last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0048543689320388345,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016181229773462783,
      "eval_loss": 2.3503623008728027,
      "eval_runtime": 572.8881,
      "eval_samples_per_second": 4.544,
      "eval_steps_per_second": 2.273,
      "step": 1
    },
    {
      "epoch": 0.0004854368932038835,
      "grad_norm": 32.64070510864258,
      "learning_rate": 4e-05,
      "loss": 2.0943,
      "step": 3
    },
    {
      "epoch": 0.0008090614886731392,
      "eval_loss": 1.4009541273117065,
      "eval_runtime": 573.8898,
      "eval_samples_per_second": 4.536,
      "eval_steps_per_second": 2.269,
      "step": 5
    },
    {
      "epoch": 0.000970873786407767,
      "grad_norm": 12.463337898254395,
      "learning_rate": 8e-05,
      "loss": 1.4308,
      "step": 6
    },
    {
      "epoch": 0.0014563106796116505,
      "grad_norm": 2.2853708267211914,
      "learning_rate": 0.00012,
      "loss": 1.3387,
      "step": 9
    },
    {
      "epoch": 0.0016181229773462784,
      "eval_loss": 1.042096495628357,
      "eval_runtime": 574.005,
      "eval_samples_per_second": 4.535,
      "eval_steps_per_second": 2.268,
      "step": 10
    },
    {
      "epoch": 0.001941747572815534,
      "grad_norm": 1.3578804731369019,
      "learning_rate": 0.00016,
      "loss": 0.7841,
      "step": 12
    },
    {
      "epoch": 0.0024271844660194173,
      "grad_norm": 1.626987099647522,
      "learning_rate": 0.0002,
      "loss": 0.8889,
      "step": 15
    },
    {
      "epoch": 0.0024271844660194173,
      "eval_loss": 0.9009343385696411,
      "eval_runtime": 575.3378,
      "eval_samples_per_second": 4.524,
      "eval_steps_per_second": 2.263,
      "step": 15
    },
    {
      "epoch": 0.002912621359223301,
      "grad_norm": 2.2033326625823975,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.8597,
      "step": 18
    },
    {
      "epoch": 0.003236245954692557,
      "eval_loss": 0.8138495683670044,
      "eval_runtime": 573.2693,
      "eval_samples_per_second": 4.541,
      "eval_steps_per_second": 2.271,
      "step": 20
    },
    {
      "epoch": 0.0033980582524271844,
      "grad_norm": 1.6454766988754272,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.8539,
      "step": 21
    },
    {
      "epoch": 0.003883495145631068,
      "grad_norm": 1.1470767259597778,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.6777,
      "step": 24
    },
    {
      "epoch": 0.0040453074433656954,
      "eval_loss": 0.7886656522750854,
      "eval_runtime": 575.3052,
      "eval_samples_per_second": 4.525,
      "eval_steps_per_second": 2.263,
      "step": 25
    },
    {
      "epoch": 0.004368932038834952,
      "grad_norm": 1.2917059659957886,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.7204,
      "step": 27
    },
    {
      "epoch": 0.0048543689320388345,
      "grad_norm": 0.9337906837463379,
      "learning_rate": 0.0,
      "loss": 0.6264,
      "step": 30
    },
    {
      "epoch": 0.0048543689320388345,
      "eval_loss": 0.7828293442726135,
      "eval_runtime": 574.2879,
      "eval_samples_per_second": 4.533,
      "eval_steps_per_second": 2.267,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1791000808718336e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}