last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02386634844868735,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002386634844868735,
      "grad_norm": 1.0092898607254028,
      "learning_rate": 2e-05,
      "loss": 1.1095,
      "step": 1
    },
    {
      "epoch": 0.002386634844868735,
      "eval_loss": 1.0069401264190674,
      "eval_runtime": 27.2083,
      "eval_samples_per_second": 6.505,
      "eval_steps_per_second": 3.271,
      "step": 1
    },
    {
      "epoch": 0.00477326968973747,
      "grad_norm": 0.777765154838562,
      "learning_rate": 4e-05,
      "loss": 0.8552,
      "step": 2
    },
    {
      "epoch": 0.007159904534606206,
      "grad_norm": 0.7151408195495605,
      "learning_rate": 6e-05,
      "loss": 1.0173,
      "step": 3
    },
    {
      "epoch": 0.007159904534606206,
      "eval_loss": 1.0022640228271484,
      "eval_runtime": 27.1923,
      "eval_samples_per_second": 6.509,
      "eval_steps_per_second": 3.273,
      "step": 3
    },
    {
      "epoch": 0.00954653937947494,
      "grad_norm": 0.569198489189148,
      "learning_rate": 8e-05,
      "loss": 0.8199,
      "step": 4
    },
    {
      "epoch": 0.011933174224343675,
      "grad_norm": 0.684947669506073,
      "learning_rate": 0.0001,
      "loss": 0.7825,
      "step": 5
    },
    {
      "epoch": 0.014319809069212411,
      "grad_norm": 1.0612146854400635,
      "learning_rate": 0.00012,
      "loss": 0.8894,
      "step": 6
    },
    {
      "epoch": 0.014319809069212411,
      "eval_loss": 0.9630873799324036,
      "eval_runtime": 27.2494,
      "eval_samples_per_second": 6.496,
      "eval_steps_per_second": 3.266,
      "step": 6
    },
    {
      "epoch": 0.016706443914081145,
      "grad_norm": 0.7056834101676941,
      "learning_rate": 0.00014,
      "loss": 0.8648,
      "step": 7
    },
    {
      "epoch": 0.01909307875894988,
      "grad_norm": 0.8485152125358582,
      "learning_rate": 0.00016,
      "loss": 1.0942,
      "step": 8
    },
    {
      "epoch": 0.021479713603818614,
      "grad_norm": 0.4888964891433716,
      "learning_rate": 0.00018,
      "loss": 0.7532,
      "step": 9
    },
    {
      "epoch": 0.021479713603818614,
      "eval_loss": 0.9085158109664917,
      "eval_runtime": 27.2896,
      "eval_samples_per_second": 6.486,
      "eval_steps_per_second": 3.261,
      "step": 9
    },
    {
      "epoch": 0.02386634844868735,
      "grad_norm": 0.5342348217964172,
      "learning_rate": 0.0002,
      "loss": 0.7663,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1935445139128320.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}