last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1643835616438356,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0182648401826484,
      "grad_norm": 0.4796290099620819,
      "learning_rate": 2e-05,
      "loss": 1.0919,
      "step": 1
    },
    {
      "epoch": 0.0182648401826484,
      "eval_loss": 1.0734666585922241,
      "eval_runtime": 1.8226,
      "eval_samples_per_second": 51.027,
      "eval_steps_per_second": 6.584,
      "step": 1
    },
    {
      "epoch": 0.0365296803652968,
      "grad_norm": 0.4808058738708496,
      "learning_rate": 4e-05,
      "loss": 1.0656,
      "step": 2
    },
    {
      "epoch": 0.0547945205479452,
      "grad_norm": 0.4675324261188507,
      "learning_rate": 6e-05,
      "loss": 1.0403,
      "step": 3
    },
    {
      "epoch": 0.0547945205479452,
      "eval_loss": 1.0429679155349731,
      "eval_runtime": 1.8705,
      "eval_samples_per_second": 49.719,
      "eval_steps_per_second": 6.415,
      "step": 3
    },
    {
      "epoch": 0.0730593607305936,
      "grad_norm": 0.4484165608882904,
      "learning_rate": 8e-05,
      "loss": 1.0483,
      "step": 4
    },
    {
      "epoch": 0.091324200913242,
      "grad_norm": 0.4434252083301544,
      "learning_rate": 0.0001,
      "loss": 1.0122,
      "step": 5
    },
    {
      "epoch": 0.1095890410958904,
      "grad_norm": 0.4385027587413788,
      "learning_rate": 0.00012,
      "loss": 0.9783,
      "step": 6
    },
    {
      "epoch": 0.1095890410958904,
      "eval_loss": 0.9256500601768494,
      "eval_runtime": 1.8637,
      "eval_samples_per_second": 49.9,
      "eval_steps_per_second": 6.439,
      "step": 6
    },
    {
      "epoch": 0.1278538812785388,
      "grad_norm": 0.40307268500328064,
      "learning_rate": 0.00014,
      "loss": 0.9424,
      "step": 7
    },
    {
      "epoch": 0.1461187214611872,
      "grad_norm": 0.39569929242134094,
      "learning_rate": 0.00016,
      "loss": 0.8835,
      "step": 8
    },
    {
      "epoch": 0.1643835616438356,
      "grad_norm": 0.4634018540382385,
      "learning_rate": 0.00018,
      "loss": 0.8178,
      "step": 9
    },
    {
      "epoch": 0.1643835616438356,
      "eval_loss": 0.8397897481918335,
      "eval_runtime": 1.867,
      "eval_samples_per_second": 49.812,
      "eval_steps_per_second": 6.427,
      "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": 2.0122869090484224e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}