last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00014832558950151478,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.4832558950151478e-05,
      "grad_norm": 992.8629150390625,
      "learning_rate": 2e-05,
      "loss": 95.6979,
      "step": 1
    },
    {
      "epoch": 1.4832558950151478e-05,
      "eval_loss": 23.534069061279297,
      "eval_runtime": 1783.7836,
      "eval_samples_per_second": 15.914,
      "eval_steps_per_second": 7.957,
      "step": 1
    },
    {
      "epoch": 2.9665117900302956e-05,
      "grad_norm": 1293.0372314453125,
      "learning_rate": 4e-05,
      "loss": 96.301,
      "step": 2
    },
    {
      "epoch": 4.449767685045443e-05,
      "grad_norm": 1802.606689453125,
      "learning_rate": 6e-05,
      "loss": 94.739,
      "step": 3
    },
    {
      "epoch": 4.449767685045443e-05,
      "eval_loss": 23.527429580688477,
      "eval_runtime": 1782.403,
      "eval_samples_per_second": 15.926,
      "eval_steps_per_second": 7.963,
      "step": 3
    },
    {
      "epoch": 5.933023580060591e-05,
      "grad_norm": 1914.365478515625,
      "learning_rate": 8e-05,
      "loss": 93.6926,
      "step": 4
    },
    {
      "epoch": 7.416279475075739e-05,
      "grad_norm": 942.52734375,
      "learning_rate": 0.0001,
      "loss": 94.806,
      "step": 5
    },
    {
      "epoch": 8.899535370090886e-05,
      "grad_norm": 1608.42919921875,
      "learning_rate": 0.00012,
      "loss": 94.352,
      "step": 6
    },
    {
      "epoch": 8.899535370090886e-05,
      "eval_loss": 23.49734115600586,
      "eval_runtime": 1542.192,
      "eval_samples_per_second": 18.407,
      "eval_steps_per_second": 9.204,
      "step": 6
    },
    {
      "epoch": 0.00010382791265106034,
      "grad_norm": 1553.6900634765625,
      "learning_rate": 0.00014,
      "loss": 92.2466,
      "step": 7
    },
    {
      "epoch": 0.00011866047160121182,
      "grad_norm": 963.3795166015625,
      "learning_rate": 0.00016,
      "loss": 92.4837,
      "step": 8
    },
    {
      "epoch": 0.0001334930305513633,
      "grad_norm": 1251.0181884765625,
      "learning_rate": 0.00018,
      "loss": 94.2449,
      "step": 9
    },
    {
      "epoch": 0.0001334930305513633,
      "eval_loss": 23.44436264038086,
      "eval_runtime": 1621.1736,
      "eval_samples_per_second": 17.51,
      "eval_steps_per_second": 8.755,
      "step": 9
    },
    {
      "epoch": 0.00014832558950151478,
      "grad_norm": 1554.7286376953125,
      "learning_rate": 0.0002,
      "loss": 94.9453,
      "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": 89372900720640.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}