machine-translation

Build error

File size: 18,628 Bytes

2238e7c

Submitting job: /common/home/users/d/dh.huang.2023/code/rapget-translation/scripts/eval-mac.sh
Current Directory:
/common/home/users/d/dh.huang.2023/code/rapget-translation
Mon Aug 26 16:14:11 2024       
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 550.90.07              Driver Version: 550.90.07      CUDA Version: 12.4     |
|-----------------------------------------+------------------------+----------------------+
| GPU  Name                 Persistence-M | Bus-Id          Disp.A | Volatile Uncorr. ECC |
| Fan  Temp   Perf          Pwr:Usage/Cap |           Memory-Usage | GPU-Util  Compute M. |
|                                         |                        |               MIG M. |
|=========================================+========================+======================|
|   0  NVIDIA L40                     On  |   00000000:01:00.0 Off |                    0 |
| N/A   32C    P8             34W /  300W |       1MiB /  46068MiB |      0%      Default |
|                                         |                        |                  N/A |
+-----------------------------------------+------------------------+----------------------+
                                                                                         
+-----------------------------------------------------------------------------------------+
| Processes:                                                                              |
|  GPU   GI   CI        PID   Type   Process name                              GPU Memory |
|        ID   ID                                                               Usage      |
|=========================================================================================|
|  No running processes found                                                             |
+-----------------------------------------------------------------------------------------+
Linux lexicon 4.18.0-553.5.1.el8_10.x86_64 #1 SMP Thu Jun 6 09:41:19 UTC 2024 x86_64 x86_64 x86_64 GNU/Linux
NAME="Rocky Linux"
VERSION="8.10 (Green Obsidian)"
ID="rocky"
ID_LIKE="rhel centos fedora"
VERSION_ID="8.10"
PLATFORM_ID="platform:el8"
PRETTY_NAME="Rocky Linux 8.10 (Green Obsidian)"
ANSI_COLOR="0;32"
LOGO="fedora-logo-icon"
CPE_NAME="cpe:/o:rocky:rocky:8:GA"
HOME_URL="https://rockylinux.org/"
BUG_REPORT_URL="https://bugs.rockylinux.org/"
SUPPORT_END="2029-05-31"
ROCKY_SUPPORT_PRODUCT="Rocky-Linux-8"
ROCKY_SUPPORT_PRODUCT_VERSION="8.10"
REDHAT_SUPPORT_PRODUCT="Rocky Linux"
REDHAT_SUPPORT_PRODUCT_VERSION="8.10"
Architecture:        x86_64
CPU op-mode(s):      32-bit, 64-bit
Byte Order:          Little Endian
CPU(s):              128
On-line CPU(s) list: 0-127
Thread(s) per core:  2
Core(s) per socket:  64
Socket(s):           1
NUMA node(s):        1
Vendor ID:           AuthenticAMD
CPU family:          25
Model:               1
Model name:          AMD EPYC 7763 64-Core Processor
Stepping:            1
CPU MHz:             2450.000
CPU max MHz:         3529.0520
CPU min MHz:         1500.0000
BogoMIPS:            4890.34
Virtualization:      AMD-V
L1d cache:           32K
L1i cache:           32K
L2 cache:            512K
L3 cache:            32768K
NUMA node0 CPU(s):   0-127
Flags:               fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 invpcid_single hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr wbnoinvd amd_ppin brs arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold v_vmsave_vmload vgif v_spec_ctrl umip pku ospke vaes vpclmulqdq rdpid overflow_recov succor smca fsrm
MemTotal:       527669564 kB
Current Directory:
/common/home/users/d/dh.huang.2023/code/rapget-translation
Evaluating microsoft/Phi-3.5-mini-instruct
[nltk_data] Downloading package wordnet to
[nltk_data]     /common/home/users/d/dh.huang.2023/nltk_data...
[nltk_data]   Package wordnet is already up-to-date!
[nltk_data] Downloading package punkt to
[nltk_data]     /common/home/users/d/dh.huang.2023/nltk_data...
[nltk_data]   Package punkt is already up-to-date!
[nltk_data] Downloading package omw-1.4 to
[nltk_data]     /common/home/users/d/dh.huang.2023/nltk_data...
[nltk_data]   Package omw-1.4 is already up-to-date!
[nltk_data] Downloading package wordnet to
[nltk_data]     /common/home/users/d/dh.huang.2023/nltk_data...
[nltk_data]   Package wordnet is already up-to-date!
[nltk_data] Downloading package punkt to
[nltk_data]     /common/home/users/d/dh.huang.2023/nltk_data...
[nltk_data]   Package punkt is already up-to-date!
[nltk_data] Downloading package omw-1.4 to
[nltk_data]     /common/home/users/d/dh.huang.2023/nltk_data...
[nltk_data]   Package omw-1.4 is already up-to-date!
`flash-attention` package not found, consider installing for better performance: No module named 'flash_attn'.
Current `flash-attention` does not support `window_size`. Either upgrade or use `attn_implementation='eager'`.
loading env vars from: /common/home/users/d/dh.huang.2023/common2/code/rapget-translation/.env
Adding /common/home/users/d/dh.huang.2023/common2/code/rapget-translation to sys.path
loading: /common/home/users/d/dh.huang.2023/common2/code/rapget-translation/eval_modules/calc_repetitions.py
loading /common/home/users/d/dh.huang.2023/common2/code/rapget-translation/llm_toolkit/translation_utils.py
CUDA is available, we have found  1  GPU(s)
NVIDIA L40
CUDA version: 12.1
microsoft/Phi-3.5-mini-instruct llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-210 False datasets/mac/mac.tsv results/mac-results_rpp_with_mnt_2048.csv False 2048 2
(0) GPU = NVIDIA L40. Max memory = 44.309 GB.
0.0 GB of memory reserved.
loading model: microsoft/Phi-3.5-mini-instruct with adapter: llama-factory/saves/Phi-3.5-mini-instruct/checkpoint-210

Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:21<00:21, 21.36s/it]
Loading checkpoint shards: 100%|██████████| 2/2 [00:32<00:00, 15.50s/it]
Loading checkpoint shards: 100%|██████████| 2/2 [00:32<00:00, 16.38s/it]
(2) GPU = NVIDIA L40. Max memory = 44.309 GB.
7.189 GB of memory reserved.
loading train/test data files
DatasetDict({
    train: Dataset({
        features: ['chinese', 'english', 'text', 'prompt'],
        num_rows: 4528
    })
    test: Dataset({
        features: ['chinese', 'english', 'text', 'prompt'],
        num_rows: 1133
    })
})
--------------------------------------------------
chinese: 老耿端起枪，眯缝起一只三角眼，一搂扳机响了枪，冰雹般的金麻雀劈哩啪啦往下落，铁砂子在柳枝间飞迸着，嚓嚓有声。
--------------------------------------------------
english: Old Geng picked up his shotgun, squinted, and pulled the trigger. Two sparrows crashed to the ground like hailstones as shotgun pellets tore noisily through the branches.
--------------------------------------------------
text: <|system|>
You are a helpful assistant that translates Chinese to English.<|end|>
<|user|>
You will be given a Chinese sentence to translate. If it is an incomplete sentence, or if you are unsure about the meaning, simply copy the input text as your output. Do not output any additional sentence such as explanation or reasoning.

Chinese: 老耿端起枪，眯缝起一只三角眼，一搂扳机响了枪，冰雹般的金麻雀劈哩啪啦往下落，铁砂子在柳枝间飞迸着，嚓嚓有声。
English:<|end|>
<|assistant|>
Old Geng picked up his shotgun, squinted, and pulled the trigger. Two sparrows crashed to the ground like hailstones as shotgun pellets tore noisily through the branches.<|endoftext|>
--------------------------------------------------
prompt: <|system|>
You are a helpful assistant that translates Chinese to English.<|end|>
<|user|>
You will be given a Chinese sentence to translate. If it is an incomplete sentence, or if you are unsure about the meaning, simply copy the input text as your output. Do not output any additional sentence such as explanation or reasoning.

Chinese: 老耿端起枪，眯缝起一只三角眼，一搂扳机响了枪，冰雹般的金麻雀劈哩啪啦往下落，铁砂子在柳枝间飞迸着，嚓嚓有声。
English:<|end|>
<|assistant|>

--------------------------------------------------
chinese: 对我一刻也不能放松。
--------------------------------------------------
english: People shouldn't let up on me for a minute.
--------------------------------------------------
text: <|system|>
You are a helpful assistant that translates Chinese to English.<|end|>
<|user|>
You will be given a Chinese sentence to translate. If it is an incomplete sentence, or if you are unsure about the meaning, simply copy the input text as your output. Do not output any additional sentence such as explanation or reasoning.

Chinese: 对我一刻也不能放松。
English:<|end|>
<|assistant|>
People shouldn't let up on me for a minute.<|endoftext|>
--------------------------------------------------
prompt: <|system|>
You are a helpful assistant that translates Chinese to English.<|end|>
<|user|>
You will be given a Chinese sentence to translate. If it is an incomplete sentence, or if you are unsure about the meaning, simply copy the input text as your output. Do not output any additional sentence such as explanation or reasoning.

Chinese: 对我一刻也不能放松。
English:<|end|>
<|assistant|>

Evaluating model: microsoft/Phi-3.5-mini-instruct/checkpoint-210 on cuda
*** Evaluating with repetition_penalty: 1.0

  0%|          | 0/567 [00:00<?, ?it/s]The `seen_tokens` attribute is deprecated and will be removed in v4.41. Use the `cache_position` model input instead.
You are not running the flash-attention implementation, expect numerical differences.

  0%|          | 1/567 [00:03<36:05,  3.83s/it]
  0%|          | 2/567 [00:08<42:05,  4.47s/it]
  1%|          | 3/567 [00:12<37:05,  3.95s/it]
  1%|          | 4/567 [00:17<42:13,  4.50s/it]
  1%|          | 5/567 [00:18<30:34,  3.26s/it]
  1%|          | 6/567 [00:20<27:54,  2.99s/it]
  1%|          | 7/567 [00:21<21:15,  2.28s/it]
  1%|▏         | 8/567 [00:24<22:21,  2.40s/it]
  2%|▏         | 9/567 [00:28<27:42,  2.98s/it]
  2%|▏         | 10/567 [00:30<24:02,  2.59s/it]
  2%|▏         | 11/567 [00:33<25:05,  2.71s/it]
  2%|▏         | 12/567 [00:34<20:53,  2.26s/it]
  2%|▏         | 13/567 [00:36<20:34,  2.23s/it]
  2%|▏         | 14/567 [00:37<17:30,  1.90s/it]
  3%|▎         | 15/567 [00:39<15:45,  1.71s/it]
  3%|▎         | 16/567 [00:41<18:05,  1.97s/it]
  3%|▎         | 17/567 [00:47<27:10,  2.96s/it]
  3%|▎         | 18/567 [00:48<23:27,  2.56s/it]
  3%|▎         | 19/567 [00:49<19:42,  2.16s/it]
  4%|▎         | 20/567 [00:51<18:38,  2.05s/it]
  4%|▎         | 21/567 [00:54<21:50,  2.40s/it]
  4%|▍         | 22/567 [00:56<19:45,  2.17s/it]
  4%|▍         | 23/567 [01:01<26:05,  2.88s/it]
  4%|▍         | 24/567 [01:02<21:58,  2.43s/it]
  4%|▍         | 25/567 [01:03<17:49,  1.97s/it]
  5%|▍         | 26/567 [01:05<19:07,  2.12s/it]
  5%|▍         | 27/567 [01:07<17:37,  1.96s/it]
  5%|▍         | 28/567 [01:12<27:00,  3.01s/it]
  5%|▌         | 29/567 [01:14<24:17,  2.71s/it]
  5%|▌         | 30/567 [01:17<25:24,  2.84s/it]
  5%|▌         | 31/567 [01:18<20:13,  2.26s/it]
  6%|▌         | 32/567 [01:21<21:09,  2.37s/it]
  6%|▌         | 33/567 [01:23<19:48,  2.23s/it]
  6%|▌         | 34/567 [01:26<21:46,  2.45s/it]
  6%|▌         | 35/567 [01:28<21:38,  2.44s/it]
  6%|▋         | 36/567 [01:29<17:21,  1.96s/it]
  7%|▋         | 37/567 [01:30<13:47,  1.56s/it]
  7%|▋         | 38/567 [01:31<12:47,  1.45s/it]
  7%|▋         | 39/567 [01:33<13:20,  1.52s/it]
  7%|▋         | 40/567 [01:35<14:44,  1.68s/it]
  7%|▋         | 41/567 [01:35<11:51,  1.35s/it]
  7%|▋         | 42/567 [01:39<17:47,  2.03s/it]
  8%|▊         | 43/567 [01:40<15:13,  1.74s/it]
  8%|▊         | 44/567 [01:42<16:30,  1.89s/it]
  8%|▊         | 45/567 [01:45<17:44,  2.04s/it]
  8%|▊         | 46/567 [01:46<15:26,  1.78s/it]
  8%|▊         | 47/567 [01:48<16:37,  1.92s/it]
  8%|▊         | 48/567 [01:51<20:04,  2.32s/it]
  9%|▊         | 49/567 [01:53<18:15,  2.11s/it]
  9%|▉         | 50/567 [01:55<17:51,  2.07s/it]
  9%|▉         | 51/567 [01:58<20:55,  2.43s/it]
  9%|▉         | 52/567 [01:59<16:49,  1.96s/it]
  9%|▉         | 53/567 [02:10<40:57,  4.78s/it]
 10%|▉         | 54/567 [02:14<38:04,  4.45s/it]
 10%|▉         | 55/567 [02:18<36:17,  4.25s/it]
 10%|▉         | 56/567 [02:24<39:48,  4.67s/it]
 10%|█         | 57/567 [02:27<35:30,  4.18s/it]
 10%|█         | 58/567 [02:28<27:33,  3.25s/it]
 10%|█         | 59/567 [02:31<27:53,  3.29s/it]
 11%|█         | 60/567 [02:33<24:05,  2.85s/it]
 11%|█         | 61/567 [02:34<20:02,  2.38s/it]
 11%|█         | 62/567 [02:36<17:41,  2.10s/it]
 11%|█         | 63/567 [02:39<20:07,  2.40s/it]
 11%|█▏        | 64/567 [02:42<21:39,  2.58s/it]
 11%|█▏        | 65/567 [02:43<18:53,  2.26s/it]
 12%|█▏        | 66/567 [02:46<21:28,  2.57s/it]
 12%|█▏        | 67/567 [02:47<17:08,  2.06s/it]
 12%|█▏        | 68/567 [02:54<27:28,  3.30s/it]
 12%|█▏        | 69/567 [02:55<22:49,  2.75s/it]
 12%|█▏        | 70/567 [02:57<21:10,  2.56s/it]
 13%|█▎        | 71/567 [02:58<17:42,  2.14s/it]
 13%|█▎        | 72/567 [03:01<17:59,  2.18s/it]
 13%|█▎        | 73/567 [03:02<14:59,  1.82s/it]
 13%|█▎        | 74/567 [03:03<14:55,  1.82s/it]
 13%|█▎        | 75/567 [03:05<13:25,  1.64s/it]
 13%|█▎        | 76/567 [03:06<14:09,  1.73s/it]
 14%|█▎        | 77/567 [03:09<14:58,  1.83s/it]
 14%|█▍        | 78/567 [03:11<16:13,  1.99s/it]
 14%|█▍        | 79/567 [03:13<16:46,  2.06s/it]
 14%|█▍        | 80/567 [03:14<14:01,  1.73s/it]
 14%|█▍        | 81/567 [03:15<12:16,  1.51s/it]
 14%|█▍        | 82/567 [03:17<12:39,  1.57s/it]
 15%|█▍        | 83/567 [03:19<13:26,  1.67s/it]
 15%|█▍        | 84/567 [03:20<13:24,  1.67s/it]
 15%|█▍        | 85/567 [03:21<11:25,  1.42s/it]
 15%|█▌        | 86/567 [03:22<09:48,  1.22s/it]
 15%|█▌        | 87/567 [03:23<09:49,  1.23s/it]
 16%|█▌        | 88/567 [03:25<10:11,  1.28s/it]
 16%|█▌        | 89/567 [03:29<18:01,  2.26s/it]
 16%|█▌        | 90/567 [03:31<17:25,  2.19s/it]
 16%|█▌        | 91/567 [03:34<18:20,  2.31s/it]
 16%|█▌        | 92/567 [03:35<16:06,  2.04s/it]
 16%|█▋        | 93/567 [03:36<13:24,  1.70s/it]
 17%|█▋        | 94/567 [03:39<15:57,  2.02s/it]
 17%|█▋        | 95/567 [03:40<14:49,  1.88s/it]
 17%|█▋        | 96/567 [03:43<15:27,  1.97s/it]
 17%|█▋        | 97/567 [03:45<16:27,  2.10s/it]
 17%|█▋        | 98/567 [03:46<13:08,  1.68s/it]
 17%|█▋        | 99/567 [03:47<12:44,  1.63s/it]
 18%|█▊        | 100/567 [03:52<19:07,  2.46s/it]
 18%|█▊        | 101/567 [03:54<18:24,  2.37s/it]
 18%|█▊        | 102/567 [03:56<17:39,  2.28s/it]
 18%|█▊        | 103/567 [03:57<14:24,  1.86s/it]
 18%|█▊        | 104/567 [03:59<15:08,  1.96s/it]
 19%|█▊        | 105/567 [04:05<23:56,  3.11s/it]
 19%|█▊        | 106/567 [04:08<23:14,  3.03s/it]
 19%|█▉        | 107/567 [04:08<17:57,  2.34s/it]
 19%|█▉        | 108/567 [04:13<23:42,  3.10s/it]
 19%|█▉        | 109/567 [04:14<18:00,  2.36s/it]
 19%|█▉        | 110/567 [04:15<15:11,  2.00s/it]
 20%|█▉        | 111/567 [18:04<31:40:58, 250.13s/it]
 20%|█▉        | 112/567 [18:07<22:14:09, 175.93s/it]
 20%|█▉        | 113/567 [18:12<15:44:02, 124.76s/it]
 20%|██        | 114/567 [18:14<11:03:04, 87.82s/it] 
 20%|██        | 115/567 [18:17<7:49:08, 62.28s/it] 
 20%|██        | 116/567 [18:18<5:31:24, 44.09s/it]
 21%|██        | 117/567 [18:20<3:55:15, 31.37s/it]
 21%|██        | 118/567 [18:23<2:50:37, 22.80s/it]
 21%|██        | 119/567 [18:28<2:10:59, 17.54s/it]
 21%|██        | 120/567 [18:30<1:35:16, 12.79s/it]
 21%|██▏       | 121/567 [18:31<1:08:30,  9.22s/it]
 22%|██▏       | 122/567 [18:32<51:29,  6.94s/it]  
 22%|██▏       | 123/567 [18:34<39:55,  5.40s/it]
 22%|██▏       | 124/567 [18:35<30:07,  4.08s/it]
 22%|██▏       | 125/567 [18:37<25:04,  3.40s/it]
 22%|██▏       | 126/567 [18:38<20:39,  2.81s/it]
 22%|██▏       | 127/567 [18:42<23:31,  3.21s/it]
 23%|██▎       | 128/567 [18:45<22:34,  3.09s/it]
 23%|██▎       | 129/567 [18:49<24:04,  3.30s/it]
 23%|██▎       | 130/567 [18:56<32:40,  4.49s/it]
 23%|██▎       | 131/567 [19:00<31:13,  4.30s/it]
 23%|██▎       | 132/567 [19:07<36:22,  5.02s/it]
 23%|██▎       | 133/567 [19:13<38:14,  5.29s/it]
 24%|██▎       | 134/567 [19:20<42:04,  5.83s/it]
 24%|██▍       | 135/567 [19:22<34:12,  4.75s/it]
 24%|██▍       | 136/567 [19:24<28:09,  3.92s/it]
 24%|██▍       | 137/567 [19:26<24:13,  3.38s/it]
 24%|██▍       | 138/567 [19:28<20:04,  2.81s/it]
 25%|██▍       | 139/567 [19:29<17:38,  2.47s/it]
 25%|██▍       | 140/567 [19:31<15:50,  2.23s/it]
 25%|██▍       | 141/567 [19:34<17:32,  2.47s/it]
 25%|██▌       | 142/567 [19:35<15:07,  2.13s/it]
 25%|██▌       | 143/567 [19:37<14:26,  2.04s/it]
 25%|██▌       | 144/567 [19:40<16:20,  2.32s/it]
 26%|██▌       | 145/567 [19:42<14:47,  2.10s/it]
 26%|██▌       | 146/567 [19:44<15:48,  2.25s/it]
 26%|██▌       | 147/567 [19:48<18:43,  2.68s/it]
 26%|██▌       | 148/567 [19:50<17:17,  2.48s/it]
 26%|██▋       | 149/567 [19:51<14:27,  2.07s/it]
 26%|██▋       | 150/567 [19:52<11:08,  1.60s/it]
 27%|██▋       | 151/567 [19:52<09:29,  1.37s/it]
 27%|██▋       | 152/567 [19:54<10:18,  1.49s/it]
 27%|██▋       | 153/567 [19:57<12:27,  1.81s/it]
 27%|██▋       | 154/567 [19:58<11:03,  1.61s/it]
 27%|██▋       |