last-checkpoint/trainer_state.json

{
  "best_metric": 0.9905564785003662,
  "best_model_checkpoint": "./opt_trained/checkpoint-2412",
  "epoch": 12.0,
  "eval_steps": 500,
  "global_step": 2412,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 1.0177865028381348,
      "eval_runtime": 77.0752,
      "eval_samples_per_second": 37.055,
      "eval_steps_per_second": 9.264,
      "step": 201
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.0106526613235474,
      "eval_runtime": 77.338,
      "eval_samples_per_second": 36.929,
      "eval_steps_per_second": 9.232,
      "step": 402
    },
    {
      "epoch": 2.488169364881694,
      "grad_norm": 1.6413393020629883,
      "learning_rate": 0.0003501,
      "loss": 1.0175,
      "step": 500
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.0082063674926758,
      "eval_runtime": 77.1371,
      "eval_samples_per_second": 37.025,
      "eval_steps_per_second": 9.256,
      "step": 603
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.0058513879776,
      "eval_runtime": 76.7488,
      "eval_samples_per_second": 37.212,
      "eval_steps_per_second": 9.303,
      "step": 804
    },
    {
      "epoch": 4.976338729763388,
      "grad_norm": 1.9620177745819092,
      "learning_rate": 0.00030010000000000003,
      "loss": 0.9962,
      "step": 1000
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.0030816793441772,
      "eval_runtime": 76.8119,
      "eval_samples_per_second": 37.182,
      "eval_steps_per_second": 9.295,
      "step": 1005
    },
    {
      "epoch": 6.0,
      "eval_loss": 1.0030088424682617,
      "eval_runtime": 76.8319,
      "eval_samples_per_second": 37.172,
      "eval_steps_per_second": 9.293,
      "step": 1206
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.9996200203895569,
      "eval_runtime": 77.0477,
      "eval_samples_per_second": 37.068,
      "eval_steps_per_second": 9.267,
      "step": 1407
    },
    {
      "epoch": 7.463262764632628,
      "grad_norm": 1.7347174882888794,
      "learning_rate": 0.0002501,
      "loss": 0.9871,
      "step": 1500
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.9977834820747375,
      "eval_runtime": 76.773,
      "eval_samples_per_second": 37.201,
      "eval_steps_per_second": 9.3,
      "step": 1608
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.9954783320426941,
      "eval_runtime": 76.956,
      "eval_samples_per_second": 37.112,
      "eval_steps_per_second": 9.278,
      "step": 1809
    },
    {
      "epoch": 9.951432129514322,
      "grad_norm": 1.4501839876174927,
      "learning_rate": 0.0002001,
      "loss": 0.9774,
      "step": 2000
    },
    {
      "epoch": 10.0,
      "eval_loss": 0.995110273361206,
      "eval_runtime": 77.0387,
      "eval_samples_per_second": 37.072,
      "eval_steps_per_second": 9.268,
      "step": 2010
    },
    {
      "epoch": 11.0,
      "eval_loss": 0.9924370050430298,
      "eval_runtime": 77.2049,
      "eval_samples_per_second": 36.992,
      "eval_steps_per_second": 9.248,
      "step": 2211
    },
    {
      "epoch": 12.0,
      "eval_loss": 0.9905564785003662,
      "eval_runtime": 77.3311,
      "eval_samples_per_second": 36.932,
      "eval_steps_per_second": 9.233,
      "step": 2412
    }
  ],
  "logging_steps": 500,
  "max_steps": 4000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.119621315584e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}