last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0029942360955161314,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002994236095516131,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 10.9802,
      "step": 1
    },
    {
      "epoch": 0.0002994236095516131,
      "eval_loss": 11.5775728225708,
      "eval_runtime": 95.8227,
      "eval_samples_per_second": 7.347,
      "eval_steps_per_second": 7.347,
      "step": 1
    },
    {
      "epoch": 0.0005988472191032262,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 10.7165,
      "step": 2
    },
    {
      "epoch": 0.0008982708286548395,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 10.434,
      "step": 3
    },
    {
      "epoch": 0.0008982708286548395,
      "eval_loss": 11.5775728225708,
      "eval_runtime": 95.0865,
      "eval_samples_per_second": 7.404,
      "eval_steps_per_second": 7.404,
      "step": 3
    },
    {
      "epoch": 0.0011976944382064525,
      "grad_norm": 10.02202320098877,
      "learning_rate": 2e-05,
      "loss": 9.5838,
      "step": 4
    },
    {
      "epoch": 0.0014971180477580657,
      "grad_norm": 11.54944896697998,
      "learning_rate": 4e-05,
      "loss": 11.0567,
      "step": 5
    },
    {
      "epoch": 0.001796541657309679,
      "grad_norm": 12.557976722717285,
      "learning_rate": 6e-05,
      "loss": 12.2132,
      "step": 6
    },
    {
      "epoch": 0.001796541657309679,
      "eval_loss": 11.523130416870117,
      "eval_runtime": 94.7466,
      "eval_samples_per_second": 7.43,
      "eval_steps_per_second": 7.43,
      "step": 6
    },
    {
      "epoch": 0.002095965266861292,
      "grad_norm": 10.816157341003418,
      "learning_rate": 8e-05,
      "loss": 11.453,
      "step": 7
    },
    {
      "epoch": 0.002395388876412905,
      "grad_norm": 11.840999603271484,
      "learning_rate": 0.0001,
      "loss": 11.202,
      "step": 8
    },
    {
      "epoch": 0.002694812485964518,
      "grad_norm": 8.202712059020996,
      "learning_rate": 0.00012,
      "loss": 9.0586,
      "step": 9
    },
    {
      "epoch": 0.002694812485964518,
      "eval_loss": 11.066697120666504,
      "eval_runtime": 95.5362,
      "eval_samples_per_second": 7.369,
      "eval_steps_per_second": 7.369,
      "step": 9
    },
    {
      "epoch": 0.0029942360955161314,
      "grad_norm": 7.411980152130127,
      "learning_rate": 0.00014,
      "loss": 10.0089,
      "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": 1849564248145920.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}