last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.008592910848549946,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008592910848549946,
      "grad_norm": 2.3441901206970215,
      "learning_rate": 2e-05,
      "loss": 9.8808,
      "step": 1
    },
    {
      "epoch": 0.0008592910848549946,
      "eval_loss": 2.5703487396240234,
      "eval_runtime": 9.1047,
      "eval_samples_per_second": 53.818,
      "eval_steps_per_second": 26.909,
      "step": 1
    },
    {
      "epoch": 0.0017185821697099893,
      "grad_norm": 2.2714202404022217,
      "learning_rate": 4e-05,
      "loss": 10.0748,
      "step": 2
    },
    {
      "epoch": 0.0025778732545649837,
      "grad_norm": 2.318856716156006,
      "learning_rate": 6e-05,
      "loss": 11.5674,
      "step": 3
    },
    {
      "epoch": 0.0025778732545649837,
      "eval_loss": 2.5691211223602295,
      "eval_runtime": 7.7786,
      "eval_samples_per_second": 62.993,
      "eval_steps_per_second": 31.497,
      "step": 3
    },
    {
      "epoch": 0.0034371643394199786,
      "grad_norm": 2.429922342300415,
      "learning_rate": 8e-05,
      "loss": 11.4193,
      "step": 4
    },
    {
      "epoch": 0.004296455424274973,
      "grad_norm": 2.8628859519958496,
      "learning_rate": 0.0001,
      "loss": 11.5228,
      "step": 5
    },
    {
      "epoch": 0.0051557465091299675,
      "grad_norm": 2.476830005645752,
      "learning_rate": 0.00012,
      "loss": 10.3362,
      "step": 6
    },
    {
      "epoch": 0.0051557465091299675,
      "eval_loss": 2.563114881515503,
      "eval_runtime": 7.7981,
      "eval_samples_per_second": 62.836,
      "eval_steps_per_second": 31.418,
      "step": 6
    },
    {
      "epoch": 0.006015037593984963,
      "grad_norm": 2.392770290374756,
      "learning_rate": 0.00014,
      "loss": 11.1243,
      "step": 7
    },
    {
      "epoch": 0.006874328678839957,
      "grad_norm": 2.50643253326416,
      "learning_rate": 0.00016,
      "loss": 10.2998,
      "step": 8
    },
    {
      "epoch": 0.007733619763694952,
      "grad_norm": 2.93513560295105,
      "learning_rate": 0.00018,
      "loss": 10.8094,
      "step": 9
    },
    {
      "epoch": 0.007733619763694952,
      "eval_loss": 2.5549163818359375,
      "eval_runtime": 7.8907,
      "eval_samples_per_second": 62.098,
      "eval_steps_per_second": 31.049,
      "step": 9
    },
    {
      "epoch": 0.008592910848549946,
      "grad_norm": 2.5666284561157227,
      "learning_rate": 0.0002,
      "loss": 10.3832,
      "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": 552716438863872.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}