last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0008449315840120169,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.388128711244632e-05,
      "grad_norm": 4.312055587768555,
      "learning_rate": 2e-05,
      "loss": 2.2041,
      "step": 1
    },
    {
      "epoch": 9.388128711244632e-05,
      "eval_loss": 1.9480620622634888,
      "eval_runtime": 156.9033,
      "eval_samples_per_second": 28.584,
      "eval_steps_per_second": 14.295,
      "step": 1
    },
    {
      "epoch": 0.00018776257422489263,
      "grad_norm": 3.6886849403381348,
      "learning_rate": 4e-05,
      "loss": 2.1589,
      "step": 2
    },
    {
      "epoch": 0.00028164386133733895,
      "grad_norm": 3.211580276489258,
      "learning_rate": 6e-05,
      "loss": 1.7927,
      "step": 3
    },
    {
      "epoch": 0.00028164386133733895,
      "eval_loss": 1.8695504665374756,
      "eval_runtime": 157.0964,
      "eval_samples_per_second": 28.549,
      "eval_steps_per_second": 14.278,
      "step": 3
    },
    {
      "epoch": 0.00037552514844978527,
      "grad_norm": 3.755586624145508,
      "learning_rate": 8e-05,
      "loss": 1.9429,
      "step": 4
    },
    {
      "epoch": 0.0004694064355622316,
      "grad_norm": 3.243609666824341,
      "learning_rate": 0.0001,
      "loss": 1.4794,
      "step": 5
    },
    {
      "epoch": 0.0005632877226746779,
      "grad_norm": 3.549593925476074,
      "learning_rate": 0.00012,
      "loss": 1.4719,
      "step": 6
    },
    {
      "epoch": 0.0005632877226746779,
      "eval_loss": 1.130536675453186,
      "eval_runtime": 157.1456,
      "eval_samples_per_second": 28.54,
      "eval_steps_per_second": 14.273,
      "step": 6
    },
    {
      "epoch": 0.0006571690097871242,
      "grad_norm": 3.0410995483398438,
      "learning_rate": 0.00014,
      "loss": 1.146,
      "step": 7
    },
    {
      "epoch": 0.0007510502968995705,
      "grad_norm": 2.8524529933929443,
      "learning_rate": 0.00016,
      "loss": 1.1605,
      "step": 8
    },
    {
      "epoch": 0.0008449315840120169,
      "grad_norm": 2.822139263153076,
      "learning_rate": 0.00018,
      "loss": 0.7606,
      "step": 9
    },
    {
      "epoch": 0.0008449315840120169,
      "eval_loss": 0.6162478923797607,
      "eval_runtime": 157.166,
      "eval_samples_per_second": 28.537,
      "eval_steps_per_second": 14.272,
      "step": 9
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1719982274641920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}