diff --git "a/logs/l40-1gpu-epoch-1.txt" "b/logs/l40-1gpu-epoch-1.txt" new file mode 100644--- /dev/null +++ "b/logs/l40-1gpu-epoch-1.txt" @@ -0,0 +1,435 @@ +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 +Thu Aug 8 23:20:24 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 38C P0 78W / 300W | 25036MiB / 46068MiB | 0% Default | +| | | N/A | ++-----------------------------------------+------------------------+----------------------+ + ++-----------------------------------------------------------------------------------------+ +| Processes: | +| GPU GI CI PID Type Process name GPU Memory | +| ID ID Usage | +|=========================================================================================| ++-----------------------------------------------------------------------------------------+ +Linux lithium 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: 3097.291 +CPU max MHz: 3529.0520 +CPU min MHz: 1500.0000 +BogoMIPS: 4890.62 +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: 527670712 kB +Current Directory: +/common/home/users/d/dh.huang.2023/code/rapget-translation +Evaluating internlm/internlm2_5-7b-chat +Using the latest cached version of the module from /common/scratch/users/d/dh.huang.2023/transformers/modules/evaluate_modules/metrics/evaluate-metric--meteor/ea1b63f27faab173b022be2d3cc3df2fc44a894247f833943ea98c8a7caeb1e8 (last modified on Wed Jun 19 06:03:37 2024) since it couldn't be found locally at evaluate-metric--meteor, or remotely on the Hugging Face Hub. +[nltk_data] Error loading wordnet: +[nltk_data] Error loading punkt: +[nltk_data] Error loading omw-1.4: +Using the latest cached version of the module from /common/scratch/users/d/dh.huang.2023/transformers/modules/evaluate_modules/metrics/evaluate-metric--bleu/9e0985c1200e367cce45605ce0ecb5ede079894e0f24f54613fca08eeb8aff76 (last modified on Wed May 8 07:48:30 2024) since it couldn't be found locally at evaluate-metric--bleu, or remotely on the Hugging Face Hub. +Using the latest cached version of the module from /common/scratch/users/d/dh.huang.2023/transformers/modules/evaluate_modules/metrics/evaluate-metric--rouge/b01e0accf3bd6dd24839b769a5fda24e14995071570870922c71970b3a6ed886 (last modified on Wed May 8 07:48:31 2024) since it couldn't be found locally at evaluate-metric--rouge, or remotely on the Hugging Face Hub. +Using the latest cached version of the module from /common/scratch/users/d/dh.huang.2023/transformers/modules/evaluate_modules/metrics/evaluate-metric--meteor/ea1b63f27faab173b022be2d3cc3df2fc44a894247f833943ea98c8a7caeb1e8 (last modified on Wed Jun 19 06:03:37 2024) since it couldn't be found locally at evaluate-metric--meteor, or remotely on the Hugging Face Hub. +[nltk_data] Error loading wordnet: +[nltk_data] Error loading punkt: +[nltk_data] Error loading omw-1.4: +Using the latest cached version of the module from /common/scratch/users/d/dh.huang.2023/transformers/modules/evaluate_modules/metrics/evaluate-metric--accuracy/f887c0aab52c2d38e1f8a215681126379eca617f96c447638f751434e8e65b14 (last modified on Wed Jun 19 06:03:39 2024) since it couldn't be found locally at evaluate-metric--accuracy, or remotely on the Hugging Face Hub. +loading env vars from: /common/home/users/d/dh.huang.2023/common2/code/rapget-translation/.env +workding dir: /common/home/users/d/dh.huang.2023/common2/code/rapget-translation +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 +internlm/internlm2_5-7b-chat llama-factory/saves/internlm2_5-7b-chat False 1 results/mac-results_fine_tuned.csv +CUDA is available, we have found 1 GPU(s) +NVIDIA L40 +CUDA version: 12.1 +Evaluating model: internlm/internlm2_5-7b-chat on cuda +(0) GPU = NVIDIA L40. Max memory = 44.309 GB. +0.0 GB of memory reserved. +loading model: internlm/internlm2_5-7b-chat with adapter: None + Loading checkpoint shards: 0%| | 0/8 [00:00<|im_start|>system +You are a helpful assistant that translates Chinese to English.<|im_end|> +<|im_start|>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:<|im_end|> +<|im_start|>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. +-------------------------------------------------- +prompt: <|im_start|>system +You are a helpful assistant that translates Chinese to English.<|im_end|> +<|im_start|>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:<|im_end|> +<|im_start|>assistant + +(1) GPU = NVIDIA L40. Max memory = 44.309 GB. +14.416 GB of memory reserved. +found 6 checkpoints: ['checkpoint-35', 'checkpoint-70', 'checkpoint-105', 'checkpoint-140', 'checkpoint-175', 'checkpoint-210'] +Running from epoch 1 to 6 +Epoch 1 +loading adapter: llama-factory/saves/internlm2_5-7b-chat/checkpoint-35 + 0%| | 0/1133 [00:00 + evaluate_model_all_epochs( + File "/common/home/users/d/dh.huang.2023/common2/code/rapget-translation/llm_toolkit/eval_epochs.py", line 63, in evaluate_model_all_epochs + adapter_name = model.load_adapter(adapter_path) + ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + File "/common/home/users/d/dh.huang.2023/.conda/envs/llm-perf-bench/lib/python3.11/site-packages/transformers/integrations/peft.py", line 146, in load_adapter + raise ValueError(f"Adapter with name {adapter_name} already exists. Please use a different name.") +ValueError: Adapter with name default already exists. Please use a different name. +Current Directory: +/common/home/users/d/dh.huang.2023/code/rapget-translation +Evaluating Qwen/Qwen2-7B-Instruct +Using the latest cached version of the module from /common/scratch/users/d/dh.huang.2023/transformers/modules/evaluate_modules/metrics/evaluate-metric--meteor/ea1b63f27faab173b022be2d3cc3df2fc44a894247f833943ea98c8a7caeb1e8 (last modified on Wed Jun 19 06:03:37 2024) since it couldn't be found locally at evaluate-metric--meteor, or remotely on the Hugging Face Hub. +[nltk_data] Error loading wordnet: +[nltk_data] Error loading punkt: +[nltk_data] Error loading omw-1.4: +Using the latest cached version of the module from /common/scratch/users/d/dh.huang.2023/transformers/modules/evaluate_modules/metrics/evaluate-metric--bleu/9e0985c1200e367cce45605ce0ecb5ede079894e0f24f54613fca08eeb8aff76 (last modified on Wed May 8 07:48:30 2024) since it couldn't be found locally at evaluate-metric--bleu, or remotely on the Hugging Face Hub. +Using the latest cached version of the module from /common/scratch/users/d/dh.huang.2023/transformers/modules/evaluate_modules/metrics/evaluate-metric--rouge/b01e0accf3bd6dd24839b769a5fda24e14995071570870922c71970b3a6ed886 (last modified on Wed May 8 07:48:31 2024) since it couldn't be found locally at evaluate-metric--rouge, or remotely on the Hugging Face Hub. +Using the latest cached version of the module from /common/scratch/users/d/dh.huang.2023/transformers/modules/evaluate_modules/metrics/evaluate-metric--meteor/ea1b63f27faab173b022be2d3cc3df2fc44a894247f833943ea98c8a7caeb1e8 (last modified on Wed Jun 19 06:03:37 2024) since it couldn't be found locally at evaluate-metric--meteor, or remotely on the Hugging Face Hub. +[nltk_data] Error loading wordnet: +[nltk_data] Error loading punkt: +[nltk_data] Error loading omw-1.4: +Using the latest cached version of the module from /common/scratch/users/d/dh.huang.2023/transformers/modules/evaluate_modules/metrics/evaluate-metric--accuracy/f887c0aab52c2d38e1f8a215681126379eca617f96c447638f751434e8e65b14 (last modified on Wed Jun 19 06:03:39 2024) since it couldn't be found locally at evaluate-metric--accuracy, or remotely on the Hugging Face Hub. +loading env vars from: /common/home/users/d/dh.huang.2023/common2/code/rapget-translation/.env +workding dir: /common/home/users/d/dh.huang.2023/common2/code/rapget-translation +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 +Qwen/Qwen2-7B-Instruct llama-factory/saves/Qwen2-7B-Instruct False 1 results/mac-results_fine_tuned.csv +CUDA is available, we have found 1 GPU(s) +NVIDIA L40 +CUDA version: 12.1 +Evaluating model: Qwen/Qwen2-7B-Instruct on cuda +(0) GPU = NVIDIA L40. Max memory = 44.309 GB. +0.0 GB of memory reserved. +loading model: Qwen/Qwen2-7B-Instruct with adapter: None + Loading checkpoint shards: 0%| | 0/4 [00:00system +You are a helpful assistant that translates Chinese to English.<|im_end|> +<|im_start|>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:<|im_end|> +<|im_start|>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.<|im_end|> +-------------------------------------------------- +prompt: <|im_start|>system +You are a helpful assistant that translates Chinese to English.<|im_end|> +<|im_start|>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:<|im_end|> +<|im_start|>assistant + +(1) GPU = NVIDIA L40. Max memory = 44.309 GB. +14.881 GB of memory reserved. +found 6 checkpoints: ['checkpoint-35', 'checkpoint-70', 'checkpoint-105', 'checkpoint-140', 'checkpoint-175', 'checkpoint-210'] +Running from epoch 1 to 6 +Epoch 1 +loading adapter: llama-factory/saves/Qwen2-7B-Instruct/checkpoint-35 + 0%| | 0/1133 [00:00 + evaluate_model_all_epochs( + File "/common/home/users/d/dh.huang.2023/common2/code/rapget-translation/llm_toolkit/eval_epochs.py", line 63, in evaluate_model_all_epochs + adapter_name = model.load_adapter(adapter_path) + ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + File "/common/home/users/d/dh.huang.2023/.conda/envs/llm-perf-bench/lib/python3.11/site-packages/transformers/integrations/peft.py", line 146, in load_adapter + raise ValueError(f"Adapter with name {adapter_name} already exists. Please use a different name.") +ValueError: Adapter with name default already exists. Please use a different name. +Current Directory: +/common/home/users/d/dh.huang.2023/code/rapget-translation +Evaluating shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat +Using the latest cached version of the module from /common/scratch/users/d/dh.huang.2023/transformers/modules/evaluate_modules/metrics/evaluate-metric--meteor/ea1b63f27faab173b022be2d3cc3df2fc44a894247f833943ea98c8a7caeb1e8 (last modified on Wed Jun 19 06:03:37 2024) since it couldn't be found locally at evaluate-metric--meteor, or remotely on the Hugging Face Hub. +[nltk_data] Error loading wordnet: +[nltk_data] Error loading punkt: +[nltk_data] Error loading omw-1.4: +Using the latest cached version of the module from /common/scratch/users/d/dh.huang.2023/transformers/modules/evaluate_modules/metrics/evaluate-metric--bleu/9e0985c1200e367cce45605ce0ecb5ede079894e0f24f54613fca08eeb8aff76 (last modified on Wed May 8 07:48:30 2024) since it couldn't be found locally at evaluate-metric--bleu, or remotely on the Hugging Face Hub. +Using the latest cached version of the module from /common/scratch/users/d/dh.huang.2023/transformers/modules/evaluate_modules/metrics/evaluate-metric--rouge/b01e0accf3bd6dd24839b769a5fda24e14995071570870922c71970b3a6ed886 (last modified on Wed May 8 07:48:31 2024) since it couldn't be found locally at evaluate-metric--rouge, or remotely on the Hugging Face Hub. +Using the latest cached version of the module from /common/scratch/users/d/dh.huang.2023/transformers/modules/evaluate_modules/metrics/evaluate-metric--meteor/ea1b63f27faab173b022be2d3cc3df2fc44a894247f833943ea98c8a7caeb1e8 (last modified on Wed Jun 19 06:03:37 2024) since it couldn't be found locally at evaluate-metric--meteor, or remotely on the Hugging Face Hub. +[nltk_data] Error loading wordnet: +[nltk_data] Error loading punkt: +[nltk_data] Error loading omw-1.4: +Using the latest cached version of the module from /common/scratch/users/d/dh.huang.2023/transformers/modules/evaluate_modules/metrics/evaluate-metric--accuracy/f887c0aab52c2d38e1f8a215681126379eca617f96c447638f751434e8e65b14 (last modified on Wed Jun 19 06:03:39 2024) since it couldn't be found locally at evaluate-metric--accuracy, or remotely on the Hugging Face Hub. +loading env vars from: /common/home/users/d/dh.huang.2023/common2/code/rapget-translation/.env +workding dir: /common/home/users/d/dh.huang.2023/common2/code/rapget-translation +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 +shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat llama-factory/saves/Mistral-7B-v0.3-Chinese-Chat False 1 results/mac-results_fine_tuned.csv +CUDA is available, we have found 1 GPU(s) +NVIDIA L40 +CUDA version: 12.1 +Evaluating model: shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat on cuda +(0) GPU = NVIDIA L40. Max memory = 44.309 GB. +0.0 GB of memory reserved. +loading model: shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat with adapter: None + Loading checkpoint shards: 0%| | 0/3 [00:00You are a helpful assistant that translates Chinese to English. [INST] 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: [/INST]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. +-------------------------------------------------- +prompt: You are a helpful assistant that translates Chinese to English. [INST] 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: [/INST] +(1) GPU = NVIDIA L40. Max memory = 44.309 GB. +13.627 GB of memory reserved. +found 6 checkpoints: ['checkpoint-35', 'checkpoint-70', 'checkpoint-105', 'checkpoint-140', 'checkpoint-175', 'checkpoint-210'] +Running from epoch 1 to 6 +Epoch 1 +loading adapter: llama-factory/saves/Mistral-7B-v0.3-Chinese-Chat/checkpoint-35 + 0%| | 0/1133 [00:00 + evaluate_model_all_epochs( + File "/common/home/users/d/dh.huang.2023/common2/code/rapget-translation/llm_toolkit/eval_epochs.py", line 63, in evaluate_model_all_epochs + adapter_name = model.load_adapter(adapter_path) + ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + File "/common/home/users/d/dh.huang.2023/.conda/envs/llm-perf-bench/lib/python3.11/site-packages/transformers/integrations/peft.py", line 146, in load_adapter + raise ValueError(f"Adapter with name {adapter_name} already exists. Please use a different name.") +ValueError: Adapter with name default already exists. Please use a different name. +Current Directory: +/common/home/users/d/dh.huang.2023/code/rapget-translation +Evaluating shenzhi-wang/Llama3.1-8B-Chinese-Chat +Using the latest cached version of the module from /common/scratch/users/d/dh.huang.2023/transformers/modules/evaluate_modules/metrics/evaluate-metric--meteor/ea1b63f27faab173b022be2d3cc3df2fc44a894247f833943ea98c8a7caeb1e8 (last modified on Wed Jun 19 06:03:37 2024) since it couldn't be found locally at evaluate-metric--meteor, or remotely on the Hugging Face Hub. +[nltk_data] Error loading wordnet: +[nltk_data] Error loading punkt: +[nltk_data] Error loading omw-1.4: +Using the latest cached version of the module from /common/scratch/users/d/dh.huang.2023/transformers/modules/evaluate_modules/metrics/evaluate-metric--bleu/9e0985c1200e367cce45605ce0ecb5ede079894e0f24f54613fca08eeb8aff76 (last modified on Wed May 8 07:48:30 2024) since it couldn't be found locally at evaluate-metric--bleu, or remotely on the Hugging Face Hub. +Using the latest cached version of the module from /common/scratch/users/d/dh.huang.2023/transformers/modules/evaluate_modules/metrics/evaluate-metric--rouge/b01e0accf3bd6dd24839b769a5fda24e14995071570870922c71970b3a6ed886 (last modified on Wed May 8 07:48:31 2024) since it couldn't be found locally at evaluate-metric--rouge, or remotely on the Hugging Face Hub. +Using the latest cached version of the module from /common/scratch/users/d/dh.huang.2023/transformers/modules/evaluate_modules/metrics/evaluate-metric--meteor/ea1b63f27faab173b022be2d3cc3df2fc44a894247f833943ea98c8a7caeb1e8 (last modified on Wed Jun 19 06:03:37 2024) since it couldn't be found locally at evaluate-metric--meteor, or remotely on the Hugging Face Hub. +[nltk_data] Error loading wordnet: +[nltk_data] Error loading punkt: +[nltk_data] Error loading omw-1.4: +Using the latest cached version of the module from /common/scratch/users/d/dh.huang.2023/transformers/modules/evaluate_modules/metrics/evaluate-metric--accuracy/f887c0aab52c2d38e1f8a215681126379eca617f96c447638f751434e8e65b14 (last modified on Wed Jun 19 06:03:39 2024) since it couldn't be found locally at evaluate-metric--accuracy, or remotely on the Hugging Face Hub. +loading env vars from: /common/home/users/d/dh.huang.2023/common2/code/rapget-translation/.env +workding dir: /common/home/users/d/dh.huang.2023/common2/code/rapget-translation +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 +shenzhi-wang/Llama3.1-8B-Chinese-Chat llama-factory/saves/Llama3.1-8B-Chinese-Chat False 1 results/mac-results_fine_tuned.csv +CUDA is available, we have found 1 GPU(s) +NVIDIA L40 +CUDA version: 12.1 +Evaluating model: shenzhi-wang/Llama3.1-8B-Chinese-Chat on cuda +(0) GPU = NVIDIA L40. Max memory = 44.309 GB. +0.0 GB of memory reserved. +loading model: shenzhi-wang/Llama3.1-8B-Chinese-Chat with adapter: None + Loading checkpoint shards: 0%| | 0/4 [00:00<|start_header_id|>system<|end_header_id|> + +You are a helpful assistant that translates Chinese to English.<|eot_id|><|start_header_id|>user<|end_header_id|> + +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:<|eot_id|><|start_header_id|>assistant<|end_header_id|> + +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.<|eot_id|> +-------------------------------------------------- +prompt: <|begin_of_text|><|start_header_id|>system<|end_header_id|> + +You are a helpful assistant that translates Chinese to English.<|eot_id|><|start_header_id|>user<|end_header_id|> + +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:<|eot_id|><|start_header_id|>assistant<|end_header_id|> + + +(1) GPU = NVIDIA L40. Max memory = 44.309 GB. +15.084 GB of memory reserved. +found 6 checkpoints: ['checkpoint-35', 'checkpoint-70', 'checkpoint-105', 'checkpoint-140', 'checkpoint-175', 'checkpoint-210'] +Running from epoch 1 to 6 +Epoch 1 +loading adapter: llama-factory/saves/Llama3.1-8B-Chinese-Chat/checkpoint-35 + 0%| | 0/1133 [00:00 + evaluate_model_all_epochs( + File "/common/home/users/d/dh.huang.2023/common2/code/rapget-translation/llm_toolkit/eval_epochs.py", line 63, in evaluate_model_all_epochs + adapter_name = model.load_adapter(adapter_path) + ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + File "/common/home/users/d/dh.huang.2023/.conda/envs/llm-perf-bench/lib/python3.11/site-packages/transformers/integrations/peft.py", line 146, in load_adapter + raise ValueError(f"Adapter with name {adapter_name} already exists. Please use a different name.") +ValueError: Adapter with name default already exists. Please use a different name. +srun: error: lithium: task 0: Exited with exit code 1 +srun: Terminating StepId=76652.0 +Job ID: 76652 +Cluster: crimson +User/Group: dh.huang.2023/dh.huang.2023 +State: FAILED (exit code 1) +Nodes: 1 +Cores per node: 10 +CPU Utilized: 01:44:48 +CPU Efficiency: 6.93% of 1-01:13:10 core-walltime +Job Wall-clock time: 02:31:19 +Memory Utilized: 4.80 GB +Memory Efficiency: 1.87% of 256.00 GB