last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0012396566151176124,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00012396566151176124,
      "grad_norm": 1.4471592903137207,
      "learning_rate": 2e-05,
      "loss": 2.3448,
      "step": 1
    },
    {
      "epoch": 0.0002479313230235225,
      "grad_norm": 1.0944325923919678,
      "learning_rate": 4e-05,
      "loss": 2.3491,
      "step": 2
    },
    {
      "epoch": 0.00037189698453528373,
      "grad_norm": 1.218919038772583,
      "learning_rate": 6e-05,
      "loss": 2.3275,
      "step": 3
    },
    {
      "epoch": 0.00037189698453528373,
      "eval_loss": 2.830389976501465,
      "eval_runtime": 237.5957,
      "eval_samples_per_second": 14.297,
      "eval_steps_per_second": 7.151,
      "step": 3
    },
    {
      "epoch": 0.000495862646047045,
      "grad_norm": 1.9702732563018799,
      "learning_rate": 8e-05,
      "loss": 3.0104,
      "step": 4
    },
    {
      "epoch": 0.0006198283075588062,
      "grad_norm": 1.2266989946365356,
      "learning_rate": 0.0001,
      "loss": 2.5549,
      "step": 5
    },
    {
      "epoch": 0.0007437939690705675,
      "grad_norm": 1.4129709005355835,
      "learning_rate": 0.00012,
      "loss": 2.4043,
      "step": 6
    },
    {
      "epoch": 0.0007437939690705675,
      "eval_loss": 2.7152512073516846,
      "eval_runtime": 241.0314,
      "eval_samples_per_second": 14.094,
      "eval_steps_per_second": 7.049,
      "step": 6
    },
    {
      "epoch": 0.0008677596305823287,
      "grad_norm": 1.189100980758667,
      "learning_rate": 0.00014,
      "loss": 2.1755,
      "step": 7
    },
    {
      "epoch": 0.00099172529209409,
      "grad_norm": 1.5066560506820679,
      "learning_rate": 0.00016,
      "loss": 2.777,
      "step": 8
    },
    {
      "epoch": 0.001115690953605851,
      "grad_norm": 1.7966433763504028,
      "learning_rate": 0.00018,
      "loss": 2.856,
      "step": 9
    },
    {
      "epoch": 0.001115690953605851,
      "eval_loss": 2.3698041439056396,
      "eval_runtime": 240.7146,
      "eval_samples_per_second": 14.112,
      "eval_steps_per_second": 7.058,
      "step": 9
    },
    {
      "epoch": 0.0012396566151176124,
      "grad_norm": 1.487255334854126,
      "learning_rate": 0.0002,
      "loss": 2.0388,
      "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": 397265366679552.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}