last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0016225205857299315,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016225205857299315,
      "grad_norm": 0.2818737030029297,
      "learning_rate": 2e-05,
      "loss": 41.5055,
      "step": 1
    },
    {
      "epoch": 0.00016225205857299315,
      "eval_loss": 10.375090599060059,
      "eval_runtime": 28.7427,
      "eval_samples_per_second": 90.319,
      "eval_steps_per_second": 45.159,
      "step": 1
    },
    {
      "epoch": 0.0003245041171459863,
      "grad_norm": 0.2798120081424713,
      "learning_rate": 4e-05,
      "loss": 41.4988,
      "step": 2
    },
    {
      "epoch": 0.00048675617571897943,
      "grad_norm": 0.2761710286140442,
      "learning_rate": 6e-05,
      "loss": 41.4743,
      "step": 3
    },
    {
      "epoch": 0.00048675617571897943,
      "eval_loss": 10.375024795532227,
      "eval_runtime": 26.1662,
      "eval_samples_per_second": 99.212,
      "eval_steps_per_second": 49.606,
      "step": 3
    },
    {
      "epoch": 0.0006490082342919726,
      "grad_norm": 0.48735612630844116,
      "learning_rate": 8e-05,
      "loss": 41.4852,
      "step": 4
    },
    {
      "epoch": 0.0008112602928649657,
      "grad_norm": 0.30077189207077026,
      "learning_rate": 0.0001,
      "loss": 41.4969,
      "step": 5
    },
    {
      "epoch": 0.0009735123514379589,
      "grad_norm": 0.3059787452220917,
      "learning_rate": 0.00012,
      "loss": 41.504,
      "step": 6
    },
    {
      "epoch": 0.0009735123514379589,
      "eval_loss": 10.374716758728027,
      "eval_runtime": 26.2434,
      "eval_samples_per_second": 98.92,
      "eval_steps_per_second": 49.46,
      "step": 6
    },
    {
      "epoch": 0.001135764410010952,
      "grad_norm": 0.2234823852777481,
      "learning_rate": 0.00014,
      "loss": 41.4802,
      "step": 7
    },
    {
      "epoch": 0.0012980164685839452,
      "grad_norm": 0.5015853047370911,
      "learning_rate": 0.00016,
      "loss": 41.5159,
      "step": 8
    },
    {
      "epoch": 0.0014602685271569384,
      "grad_norm": 0.313923180103302,
      "learning_rate": 0.00018,
      "loss": 41.4942,
      "step": 9
    },
    {
      "epoch": 0.0014602685271569384,
      "eval_loss": 10.374176979064941,
      "eval_runtime": 26.4109,
      "eval_samples_per_second": 98.293,
      "eval_steps_per_second": 49.146,
      "step": 9
    },
    {
      "epoch": 0.0016225205857299315,
      "grad_norm": 0.3687320053577423,
      "learning_rate": 0.0002,
      "loss": 41.4688,
      "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": 2066743296000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}