last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.027434842249657063,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0027434842249657062,
      "grad_norm": 0.8217653632164001,
      "learning_rate": 2e-05,
      "loss": 1.7588,
      "step": 1
    },
    {
      "epoch": 0.0027434842249657062,
      "eval_loss": 1.2827941179275513,
      "eval_runtime": 15.0875,
      "eval_samples_per_second": 10.207,
      "eval_steps_per_second": 5.104,
      "step": 1
    },
    {
      "epoch": 0.0054869684499314125,
      "grad_norm": 0.677155613899231,
      "learning_rate": 4e-05,
      "loss": 0.8861,
      "step": 2
    },
    {
      "epoch": 0.00823045267489712,
      "grad_norm": 0.7100198864936829,
      "learning_rate": 6e-05,
      "loss": 0.8979,
      "step": 3
    },
    {
      "epoch": 0.00823045267489712,
      "eval_loss": 1.2811253070831299,
      "eval_runtime": 14.4824,
      "eval_samples_per_second": 10.634,
      "eval_steps_per_second": 5.317,
      "step": 3
    },
    {
      "epoch": 0.010973936899862825,
      "grad_norm": 0.6011113524436951,
      "learning_rate": 8e-05,
      "loss": 1.2019,
      "step": 4
    },
    {
      "epoch": 0.013717421124828532,
      "grad_norm": 0.9559582471847534,
      "learning_rate": 0.0001,
      "loss": 1.7005,
      "step": 5
    },
    {
      "epoch": 0.01646090534979424,
      "grad_norm": 0.5423510670661926,
      "learning_rate": 0.00012,
      "loss": 1.0275,
      "step": 6
    },
    {
      "epoch": 0.01646090534979424,
      "eval_loss": 1.261582851409912,
      "eval_runtime": 14.4742,
      "eval_samples_per_second": 10.64,
      "eval_steps_per_second": 5.32,
      "step": 6
    },
    {
      "epoch": 0.019204389574759947,
      "grad_norm": 0.4940236806869507,
      "learning_rate": 0.00014,
      "loss": 0.6075,
      "step": 7
    },
    {
      "epoch": 0.02194787379972565,
      "grad_norm": 1.0571178197860718,
      "learning_rate": 0.00016,
      "loss": 1.7574,
      "step": 8
    },
    {
      "epoch": 0.024691358024691357,
      "grad_norm": 1.5808483362197876,
      "learning_rate": 0.00018,
      "loss": 2.0463,
      "step": 9
    },
    {
      "epoch": 0.024691358024691357,
      "eval_loss": 1.1668046712875366,
      "eval_runtime": 14.4888,
      "eval_samples_per_second": 10.629,
      "eval_steps_per_second": 5.314,
      "step": 9
    },
    {
      "epoch": 0.027434842249657063,
      "grad_norm": 0.5054391026496887,
      "learning_rate": 0.0002,
      "loss": 0.458,
      "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": 6332410861977600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}