last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004253056884635832,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004253056884635832,
      "grad_norm": 0.0074624610133469105,
      "learning_rate": 2e-05,
      "loss": 11.9306,
      "step": 1
    },
    {
      "epoch": 0.0004253056884635832,
      "eval_loss": 11.931585311889648,
      "eval_runtime": 5.278,
      "eval_samples_per_second": 187.572,
      "eval_steps_per_second": 93.786,
      "step": 1
    },
    {
      "epoch": 0.0008506113769271664,
      "grad_norm": 0.007450843695551157,
      "learning_rate": 4e-05,
      "loss": 11.932,
      "step": 2
    },
    {
      "epoch": 0.0012759170653907496,
      "grad_norm": 0.00934767909348011,
      "learning_rate": 6e-05,
      "loss": 11.9344,
      "step": 3
    },
    {
      "epoch": 0.0012759170653907496,
      "eval_loss": 11.931581497192383,
      "eval_runtime": 5.3013,
      "eval_samples_per_second": 186.747,
      "eval_steps_per_second": 93.373,
      "step": 3
    },
    {
      "epoch": 0.0017012227538543328,
      "grad_norm": 0.008699387311935425,
      "learning_rate": 8e-05,
      "loss": 11.9326,
      "step": 4
    },
    {
      "epoch": 0.002126528442317916,
      "grad_norm": 0.007176072336733341,
      "learning_rate": 0.0001,
      "loss": 11.9316,
      "step": 5
    },
    {
      "epoch": 0.002551834130781499,
      "grad_norm": 0.0072631253860890865,
      "learning_rate": 0.00012,
      "loss": 11.9303,
      "step": 6
    },
    {
      "epoch": 0.002551834130781499,
      "eval_loss": 11.931564331054688,
      "eval_runtime": 5.4397,
      "eval_samples_per_second": 181.996,
      "eval_steps_per_second": 90.998,
      "step": 6
    },
    {
      "epoch": 0.0029771398192450825,
      "grad_norm": 0.00874969083815813,
      "learning_rate": 0.00014,
      "loss": 11.932,
      "step": 7
    },
    {
      "epoch": 0.0034024455077086655,
      "grad_norm": 0.010286129079759121,
      "learning_rate": 0.00016,
      "loss": 11.9323,
      "step": 8
    },
    {
      "epoch": 0.003827751196172249,
      "grad_norm": 0.007626386824995279,
      "learning_rate": 0.00018,
      "loss": 11.9337,
      "step": 9
    },
    {
      "epoch": 0.003827751196172249,
      "eval_loss": 11.93153190612793,
      "eval_runtime": 5.3943,
      "eval_samples_per_second": 183.526,
      "eval_steps_per_second": 91.763,
      "step": 9
    },
    {
      "epoch": 0.004253056884635832,
      "grad_norm": 0.01324973814189434,
      "learning_rate": 0.0002,
      "loss": 11.9308,
      "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": 2126905344.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}