last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.002070988897198412,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00023010987746649024,
      "grad_norm": 1.5856705904006958,
      "learning_rate": 2e-05,
      "loss": 11.1082,
      "step": 1
    },
    {
      "epoch": 0.00023010987746649024,
      "eval_loss": 2.6929500102996826,
      "eval_runtime": 51.6497,
      "eval_samples_per_second": 35.431,
      "eval_steps_per_second": 17.715,
      "step": 1
    },
    {
      "epoch": 0.0004602197549329805,
      "grad_norm": 1.3869730234146118,
      "learning_rate": 4e-05,
      "loss": 10.5872,
      "step": 2
    },
    {
      "epoch": 0.0006903296323994707,
      "grad_norm": 1.505873203277588,
      "learning_rate": 6e-05,
      "loss": 10.5473,
      "step": 3
    },
    {
      "epoch": 0.0006903296323994707,
      "eval_loss": 2.6923375129699707,
      "eval_runtime": 51.0551,
      "eval_samples_per_second": 35.844,
      "eval_steps_per_second": 17.922,
      "step": 3
    },
    {
      "epoch": 0.000920439509865961,
      "grad_norm": 1.5138187408447266,
      "learning_rate": 8e-05,
      "loss": 10.3903,
      "step": 4
    },
    {
      "epoch": 0.0011505493873324513,
      "grad_norm": 2.376742124557495,
      "learning_rate": 0.0001,
      "loss": 13.2282,
      "step": 5
    },
    {
      "epoch": 0.0013806592647989415,
      "grad_norm": 2.225229263305664,
      "learning_rate": 0.00012,
      "loss": 10.927,
      "step": 6
    },
    {
      "epoch": 0.0013806592647989415,
      "eval_loss": 2.638922691345215,
      "eval_runtime": 51.3615,
      "eval_samples_per_second": 35.63,
      "eval_steps_per_second": 17.815,
      "step": 6
    },
    {
      "epoch": 0.0016107691422654318,
      "grad_norm": 2.857755422592163,
      "learning_rate": 0.00014,
      "loss": 10.3591,
      "step": 7
    },
    {
      "epoch": 0.001840879019731922,
      "grad_norm": 3.591569662094116,
      "learning_rate": 0.00016,
      "loss": 10.0244,
      "step": 8
    },
    {
      "epoch": 0.002070988897198412,
      "grad_norm": 3.8314642906188965,
      "learning_rate": 0.00018,
      "loss": 9.6656,
      "step": 9
    },
    {
      "epoch": 0.002070988897198412,
      "eval_loss": 2.298410654067993,
      "eval_runtime": 51.3089,
      "eval_samples_per_second": 35.666,
      "eval_steps_per_second": 17.833,
      "step": 9
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1469230227652608.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}