last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.008592910848549946,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008592910848549946,
      "grad_norm": 0.29745617508888245,
      "learning_rate": 2e-05,
      "loss": 1.4837,
      "step": 1
    },
    {
      "epoch": 0.0008592910848549946,
      "eval_loss": 1.376673936843872,
      "eval_runtime": 25.4548,
      "eval_samples_per_second": 19.25,
      "eval_steps_per_second": 9.625,
      "step": 1
    },
    {
      "epoch": 0.0017185821697099893,
      "grad_norm": 0.2560921609401703,
      "learning_rate": 4e-05,
      "loss": 1.2381,
      "step": 2
    },
    {
      "epoch": 0.0025778732545649837,
      "grad_norm": 0.27604779601097107,
      "learning_rate": 6e-05,
      "loss": 1.404,
      "step": 3
    },
    {
      "epoch": 0.0025778732545649837,
      "eval_loss": 1.3752812147140503,
      "eval_runtime": 24.4327,
      "eval_samples_per_second": 20.055,
      "eval_steps_per_second": 10.028,
      "step": 3
    },
    {
      "epoch": 0.0034371643394199786,
      "grad_norm": 0.22866801917552948,
      "learning_rate": 8e-05,
      "loss": 1.223,
      "step": 4
    },
    {
      "epoch": 0.004296455424274973,
      "grad_norm": 0.3337690532207489,
      "learning_rate": 0.0001,
      "loss": 1.3166,
      "step": 5
    },
    {
      "epoch": 0.0051557465091299675,
      "grad_norm": 0.3008735775947571,
      "learning_rate": 0.00012,
      "loss": 1.2531,
      "step": 6
    },
    {
      "epoch": 0.0051557465091299675,
      "eval_loss": 1.3641979694366455,
      "eval_runtime": 24.4768,
      "eval_samples_per_second": 20.019,
      "eval_steps_per_second": 10.009,
      "step": 6
    },
    {
      "epoch": 0.006015037593984963,
      "grad_norm": 0.30002692341804504,
      "learning_rate": 0.00014,
      "loss": 1.2206,
      "step": 7
    },
    {
      "epoch": 0.006874328678839957,
      "grad_norm": 0.35041213035583496,
      "learning_rate": 0.00016,
      "loss": 1.3039,
      "step": 8
    },
    {
      "epoch": 0.007733619763694952,
      "grad_norm": 0.36330825090408325,
      "learning_rate": 0.00018,
      "loss": 1.2723,
      "step": 9
    },
    {
      "epoch": 0.007733619763694952,
      "eval_loss": 1.3176864385604858,
      "eval_runtime": 24.458,
      "eval_samples_per_second": 20.034,
      "eval_steps_per_second": 10.017,
      "step": 9
    },
    {
      "epoch": 0.008592910848549946,
      "grad_norm": 0.320016473531723,
      "learning_rate": 0.0002,
      "loss": 1.4896,
      "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": 3013156301438976.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}