last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.017543859649122806,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0017543859649122807,
      "grad_norm": 1.8004238881985657e-05,
      "learning_rate": 2e-05,
      "loss": 46.0,
      "step": 1
    },
    {
      "epoch": 0.0017543859649122807,
      "eval_loss": 11.5,
      "eval_runtime": 1.2553,
      "eval_samples_per_second": 191.183,
      "eval_steps_per_second": 95.591,
      "step": 1
    },
    {
      "epoch": 0.0035087719298245615,
      "grad_norm": 3.342830314068124e-05,
      "learning_rate": 4e-05,
      "loss": 46.0,
      "step": 2
    },
    {
      "epoch": 0.005263157894736842,
      "grad_norm": 5.369931386667304e-05,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.005263157894736842,
      "eval_loss": 11.5,
      "eval_runtime": 1.239,
      "eval_samples_per_second": 193.709,
      "eval_steps_per_second": 96.855,
      "step": 3
    },
    {
      "epoch": 0.007017543859649123,
      "grad_norm": 3.151122291455977e-05,
      "learning_rate": 8e-05,
      "loss": 46.0,
      "step": 4
    },
    {
      "epoch": 0.008771929824561403,
      "grad_norm": 1.760389750415925e-05,
      "learning_rate": 0.0001,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.010526315789473684,
      "grad_norm": 2.0383486116770655e-05,
      "learning_rate": 0.00012,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.010526315789473684,
      "eval_loss": 11.5,
      "eval_runtime": 1.3331,
      "eval_samples_per_second": 180.034,
      "eval_steps_per_second": 90.017,
      "step": 6
    },
    {
      "epoch": 0.012280701754385965,
      "grad_norm": 4.4034619349986315e-05,
      "learning_rate": 0.00014,
      "loss": 46.0,
      "step": 7
    },
    {
      "epoch": 0.014035087719298246,
      "grad_norm": 6.590150587726384e-05,
      "learning_rate": 0.00016,
      "loss": 46.0,
      "step": 8
    },
    {
      "epoch": 0.015789473684210527,
      "grad_norm": 5.233305273577571e-05,
      "learning_rate": 0.00018,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.015789473684210527,
      "eval_loss": 11.5,
      "eval_runtime": 1.245,
      "eval_samples_per_second": 192.772,
      "eval_steps_per_second": 96.386,
      "step": 9
    },
    {
      "epoch": 0.017543859649122806,
      "grad_norm": 5.965233503957279e-05,
      "learning_rate": 0.0002,
      "loss": 46.0,
      "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": 199228784640.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}