last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.000331092937787637,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.31092937787637e-05,
      "grad_norm": 2.912069797515869,
      "learning_rate": 2e-05,
      "loss": 4.0173,
      "step": 1
    },
    {
      "epoch": 6.62185875575274e-05,
      "grad_norm": 3.5176327228546143,
      "learning_rate": 4e-05,
      "loss": 4.3659,
      "step": 2
    },
    {
      "epoch": 9.932788133629109e-05,
      "grad_norm": 3.4205689430236816,
      "learning_rate": 6e-05,
      "loss": 3.4445,
      "step": 3
    },
    {
      "epoch": 9.932788133629109e-05,
      "eval_loss": 3.9312729835510254,
      "eval_runtime": 1136.7176,
      "eval_samples_per_second": 11.187,
      "eval_steps_per_second": 5.594,
      "step": 3
    },
    {
      "epoch": 0.0001324371751150548,
      "grad_norm": 2.530346632003784,
      "learning_rate": 8e-05,
      "loss": 3.0466,
      "step": 4
    },
    {
      "epoch": 0.0001655464688938185,
      "grad_norm": 2.9463789463043213,
      "learning_rate": 0.0001,
      "loss": 3.5876,
      "step": 5
    },
    {
      "epoch": 0.00019865576267258218,
      "grad_norm": 3.43275785446167,
      "learning_rate": 0.00012,
      "loss": 4.2911,
      "step": 6
    },
    {
      "epoch": 0.00019865576267258218,
      "eval_loss": 3.6891279220581055,
      "eval_runtime": 1134.9587,
      "eval_samples_per_second": 11.205,
      "eval_steps_per_second": 5.603,
      "step": 6
    },
    {
      "epoch": 0.0002317650564513459,
      "grad_norm": 2.908766508102417,
      "learning_rate": 0.00014,
      "loss": 3.2145,
      "step": 7
    },
    {
      "epoch": 0.0002648743502301096,
      "grad_norm": 3.2386703491210938,
      "learning_rate": 0.00016,
      "loss": 3.6703,
      "step": 8
    },
    {
      "epoch": 0.0002979836440088733,
      "grad_norm": 2.7631428241729736,
      "learning_rate": 0.00018,
      "loss": 3.3033,
      "step": 9
    },
    {
      "epoch": 0.0002979836440088733,
      "eval_loss": 3.2122251987457275,
      "eval_runtime": 1135.9245,
      "eval_samples_per_second": 11.195,
      "eval_steps_per_second": 5.598,
      "step": 9
    },
    {
      "epoch": 0.000331092937787637,
      "grad_norm": 2.736384868621826,
      "learning_rate": 0.0002,
      "loss": 2.9474,
      "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": 501714738216960.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}