901290893555,
      "learning_rate": 0.0002,
      "loss": 1.8253,
      "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": 820048664985600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}