fancyerii

Making all in config
make[1]: Entering directory '/home/lili/openmpi-5.0.0/config'
make[1]: Nothing to be done for 'all'.
make[1]: Leaving directory '/home/lili/openmpi-5.0.0/config'
Making all in contrib
make[1]: Entering directory '/home/lili/openmpi-5.0.0/contrib'
make[1]: Nothing to be done for 'all'.
make[1]: Leaving directory '/home/lili/openmpi-5.0.0/contrib'
Making all in 3rd-party
make[1]: Entering directory '/home/lili/openmpi-5.0.0/3rd-party'

fancyerii

$ pmix_info
                 Package: PMIx lili@u-gpu-a100-01.ai.test.ten Distribution
                    PMIX: 4.2.7a1
      PMIX repo revision: v4.2.7
       PMIX release date: Unreleased developer copy
           PMIX Standard: 4.2
       PMIX Standard ABI: Stable (0.0), Provisional (0.0)
                  Prefix: /usr/local
 Configured architecture: pmix.arch
          Configure host: u-gpu-a100-01.ai.test.ten

fancyerii

============================================================================
== Configuring Open MPI
============================================================================

*** Prerequisites
checking for a sed that does not truncate output... /usr/bin/sed
checking for perl... perl

*** Startup tests

fancyerii

diff --git a/src/llama_recipes/configs/datasets.py b/src/llama_recipes/configs/datasets.py
index 62230e4..3e4c76f 100644
--- a/src/llama_recipes/configs/datasets.py
+++ b/src/llama_recipes/configs/datasets.py
@@ -15,8 +15,8 @@ class samsum_dataset:
 @dataclass
 class grammar_dataset:
     dataset: str = "grammar_dataset"
-    train_split: str = "src/llama_recipes/datasets/grammar_dataset/gtrain_10k.csv" 
-    test_split: str = "src/llama_recipes/datasets/grammar_dataset/grammar_validation.csv"

fancyerii

import tensorflow as tf
from tensor2tensor import models
from tensor2tensor import problems
from tensor2tensor.utils import trainer_lib
from tensor2tensor.utils import t2t_model
from tensor2tensor.utils import registry
from tensor2tensor.utils.trainer_lib import create_hparams
import os
import numpy as np

fancyerii

import os
import sys
import numpy as np
import collections
import matplotlib.pyplot as plt# Colab-only TensorFlow version selector
import tensorflow as tf
from tensor2tensor import models
from tensor2tensor import problems
from tensor2tensor.layers import common_layers
from tensor2tensor.utils import trainer_lib

fancyerii

diff --git a/infer.py b/infer.py
index 3f31004..ec15d47 100644
--- a/infer.py
+++ b/infer.py
@@ -63,7 +63,8 @@ def infer(args):
         dev_count = 1
         gpu_id = 0
         phase = "test"
-    place = fluid.CUDAPlace(gpu_id)
+    #place = fluid.CUDAPlace(gpu_id)

fancyerii

2020-07-17 08:57:45,864 [INFO ] main org.pytorch.serve.ModelServer - 
Torchserve version: 0.1.1
TS Home: /home/lili/env-huggface/lib/python3.6/site-packages
Current directory: /home/lili/codes/huggface-transformer/test2
Temp directory: /tmp
Number of GPUs: 1
Number of CPUs: 8
Max heap size: 7938 M
Python executable: /home/lili/env-huggface/bin/python3.6
Config file: N/A

fancyerii

from abc import ABC
import json
import logging
import os

import torch
from transformers import BertModel, BertTokenizer
from torch import nn

from ts.torch_handler.base_handler import BaseHandler

fancyerii

import transformers

from transformers import BertModel, BertTokenizer, AdamW, get_linear_schedule_with_warmup
import numpy as np
import torch
import random

from torch.utils.data import Dataset, DataLoader
from torch import nn, optim
from collections import defaultdict