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": 0.6668939590454102,
      "learning_rate": 2e-05,
      "loss": 1.7296,
      "step": 1
    },
    {
      "epoch": 0.0004253056884635832,
      "eval_loss": 1.7417739629745483,
      "eval_runtime": 17.8476,
      "eval_samples_per_second": 55.47,
      "eval_steps_per_second": 27.735,
      "step": 1
    },
    {
      "epoch": 0.0008506113769271664,
      "grad_norm": 0.6744195222854614,
      "learning_rate": 4e-05,
      "loss": 1.8076,
      "step": 2
    },
    {
      "epoch": 0.0012759170653907496,
      "grad_norm": 0.6603765487670898,
      "learning_rate": 6e-05,
      "loss": 1.7598,
      "step": 3
    },
    {
      "epoch": 0.0012759170653907496,
      "eval_loss": 1.7383559942245483,
      "eval_runtime": 17.3157,
      "eval_samples_per_second": 57.174,
      "eval_steps_per_second": 28.587,
      "step": 3
    },
    {
      "epoch": 0.0017012227538543328,
      "grad_norm": 0.7473107576370239,
      "learning_rate": 8e-05,
      "loss": 1.7205,
      "step": 4
    },
    {
      "epoch": 0.002126528442317916,
      "grad_norm": 0.8140320181846619,
      "learning_rate": 0.0001,
      "loss": 1.7428,
      "step": 5
    },
    {
      "epoch": 0.002551834130781499,
      "grad_norm": 0.6843786835670471,
      "learning_rate": 0.00012,
      "loss": 1.7149,
      "step": 6
    },
    {
      "epoch": 0.002551834130781499,
      "eval_loss": 1.6993428468704224,
      "eval_runtime": 17.4921,
      "eval_samples_per_second": 56.597,
      "eval_steps_per_second": 28.298,
      "step": 6
    },
    {
      "epoch": 0.0029771398192450825,
      "grad_norm": 0.8122773766517639,
      "learning_rate": 0.00014,
      "loss": 1.8709,
      "step": 7
    },
    {
      "epoch": 0.0034024455077086655,
      "grad_norm": 0.7426367998123169,
      "learning_rate": 0.00016,
      "loss": 1.5237,
      "step": 8
    },
    {
      "epoch": 0.003827751196172249,
      "grad_norm": 0.7333535552024841,
      "learning_rate": 0.00018,
      "loss": 1.6058,
      "step": 9
    },
    {
      "epoch": 0.003827751196172249,
      "eval_loss": 1.5814273357391357,
      "eval_runtime": 17.4785,
      "eval_samples_per_second": 56.641,
      "eval_steps_per_second": 28.321,
      "step": 9
    },
    {
      "epoch": 0.004253056884635832,
      "grad_norm": 0.8329681158065796,
      "learning_rate": 0.0002,
      "loss": 1.6524,
      "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": 255791978250240.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}