p04798526
/
LLaMA-Factory-310P3
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

testrun: test inference

This commit is contained in:
wql 2024-09-19 13:30:51 +08:00
parent 935319d630
commit bbbe4e2d00
17 changed files with 250 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
results/inference_Qwen-7B_8_gpu_50_step_20240919094809/inference_Qwen-7B_8_gpu_50_step_20240919094809.yaml Normal file
View File

@ -0,0 +1,14 @@
cutoff_len: 1024
ddp_timeout: 180000000
do_predict: true
eval_dataset: alpaca_gpt4_zh
include_tokens_per_second: true
max_samples: 50
model_name_or_path: ../../../models/qwen
output_dir: ./results/inference_Qwen-7B_8_gpu_50_step_20240919094809
overwrite_cache: true
overwrite_output_dir: true
per_device_eval_batch_size: 2
predict_with_generate: true
preprocessing_num_workers: 16
template: qwen

5
results/inference_Qwen-7B_8_gpu_50_step_20240919094809/log.txt Normal file
View File

@ -0,0 +1,5 @@
[2024-09-19 09:48:29,732] [INFO] [real_accelerator.py:203:get_accelerator] Setting ds_accelerator to npu (auto detect)
 [WARNING]  async_io requires the dev libaio .so object and headers but these were not found.
 [WARNING]  async_io: please install the libaio-devel package with yum
 [WARNING]  If libaio is already installed (perhaps from source), try setting the CFLAGS and LDFLAGS environment variables to where it can be found.
09/19/2024 09:48:35 - INFO - llamafactory.hparams.parser - Process rank: 0, device: npu:0, n_gpu: 1, distributed training: False, compute dtype: None

1
results/inference_Qwen-7B_8_gpu_50_step_20240919094809/npu_status_20240919094809.json Normal file
View File

@ -0,0 +1 @@
{"cur_time": "2024-09-19 09:48:20", "npu_power_dissipation": [{"npu_id": 0, "power_dissipation": 85.6}, {"npu_id": 1, "power_dissipation": 90.2}, {"npu_id": 2, "power_dissipation": 93.3}, {"npu_id": 3, "power_dissipation": 88.6}, {"npu_id": 4, "power_dissipation": 93.0}, {"npu_id": 5, "power_dissipation": 93.5}, {"npu_id": 6, "power_dissipation": 92.6}, {"npu_id": 7, "power_dissipation": 90.9}], "device_mem_usage": [{"npu_id": 0, "mem_usage_percent": 6}, {"npu_id": 1, "mem_usage_percent": 6}, {"npu_id": 2, "mem_usage_percent": 6}, {"npu_id": 3, "mem_usage_percent": 6}, {"npu_id": 4, "mem_usage_percent": 6}, {"npu_id": 5, "mem_usage_percent": 6}, {"npu_id": 6, "mem_usage_percent": 6}, {"npu_id": 7, "mem_usage_percent": 6}]}

14
results/inference_Qwen-7B_8_gpu_50_step_20240919110437/inference_Qwen-7B_8_gpu_50_step_20240919110437.yaml Normal file
View File

@ -0,0 +1,14 @@
cutoff_len: 1024
ddp_timeout: 180000000
do_predict: true
eval_dataset: alpaca_gpt4_zh
include_tokens_per_second: true
max_samples: 50
model_name_or_path: ../../../models/qwen
output_dir: ./results/inference_Qwen-7B_8_gpu_50_step_20240919110437
overwrite_cache: true
overwrite_output_dir: true
per_device_eval_batch_size: 2
predict_with_generate: true
preprocessing_num_workers: 16
template: qwen

8
results/inference_Qwen-7B_8_gpu_50_step_20240919110437/log.txt Normal file
View File

@ -0,0 +1,8 @@
[2024-09-19 11:04:57,330] [INFO] [real_accelerator.py:203:get_accelerator] Setting ds_accelerator to npu (auto detect)
 [WARNING]  async_io requires the dev libaio .so object and headers but these were not found.
 [WARNING]  async_io: please install the libaio-devel package with yum
 [WARNING]  If libaio is already installed (perhaps from source), try setting the CFLAGS and LDFLAGS environment variables to where it can be found.
09/19/2024 11:05:02 - INFO - llamafactory.hparams.parser - Process rank: 0, device: npu:0, n_gpu: 1, distributed training: False, compute dtype: None
09/19/2024 11:05:03 - INFO - llamafactory.data.template - Add eos token: <|im_end|>
09/19/2024 11:05:03 - INFO - llamafactory.data.template - Add pad token: <|im_end|>
09/19/2024 11:05:03 - INFO - llamafactory.data.loader - Loading dataset llamafactory/alpaca_gpt4_zh...

1
results/inference_Qwen-7B_8_gpu_50_step_20240919110437/npu_status_20240919110437.json Normal file
View File

@ -0,0 +1 @@
{"cur_time": "2024-09-19 11:04:48", "npu_power_dissipation": [{"npu_id": 0, "power_dissipation": 85.4}, {"npu_id": 1, "power_dissipation": 90.1}, {"npu_id": 2, "power_dissipation": 93.5}, {"npu_id": 3, "power_dissipation": 88.4}, {"npu_id": 4, "power_dissipation": 92.9}, {"npu_id": 5, "power_dissipation": 93.4}, {"npu_id": 6, "power_dissipation": 92.9}, {"npu_id": 7, "power_dissipation": 91.0}], "device_mem_usage": [{"npu_id": 0, "mem_usage_percent": 6}, {"npu_id": 1, "mem_usage_percent": 6}, {"npu_id": 2, "mem_usage_percent": 6}, {"npu_id": 3, "mem_usage_percent": 6}, {"npu_id": 4, "mem_usage_percent": 6}, {"npu_id": 5, "mem_usage_percent": 6}, {"npu_id": 6, "mem_usage_percent": 6}, {"npu_id": 7, "mem_usage_percent": 6}]}

14
results/inference_Qwen-7B_8_gpu_50_step_20240919110600/inference_Qwen-7B_8_gpu_50_step_20240919110600.yaml Normal file
View File

@ -0,0 +1,14 @@
cutoff_len: 1024
ddp_timeout: 180000000
do_predict: true
eval_dataset: alpaca_gpt4_zh
include_tokens_per_second: true
max_samples: 50
model_name_or_path: ../../../models/qwen
output_dir: ./results/inference_Qwen-7B_8_gpu_50_step_20240919110600
overwrite_cache: true
overwrite_output_dir: true
per_device_eval_batch_size: 2
predict_with_generate: true
preprocessing_num_workers: 16
template: qwen

8
results/inference_Qwen-7B_8_gpu_50_step_20240919110600/log.txt Normal file
View File

@ -0,0 +1,8 @@
[2024-09-19 11:06:20,616] [INFO] [real_accelerator.py:203:get_accelerator] Setting ds_accelerator to npu (auto detect)
 [WARNING]  async_io requires the dev libaio .so object and headers but these were not found.
 [WARNING]  async_io: please install the libaio-devel package with yum
 [WARNING]  If libaio is already installed (perhaps from source), try setting the CFLAGS and LDFLAGS environment variables to where it can be found.
09/19/2024 11:06:26 - INFO - llamafactory.hparams.parser - Process rank: 0, device: npu:0, n_gpu: 1, distributed training: False, compute dtype: None
09/19/2024 11:06:27 - INFO - llamafactory.data.template - Add eos token: <|im_end|>
09/19/2024 11:06:27 - INFO - llamafactory.data.template - Add pad token: <|im_end|>
09/19/2024 11:06:27 - INFO - llamafactory.data.loader - Loading dataset llamafactory/alpaca_gpt4_zh...

1
results/inference_Qwen-7B_8_gpu_50_step_20240919110600/npu_status_20240919110601.json Normal file
View File

@ -0,0 +1 @@
{"cur_time": "2024-09-19 11:06:12", "npu_power_dissipation": [{"npu_id": 0, "power_dissipation": 85.4}, {"npu_id": 1, "power_dissipation": 90.1}, {"npu_id": 2, "power_dissipation": 93.1}, {"npu_id": 3, "power_dissipation": 88.1}, {"npu_id": 4, "power_dissipation": 92.9}, {"npu_id": 5, "power_dissipation": 93.8}, {"npu_id": 6, "power_dissipation": 93.2}, {"npu_id": 7, "power_dissipation": 90.8}], "device_mem_usage": [{"npu_id": 0, "mem_usage_percent": 6}, {"npu_id": 1, "mem_usage_percent": 6}, {"npu_id": 2, "mem_usage_percent": 6}, {"npu_id": 3, "mem_usage_percent": 6}, {"npu_id": 4, "mem_usage_percent": 6}, {"npu_id": 5, "mem_usage_percent": 6}, {"npu_id": 6, "mem_usage_percent": 6}, {"npu_id": 7, "mem_usage_percent": 6}]}

10
results/inference_Qwen-7B_8_gpu_50_step_20240919110723/all_results.json Normal file
View File

@ -0,0 +1,10 @@
{
"predict_bleu-4": 1.592524,
"predict_model_preparation_time": 0.0113,
"predict_rouge-1": 10.82511,
"predict_rouge-2": 2.886692,
"predict_rouge-l": 5.202822,
"predict_runtime": 1851.4287,
"predict_samples_per_second": 0.027,
"predict_steps_per_second": 0.014
}

50
results/inference_Qwen-7B_8_gpu_50_step_20240919110723/generated_predictions.jsonl Normal file
View File

File diff suppressed because one or more lines are too long

14
results/inference_Qwen-7B_8_gpu_50_step_20240919110723/inference_Qwen-7B_8_gpu_50_step_20240919110723.yaml Normal file
View File

@ -0,0 +1,14 @@
cutoff_len: 1024
ddp_timeout: 180000000
do_predict: true
eval_dataset: alpaca_gpt4_zh
include_tokens_per_second: true
max_samples: 50
model_name_or_path: ../../../models/qwen
output_dir: ./results/inference_Qwen-7B_8_gpu_50_step_20240919110723
overwrite_cache: true
overwrite_output_dir: true
per_device_eval_batch_size: 2
predict_with_generate: true
preprocessing_num_workers: 16
template: qwen

31
results/inference_Qwen-7B_8_gpu_50_step_20240919110723/log.txt Normal file
View File

@ -0,0 +1,31 @@
[2024-09-19 11:07:41,678] [INFO] [real_accelerator.py:203:get_accelerator] Setting ds_accelerator to npu (auto detect)
 [WARNING]  async_io requires the dev libaio .so object and headers but these were not found.
 [WARNING]  async_io: please install the libaio-devel package with yum
 [WARNING]  If libaio is already installed (perhaps from source), try setting the CFLAGS and LDFLAGS environment variables to where it can be found.
09/19/2024 11:07:46 - INFO - llamafactory.hparams.parser - Process rank: 0, device: npu:0, n_gpu: 1, distributed training: False, compute dtype: None
09/19/2024 11:07:47 - INFO - llamafactory.data.template - Add eos token: <|im_end|>
09/19/2024 11:07:47 - INFO - llamafactory.data.template - Add pad token: <|im_end|>
09/19/2024 11:07:47 - INFO - llamafactory.data.loader - Loading dataset llamafactory/alpaca_gpt4_zh...
eval example:
input_ids:
[151644, 8948, 198, 2610, 525, 264, 10950, 17847, 13, 151645, 198, 151644, 872, 198, 100662, 108136, 101124, 45139, 1773, 151645, 198, 151644, 77091, 198]
inputs:
<|im_start|>system
You are a helpful assistant.<|im_end|>
<|im_start|>user
保持健康的三个提示。<|im_end|>
<|im_start|>assistant
09/19/2024 11:10:55 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.
09/19/2024 11:13:13 - INFO - llamafactory.model.model_utils.attention - Using vanilla attention implementation.
09/19/2024 11:13:13 - INFO - llamafactory.model.loader - all params: 7,721,324,544
***** predict metrics *****
predict_bleu-4 = 1.5925
predict_model_preparation_time = 0.0113
predict_rouge-1 = 10.8251
predict_rouge-2 = 2.8867
predict_rouge-l = 5.2028
predict_runtime = 0:30:51.42
predict_samples_per_second = 0.027
predict_steps_per_second = 0.014
09/19/2024 11:44:05 - INFO - llamafactory.train.sft.trainer - Saving prediction results to ./results/inference_Qwen-7B_8_gpu_50_step_20240919110723/generated_predictions.jsonl

32
results/inference_Qwen-7B_8_gpu_50_step_20240919110723/npu_status_20240919110723.json Normal file
View File

@ -0,0 +1,32 @@
{"cur_time": "2024-09-19 11:07:35", "npu_power_dissipation": [{"npu_id": 0, "power_dissipation": 85.5}, {"npu_id": 1, "power_dissipation": 89.8}, {"npu_id": 2, "power_dissipation": 93.1}, {"npu_id": 3, "power_dissipation": 88.4}, {"npu_id": 4, "power_dissipation": 92.6}, {"npu_id": 5, "power_dissipation": 93.9}, {"npu_id": 6, "power_dissipation": 93.1}, {"npu_id": 7, "power_dissipation": 90.9}], "device_mem_usage": [{"npu_id": 0, "mem_usage_percent": 6}, {"npu_id": 1, "mem_usage_percent": 6}, {"npu_id": 2, "mem_usage_percent": 6}, {"npu_id": 3, "mem_usage_percent": 6}, {"npu_id": 4, "mem_usage_percent": 6}, {"npu_id": 5, "mem_usage_percent": 6}, {"npu_id": 6, "mem_usage_percent": 6}, {"npu_id": 7, "mem_usage_percent": 6}]}
{"cur_time": "2024-09-19 11:08:45", "npu_power_dissipation": [{"npu_id": 0, "power_dissipation": 85.7}, {"npu_id": 1, "power_dissipation": 90.1}, {"npu_id": 2, "power_dissipation": 93.0}, {"npu_id": 3, "power_dissipation": 88.3}, {"npu_id": 4, "power_dissipation": 93.1}, {"npu_id": 5, "power_dissipation": 93.6}, {"npu_id": 6, "power_dissipation": 92.8}, {"npu_id": 7, "power_dissipation": 90.7}], "device_mem_usage": [{"npu_id": 0, "mem_usage_percent": 6}, {"npu_id": 1, "mem_usage_percent": 6}, {"npu_id": 2, "mem_usage_percent": 6}, {"npu_id": 3, "mem_usage_percent": 6}, {"npu_id": 4, "mem_usage_percent": 6}, {"npu_id": 5, "mem_usage_percent": 6}, {"npu_id": 6, "mem_usage_percent": 6}, {"npu_id": 7, "mem_usage_percent": 6}]}
{"cur_time": "2024-09-19 11:09:55", "npu_power_dissipation": [{"npu_id": 0, "power_dissipation": 85.5}, {"npu_id": 1, "power_dissipation": 90.1}, {"npu_id": 2, "power_dissipation": 92.9}, {"npu_id": 3, "power_dissipation": 88.5}, {"npu_id": 4, "power_dissipation": 93.1}, {"npu_id": 5, "power_dissipation": 93.8}, {"npu_id": 6, "power_dissipation": 93.2}, {"npu_id": 7, "power_dissipation": 90.6}], "device_mem_usage": [{"npu_id": 0, "mem_usage_percent": 6}, {"npu_id": 1, "mem_usage_percent": 6}, {"npu_id": 2, "mem_usage_percent": 6}, {"npu_id": 3, "mem_usage_percent": 6}, {"npu_id": 4, "mem_usage_percent": 6}, {"npu_id": 5, "mem_usage_percent": 6}, {"npu_id": 6, "mem_usage_percent": 6}, {"npu_id": 7, "mem_usage_percent": 6}]}
{"cur_time": "2024-09-19 11:11:04", "npu_power_dissipation": [{"npu_id": 0, "power_dissipation": 85.6}, {"npu_id": 1, "power_dissipation": 89.6}, {"npu_id": 2, "power_dissipation": 93.1}, {"npu_id": 3, "power_dissipation": 88.0}, {"npu_id": 4, "power_dissipation": 92.7}, {"npu_id": 5, "power_dissipation": 93.7}, {"npu_id": 6, "power_dissipation": 92.9}, {"npu_id": 7, "power_dissipation": 91.4}], "device_mem_usage": [{"npu_id": 0, "mem_usage_percent": 6}, {"npu_id": 1, "mem_usage_percent": 6}, {"npu_id": 2, "mem_usage_percent": 6}, {"npu_id": 3, "mem_usage_percent": 6}, {"npu_id": 4, "mem_usage_percent": 6}, {"npu_id": 5, "mem_usage_percent": 6}, {"npu_id": 6, "mem_usage_percent": 6}, {"npu_id": 7, "mem_usage_percent": 6}]}
{"cur_time": "2024-09-19 11:12:15", "npu_power_dissipation": [{"npu_id": 0, "power_dissipation": 85.5}, {"npu_id": 1, "power_dissipation": 90.0}, {"npu_id": 2, "power_dissipation": 93.1}, {"npu_id": 3, "power_dissipation": 88.0}, {"npu_id": 4, "power_dissipation": 92.9}, {"npu_id": 5, "power_dissipation": 93.8}, {"npu_id": 6, "power_dissipation": 93.1}, {"npu_id": 7, "power_dissipation": 91.2}], "device_mem_usage": [{"npu_id": 0, "mem_usage_percent": 17}, {"npu_id": 1, "mem_usage_percent": 6}, {"npu_id": 2, "mem_usage_percent": 6}, {"npu_id": 3, "mem_usage_percent": 6}, {"npu_id": 4, "mem_usage_percent": 6}, {"npu_id": 5, "mem_usage_percent": 6}, {"npu_id": 6, "mem_usage_percent": 6}, {"npu_id": 7, "mem_usage_percent": 6}]}
{"cur_time": "2024-09-19 11:13:25", "npu_power_dissipation": [{"npu_id": 0, "power_dissipation": 121.2}, {"npu_id": 1, "power_dissipation": 89.9}, {"npu_id": 2, "power_dissipation": 93.3}, {"npu_id": 3, "power_dissipation": 88.2}, {"npu_id": 4, "power_dissipation": 93.0}, {"npu_id": 5, "power_dissipation": 93.6}, {"npu_id": 6, "power_dissipation": 93.2}, {"npu_id": 7, "power_dissipation": 90.6}], "device_mem_usage": [{"npu_id": 0, "mem_usage_percent": 29}, {"npu_id": 1, "mem_usage_percent": 6}, {"npu_id": 2, "mem_usage_percent": 6}, {"npu_id": 3, "mem_usage_percent": 6}, {"npu_id": 4, "mem_usage_percent": 6}, {"npu_id": 5, "mem_usage_percent": 6}, {"npu_id": 6, "mem_usage_percent": 6}, {"npu_id": 7, "mem_usage_percent": 6}]}
{"cur_time": "2024-09-19 11:14:34", "npu_power_dissipation": [{"npu_id": 0, "power_dissipation": 125.9}, {"npu_id": 1, "power_dissipation": 89.8}, {"npu_id": 2, "power_dissipation": 92.9}, {"npu_id": 3, "power_dissipation": 88.6}, {"npu_id": 4, "power_dissipation": 93.2}, {"npu_id": 5, "power_dissipation": 93.8}, {"npu_id": 6, "power_dissipation": 93.1}, {"npu_id": 7, "power_dissipation": 91.0}], "device_mem_usage": [{"npu_id": 0, "mem_usage_percent": 38}, {"npu_id": 1, "mem_usage_percent": 6}, {"npu_id": 2, "mem_usage_percent": 6}, {"npu_id": 3, "mem_usage_percent": 6}, {"npu_id": 4, "mem_usage_percent": 6}, {"npu_id": 5, "mem_usage_percent": 6}, {"npu_id": 6, "mem_usage_percent": 6}, {"npu_id": 7, "mem_usage_percent": 6}]}
{"cur_time": "2024-09-19 11:15:44", "npu_power_dissipation": [{"npu_id": 0, "power_dissipation": 122.3}, {"npu_id": 1, "power_dissipation": 90.3}, {"npu_id": 2, "power_dissipation": 93.1}, {"npu_id": 3, "power_dissipation": 88.9}, {"npu_id": 4, "power_dissipation": 93.0}, {"npu_id": 5, "power_dissipation": 93.5}, {"npu_id": 6, "power_dissipation": 92.6}, {"npu_id": 7, "power_dissipation": 91.6}], "device_mem_usage": [{"npu_id": 0, "mem_usage_percent": 38}, {"npu_id": 1, "mem_usage_percent": 6}, {"npu_id": 2, "mem_usage_percent": 6}, {"npu_id": 3, "mem_usage_percent": 6}, {"npu_id": 4, "mem_usage_percent": 6}, {"npu_id": 5, "mem_usage_percent": 6}, {"npu_id": 6, "mem_usage_percent": 6}, {"npu_id": 7, "mem_usage_percent": 6}]}
{"cur_time": "2024-09-19 11:16:54", "npu_power_dissipation": [{"npu_id": 0, "power_dissipation": 128.4}, {"npu_id": 1, "power_dissipation": 89.4}, {"npu_id": 2, "power_dissipation": 93.0}, {"npu_id": 3, "power_dissipation": 88.6}, {"npu_id": 4, "power_dissipation": 92.9}, {"npu_id": 5, "power_dissipation": 93.7}, {"npu_id": 6, "power_dissipation": 92.7}, {"npu_id": 7, "power_dissipation": 90.7}], "device_mem_usage": [{"npu_id": 0, "mem_usage_percent": 38}, {"npu_id": 1, "mem_usage_percent": 6}, {"npu_id": 2, "mem_usage_percent": 6}, {"npu_id": 3, "mem_usage_percent": 6}, {"npu_id": 4, "mem_usage_percent": 6}, {"npu_id": 5, "mem_usage_percent": 6}, {"npu_id": 6, "mem_usage_percent": 6}, {"npu_id": 7, "mem_usage_percent": 6}]}
{"cur_time": "2024-09-19 11:18:04", "npu_power_dissipation": [{"npu_id": 0, "power_dissipation": 126.2}, {"npu_id": 1, "power_dissipation": 90.1}, {"npu_id": 2, "power_dissipation": 93.1}, {"npu_id": 3, "power_dissipation": 88.3}, {"npu_id": 4, "power_dissipation": 93.0}, {"npu_id": 5, "power_dissipation": 93.9}, {"npu_id": 6, "power_dissipation": 93.0}, {"npu_id": 7, "power_dissipation": 91.0}], "device_mem_usage": [{"npu_id": 0, "mem_usage_percent": 38}, {"npu_id": 1, "mem_usage_percent": 6}, {"npu_id": 2, "mem_usage_percent": 6}, {"npu_id": 3, "mem_usage_percent": 6}, {"npu_id": 4, "mem_usage_percent": 6}, {"npu_id": 5, "mem_usage_percent": 6}, {"npu_id": 6, "mem_usage_percent": 6}, {"npu_id": 7, "mem_usage_percent": 6}]}
{"cur_time": "2024-09-19 11:19:14", "npu_power_dissipation": [{"npu_id": 0, "power_dissipation": 127.5}, {"npu_id": 1, "power_dissipation": 90.3}, {"npu_id": 2, "power_dissipation": 93.0}, {"npu_id": 3, "power_dissipation": 88.5}, {"npu_id": 4, "power_dissipation": 93.2}, {"npu_id": 5, "power_dissipation": 93.7}, {"npu_id": 6, "power_dissipation": 93.2}, {"npu_id": 7, "power_dissipation": 91.1}], "device_mem_usage": [{"npu_id": 0, "mem_usage_percent": 38}, {"npu_id": 1, "mem_usage_percent": 6}, {"npu_id": 2, "mem_usage_percent": 6}, {"npu_id": 3, "mem_usage_percent": 6}, {"npu_id": 4, "mem_usage_percent": 6}, {"npu_id": 5, "mem_usage_percent": 6}, {"npu_id": 6, "mem_usage_percent": 6}, {"npu_id": 7, "mem_usage_percent": 6}]}
{"cur_time": "2024-09-19 11:20:24", "npu_power_dissipation": [{"npu_id": 0, "power_dissipation": 126.5}, {"npu_id": 1, "power_dissipation": 89.4}, {"npu_id": 2, "power_dissipation": 93.1}, {"npu_id": 3, "power_dissipation": 88.6}, {"npu_id": 4, "power_dissipation": 92.9}, {"npu_id": 5, "power_dissipation": 93.5}, {"npu_id": 6, "power_dissipation": 93.4}, {"npu_id": 7, "power_dissipation": 91.2}], "device_mem_usage": [{"npu_id": 0, "mem_usage_percent": 38}, {"npu_id": 1, "mem_usage_percent": 6}, {"npu_id": 2, "mem_usage_percent": 6}, {"npu_id": 3, "mem_usage_percent": 6}, {"npu_id": 4, "mem_usage_percent": 6}, {"npu_id": 5, "mem_usage_percent": 6}, {"npu_id": 6, "mem_usage_percent": 6}, {"npu_id": 7, "mem_usage_percent": 6}]}
{"cur_time": "2024-09-19 11:21:34", "npu_power_dissipation": [{"npu_id": 0, "power_dissipation": 128.7}, {"npu_id": 1, "power_dissipation": 90.1}, {"npu_id": 2, "power_dissipation": 93.6}, {"npu_id": 3, "power_dissipation": 88.2}, {"npu_id": 4, "power_dissipation": 92.9}, {"npu_id": 5, "power_dissipation": 93.7}, {"npu_id": 6, "power_dissipation": 92.9}, {"npu_id": 7, "power_dissipation": 91.2}], "device_mem_usage": [{"npu_id": 0, "mem_usage_percent": 38}, {"npu_id": 1, "mem_usage_percent": 6}, {"npu_id": 2, "mem_usage_percent": 6}, {"npu_id": 3, "mem_usage_percent": 6}, {"npu_id": 4, "mem_usage_percent": 6}, {"npu_id": 5, "mem_usage_percent": 6}, {"npu_id": 6, "mem_usage_percent": 6}, {"npu_id": 7, "mem_usage_percent": 6}]}
{"cur_time": "2024-09-19 11:22:44", "npu_power_dissipation": [{"npu_id": 0, "power_dissipation": 125.1}, {"npu_id": 1, "power_dissipation": 89.5}, {"npu_id": 2, "power_dissipation": 92.9}, {"npu_id": 3, "power_dissipation": 87.8}, {"npu_id": 4, "power_dissipation": 92.7}, {"npu_id": 5, "power_dissipation": 93.7}, {"npu_id": 6, "power_dissipation": 93.2}, {"npu_id": 7, "power_dissipation": 90.8}], "device_mem_usage": [{"npu_id": 0, "mem_usage_percent": 38}, {"npu_id": 1, "mem_usage_percent": 6}, {"npu_id": 2, "mem_usage_percent": 6}, {"npu_id": 3, "mem_usage_percent": 6}, {"npu_id": 4, "mem_usage_percent": 6}, {"npu_id": 5, "mem_usage_percent": 6}, {"npu_id": 6, "mem_usage_percent": 6}, {"npu_id": 7, "mem_usage_percent": 6}]}
{"cur_time": "2024-09-19 11:23:54", "npu_power_dissipation": [{"npu_id": 0, "power_dissipation": 123.5}, {"npu_id": 1, "power_dissipation": 89.5}, {"npu_id": 2, "power_dissipation": 93.2}, {"npu_id": 3, "power_dissipation": 89.2}, {"npu_id": 4, "power_dissipation": 92.7}, {"npu_id": 5, "power_dissipation": 93.6}, {"npu_id": 6, "power_dissipation": 93.0}, {"npu_id": 7, "power_dissipation": 91.2}], "device_mem_usage": [{"npu_id": 0, "mem_usage_percent": 38}, {"npu_id": 1, "mem_usage_percent": 6}, {"npu_id": 2, "mem_usage_percent": 6}, {"npu_id": 3, "mem_usage_percent": 6}, {"npu_id": 4, "mem_usage_percent": 6}, {"npu_id": 5, "mem_usage_percent": 6}, {"npu_id": 6, "mem_usage_percent": 6}, {"npu_id": 7, "mem_usage_percent": 6}]}
{"cur_time": "2024-09-19 11:25:04", "npu_power_dissipation": [{"npu_id": 0, "power_dissipation": 121.4}, {"npu_id": 1, "power_dissipation": 90.5}, {"npu_id": 2, "power_dissipation": 93.2}, {"npu_id": 3, "power_dissipation": 88.2}, {"npu_id": 4, "power_dissipation": 92.8}, {"npu_id": 5, "power_dissipation": 93.8}, {"npu_id": 6, "power_dissipation": 92.6}, {"npu_id": 7, "power_dissipation": 90.7}], "device_mem_usage": [{"npu_id": 0, "mem_usage_percent": 38}, {"npu_id": 1, "mem_usage_percent": 6}, {"npu_id": 2, "mem_usage_percent": 6}, {"npu_id": 3, "mem_usage_percent": 6}, {"npu_id": 4, "mem_usage_percent": 6}, {"npu_id": 5, "mem_usage_percent": 6}, {"npu_id": 6, "mem_usage_percent": 6}, {"npu_id": 7, "mem_usage_percent": 6}]}
{"cur_time": "2024-09-19 11:26:13", "npu_power_dissipation": [{"npu_id": 0, "power_dissipation": 131.7}, {"npu_id": 1, "power_dissipation": 89.6}, {"npu_id": 2, "power_dissipation": 93.2}, {"npu_id": 3, "power_dissipation": 88.4}, {"npu_id": 4, "power_dissipation": 92.8}, {"npu_id": 5, "power_dissipation": 94.0}, {"npu_id": 6, "power_dissipation": 92.7}, {"npu_id": 7, "power_dissipation": 90.8}], "device_mem_usage": [{"npu_id": 0, "mem_usage_percent": 38}, {"npu_id": 1, "mem_usage_percent": 6}, {"npu_id": 2, "mem_usage_percent": 6}, {"npu_id": 3, "mem_usage_percent": 6}, {"npu_id": 4, "mem_usage_percent": 6}, {"npu_id": 5, "mem_usage_percent": 6}, {"npu_id": 6, "mem_usage_percent": 6}, {"npu_id": 7, "mem_usage_percent": 6}]}
{"cur_time": "2024-09-19 11:27:23", "npu_power_dissipation": [{"npu_id": 0, "power_dissipation": 127.3}, {"npu_id": 1, "power_dissipation": 90.2}, {"npu_id": 2, "power_dissipation": 93.0}, {"npu_id": 3, "power_dissipation": 88.4}, {"npu_id": 4, "power_dissipation": 93.1}, {"npu_id": 5, "power_dissipation": 93.8}, {"npu_id": 6, "power_dissipation": 93.2}, {"npu_id": 7, "power_dissipation": 91.1}], "device_mem_usage": [{"npu_id": 0, "mem_usage_percent": 38}, {"npu_id": 1, "mem_usage_percent": 6}, {"npu_id": 2, "mem_usage_percent": 6}, {"npu_id": 3, "mem_usage_percent": 6}, {"npu_id": 4, "mem_usage_percent": 6}, {"npu_id": 5, "mem_usage_percent": 6}, {"npu_id": 6, "mem_usage_percent": 6}, {"npu_id": 7, "mem_usage_percent": 6}]}
{"cur_time": "2024-09-19 11:28:33", "npu_power_dissipation": [{"npu_id": 0, "power_dissipation": 126.8}, {"npu_id": 1, "power_dissipation": 90.3}, {"npu_id": 2, "power_dissipation": 93.2}, {"npu_id": 3, "power_dissipation": 88.4}, {"npu_id": 4, "power_dissipation": 93.1}, {"npu_id": 5, "power_dissipation": 93.8}, {"npu_id": 6, "power_dissipation": 93.1}, {"npu_id": 7, "power_dissipation": 90.9}], "device_mem_usage": [{"npu_id": 0, "mem_usage_percent": 38}, {"npu_id": 1, "mem_usage_percent": 6}, {"npu_id": 2, "mem_usage_percent": 6}, {"npu_id": 3, "mem_usage_percent": 6}, {"npu_id": 4, "mem_usage_percent": 6}, {"npu_id": 5, "mem_usage_percent": 6}, {"npu_id": 6, "mem_usage_percent": 6}, {"npu_id": 7, "mem_usage_percent": 6}]}
{"cur_time": "2024-09-19 11:29:43", "npu_power_dissipation": [{"npu_id": 0, "power_dissipation": 122.6}, {"npu_id": 1, "power_dissipation": 89.8}, {"npu_id": 2, "power_dissipation": 93.2}, {"npu_id": 3, "power_dissipation": 88.2}, {"npu_id": 4, "power_dissipation": 92.8}, {"npu_id": 5, "power_dissipation": 93.6}, {"npu_id": 6, "power_dissipation": 92.8}, {"npu_id": 7, "power_dissipation": 90.8}], "device_mem_usage": [{"npu_id": 0, "mem_usage_percent": 38}, {"npu_id": 1, "mem_usage_percent": 6}, {"npu_id": 2, "mem_usage_percent": 6}, {"npu_id": 3, "mem_usage_percent": 6}, {"npu_id": 4, "mem_usage_percent": 6}, {"npu_id": 5, "mem_usage_percent": 6}, {"npu_id": 6, "mem_usage_percent": 6}, {"npu_id": 7, "mem_usage_percent": 6}]}
{"cur_time": "2024-09-19 11:30:53", "npu_power_dissipation": [{"npu_id": 0, "power_dissipation": 125.5}, {"npu_id": 1, "power_dissipation": 89.9}, {"npu_id": 2, "power_dissipation": 93.2}, {"npu_id": 3, "power_dissipation": 88.1}, {"npu_id": 4, "power_dissipation": 93.0}, {"npu_id": 5, "power_dissipation": 93.5}, {"npu_id": 6, "power_dissipation": 92.9}, {"npu_id": 7, "power_dissipation": 91.0}], "device_mem_usage": [{"npu_id": 0, "mem_usage_percent": 38}, {"npu_id": 1, "mem_usage_percent": 6}, {"npu_id": 2, "mem_usage_percent": 6}, {"npu_id": 3, "mem_usage_percent": 6}, {"npu_id": 4, "mem_usage_percent": 6}, {"npu_id": 5, "mem_usage_percent": 6}, {"npu_id": 6, "mem_usage_percent": 6}, {"npu_id": 7, "mem_usage_percent": 6}]}
{"cur_time": "2024-09-19 11:32:03", "npu_power_dissipation": [{"npu_id": 0, "power_dissipation": 124.9}, {"npu_id": 1, "power_dissipation": 90.4}, {"npu_id": 2, "power_dissipation": 93.0}, {"npu_id": 3, "power_dissipation": 88.0}, {"npu_id": 4, "power_dissipation": 92.9}, {"npu_id": 5, "power_dissipation": 93.7}, {"npu_id": 6, "power_dissipation": 92.9}, {"npu_id": 7, "power_dissipation": 90.8}], "device_mem_usage": [{"npu_id": 0, "mem_usage_percent": 38}, {"npu_id": 1, "mem_usage_percent": 6}, {"npu_id": 2, "mem_usage_percent": 6}, {"npu_id": 3, "mem_usage_percent": 6}, {"npu_id": 4, "mem_usage_percent": 6}, {"npu_id": 5, "mem_usage_percent": 6}, {"npu_id": 6, "mem_usage_percent": 6}, {"npu_id": 7, "mem_usage_percent": 6}]}
{"cur_time": "2024-09-19 11:33:13", "npu_power_dissipation": [{"npu_id": 0, "power_dissipation": 124.1}, {"npu_id": 1, "power_dissipation": 89.6}, {"npu_id": 2, "power_dissipation": 93.2}, {"npu_id": 3, "power_dissipation": 88.7}, {"npu_id": 4, "power_dissipation": 93.2}, {"npu_id": 5, "power_dissipation": 93.6}, {"npu_id": 6, "power_dissipation": 92.6}, {"npu_id": 7, "power_dissipation": 91.0}], "device_mem_usage": [{"npu_id": 0, "mem_usage_percent": 38}, {"npu_id": 1, "mem_usage_percent": 6}, {"npu_id": 2, "mem_usage_percent": 6}, {"npu_id": 3, "mem_usage_percent": 6}, {"npu_id": 4, "mem_usage_percent": 6}, {"npu_id": 5, "mem_usage_percent": 6}, {"npu_id": 6, "mem_usage_percent": 6}, {"npu_id": 7, "mem_usage_percent": 6}]}
{"cur_time": "2024-09-19 11:34:23", "npu_power_dissipation": [{"npu_id": 0, "power_dissipation": 121.8}, {"npu_id": 1, "power_dissipation": 89.4}, {"npu_id": 2, "power_dissipation": 93.2}, {"npu_id": 3, "power_dissipation": 88.4}, {"npu_id": 4, "power_dissipation": 92.8}, {"npu_id": 5, "power_dissipation": 93.6}, {"npu_id": 6, "power_dissipation": 92.9}, {"npu_id": 7, "power_dissipation": 91.0}], "device_mem_usage": [{"npu_id": 0, "mem_usage_percent": 38}, {"npu_id": 1, "mem_usage_percent": 6}, {"npu_id": 2, "mem_usage_percent": 6}, {"npu_id": 3, "mem_usage_percent": 6}, {"npu_id": 4, "mem_usage_percent": 6}, {"npu_id": 5, "mem_usage_percent": 6}, {"npu_id": 6, "mem_usage_percent": 6}, {"npu_id": 7, "mem_usage_percent": 6}]}
{"cur_time": "2024-09-19 11:35:32", "npu_power_dissipation": [{"npu_id": 0, "power_dissipation": 121.5}, {"npu_id": 1, "power_dissipation": 89.4}, {"npu_id": 2, "power_dissipation": 93.0}, {"npu_id": 3, "power_dissipation": 88.2}, {"npu_id": 4, "power_dissipation": 92.8}, {"npu_id": 5, "power_dissipation": 93.9}, {"npu_id": 6, "power_dissipation": 92.9}, {"npu_id": 7, "power_dissipation": 91.2}], "device_mem_usage": [{"npu_id": 0, "mem_usage_percent": 38}, {"npu_id": 1, "mem_usage_percent": 6}, {"npu_id": 2, "mem_usage_percent": 6}, {"npu_id": 3, "mem_usage_percent": 6}, {"npu_id": 4, "mem_usage_percent": 6}, {"npu_id": 5, "mem_usage_percent": 6}, {"npu_id": 6, "mem_usage_percent": 6}, {"npu_id": 7, "mem_usage_percent": 6}]}
{"cur_time": "2024-09-19 11:36:42", "npu_power_dissipation": [{"npu_id": 0, "power_dissipation": 128.8}, {"npu_id": 1, "power_dissipation": 90.8}, {"npu_id": 2, "power_dissipation": 93.3}, {"npu_id": 3, "power_dissipation": 88.4}, {"npu_id": 4, "power_dissipation": 93.2}, {"npu_id": 5, "power_dissipation": 93.9}, {"npu_id": 6, "power_dissipation": 92.8}, {"npu_id": 7, "power_dissipation": 91.0}], "device_mem_usage": [{"npu_id": 0, "mem_usage_percent": 38}, {"npu_id": 1, "mem_usage_percent": 6}, {"npu_id": 2, "mem_usage_percent": 6}, {"npu_id": 3, "mem_usage_percent": 6}, {"npu_id": 4, "mem_usage_percent": 6}, {"npu_id": 5, "mem_usage_percent": 6}, {"npu_id": 6, "mem_usage_percent": 6}, {"npu_id": 7, "mem_usage_percent": 6}]}
{"cur_time": "2024-09-19 11:37:52", "npu_power_dissipation": [{"npu_id": 0, "power_dissipation": 122.8}, {"npu_id": 1, "power_dissipation": 90.1}, {"npu_id": 2, "power_dissipation": 93.2}, {"npu_id": 3, "power_dissipation": 88.8}, {"npu_id": 4, "power_dissipation": 92.9}, {"npu_id": 5, "power_dissipation": 94.0}, {"npu_id": 6, "power_dissipation": 92.7}, {"npu_id": 7, "power_dissipation": 90.4}], "device_mem_usage": [{"npu_id": 0, "mem_usage_percent": 38}, {"npu_id": 1, "mem_usage_percent": 6}, {"npu_id": 2, "mem_usage_percent": 6}, {"npu_id": 3, "mem_usage_percent": 6}, {"npu_id": 4, "mem_usage_percent": 6}, {"npu_id": 5, "mem_usage_percent": 6}, {"npu_id": 6, "mem_usage_percent": 6}, {"npu_id": 7, "mem_usage_percent": 6}]}
{"cur_time": "2024-09-19 11:39:02", "npu_power_dissipation": [{"npu_id": 0, "power_dissipation": 110.2}, {"npu_id": 1, "power_dissipation": 90.1}, {"npu_id": 2, "power_dissipation": 93.1}, {"npu_id": 3, "power_dissipation": 88.6}, {"npu_id": 4, "power_dissipation": 93.1}, {"npu_id": 5, "power_dissipation": 93.7}, {"npu_id": 6, "power_dissipation": 92.7}, {"npu_id": 7, "power_dissipation": 91.1}], "device_mem_usage": [{"npu_id": 0, "mem_usage_percent": 38}, {"npu_id": 1, "mem_usage_percent": 6}, {"npu_id": 2, "mem_usage_percent": 6}, {"npu_id": 3, "mem_usage_percent": 6}, {"npu_id": 4, "mem_usage_percent": 6}, {"npu_id": 5, "mem_usage_percent": 6}, {"npu_id": 6, "mem_usage_percent": 6}, {"npu_id": 7, "mem_usage_percent": 6}]}
{"cur_time": "2024-09-19 11:40:12", "npu_power_dissipation": [{"npu_id": 0, "power_dissipation": 126.3}, {"npu_id": 1, "power_dissipation": 89.8}, {"npu_id": 2, "power_dissipation": 92.9}, {"npu_id": 3, "power_dissipation": 87.9}, {"npu_id": 4, "power_dissipation": 93.0}, {"npu_id": 5, "power_dissipation": 94.0}, {"npu_id": 6, "power_dissipation": 92.8}, {"npu_id": 7, "power_dissipation": 91.1}], "device_mem_usage": [{"npu_id": 0, "mem_usage_percent": 38}, {"npu_id": 1, "mem_usage_percent": 6}, {"npu_id": 2, "mem_usage_percent": 6}, {"npu_id": 3, "mem_usage_percent": 6}, {"npu_id": 4, "mem_usage_percent": 6}, {"npu_id": 5, "mem_usage_percent": 6}, {"npu_id": 6, "mem_usage_percent": 6}, {"npu_id": 7, "mem_usage_percent": 6}]}
{"cur_time": "2024-09-19 11:41:22", "npu_power_dissipation": [{"npu_id": 0, "power_dissipation": 124.0}, {"npu_id": 1, "power_dissipation": 89.8}, {"npu_id": 2, "power_dissipation": 93.2}, {"npu_id": 3, "power_dissipation": 88.5}, {"npu_id": 4, "power_dissipation": 93.1}, {"npu_id": 5, "power_dissipation": 93.6}, {"npu_id": 6, "power_dissipation": 92.8}, {"npu_id": 7, "power_dissipation": 90.6}], "device_mem_usage": [{"npu_id": 0, "mem_usage_percent": 38}, {"npu_id": 1, "mem_usage_percent": 6}, {"npu_id": 2, "mem_usage_percent": 6}, {"npu_id": 3, "mem_usage_percent": 6}, {"npu_id": 4, "mem_usage_percent": 6}, {"npu_id": 5, "mem_usage_percent": 6}, {"npu_id": 6, "mem_usage_percent": 6}, {"npu_id": 7, "mem_usage_percent": 6}]}
{"cur_time": "2024-09-19 11:42:32", "npu_power_dissipation": [{"npu_id": 0, "power_dissipation": 125.1}, {"npu_id": 1, "power_dissipation": 89.7}, {"npu_id": 2, "power_dissipation": 93.2}, {"npu_id": 3, "power_dissipation": 88.5}, {"npu_id": 4, "power_dissipation": 92.6}, {"npu_id": 5, "power_dissipation": 93.5}, {"npu_id": 6, "power_dissipation": 92.9}, {"npu_id": 7, "power_dissipation": 91.1}], "device_mem_usage": [{"npu_id": 0, "mem_usage_percent": 38}, {"npu_id": 1, "mem_usage_percent": 6}, {"npu_id": 2, "mem_usage_percent": 6}, {"npu_id": 3, "mem_usage_percent": 6}, {"npu_id": 4, "mem_usage_percent": 6}, {"npu_id": 5, "mem_usage_percent": 6}, {"npu_id": 6, "mem_usage_percent": 6}, {"npu_id": 7, "mem_usage_percent": 6}]}
{"cur_time": "2024-09-19 11:43:42", "npu_power_dissipation": [{"npu_id": 0, "power_dissipation": 125.4}, {"npu_id": 1, "power_dissipation": 90.3}, {"npu_id": 2, "power_dissipation": 93.0}, {"npu_id": 3, "power_dissipation": 88.2}, {"npu_id": 4, "power_dissipation": 93.0}, {"npu_id": 5, "power_dissipation": 94.0}, {"npu_id": 6, "power_dissipation": 92.9}, {"npu_id": 7, "power_dissipation": 91.1}], "device_mem_usage": [{"npu_id": 0, "mem_usage_percent": 38}, {"npu_id": 1, "mem_usage_percent": 6}, {"npu_id": 2, "mem_usage_percent": 6}, {"npu_id": 3, "mem_usage_percent": 6}, {"npu_id": 4, "mem_usage_percent": 6}, {"npu_id": 5, "mem_usage_percent": 6}, {"npu_id": 6, "mem_usage_percent": 6}, {"npu_id": 7, "mem_usage_percent": 6}]}

10
results/inference_Qwen-7B_8_gpu_50_step_20240919110723/predict_results.json Normal file
View File

@ -0,0 +1,10 @@
{
"predict_bleu-4": 1.592524,
"predict_model_preparation_time": 0.0113,
"predict_rouge-1": 10.82511,
"predict_rouge-2": 2.886692,
"predict_rouge-l": 5.202822,
"predict_runtime": 1851.4287,
"predict_samples_per_second": 0.027,
"predict_steps_per_second": 0.014
}

5
results/inference_Qwen-7B_8_gpu_50_step_20240919110723/trainer_log.jsonl Normal file
View File

@ -0,0 +1,5 @@
{"current_steps": 5, "total_steps": 25, "percentage": 20.0, "elapsed_time": "0:04:52", "remaining_time": "0:19:29"}
{"current_steps": 10, "total_steps": 25, "percentage": 40.0, "elapsed_time": "0:10:57", "remaining_time": "0:16:26"}
{"current_steps": 15, "total_steps": 25, "percentage": 60.0, "elapsed_time": "0:17:07", "remaining_time": "0:11:25"}
{"current_steps": 20, "total_steps": 25, "percentage": 80.0, "elapsed_time": "0:23:18", "remaining_time": "0:05:49"}
{"current_steps": 25, "total_steps": 25, "percentage": 100.0, "elapsed_time": "0:29:29", "remaining_time": "0:00:00"}

32
results/inference_Qwen-7B_8_gpu_50_step_20240919110723/trainer_state.json Normal file
View File

@ -0,0 +1,32 @@
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": null,
"eval_steps": 500,
"global_step": 0,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [],
"logging_steps": 500,
"max_steps": 0,
"num_input_tokens_seen": 0,
"num_train_epochs": 0,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": false,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 0,
"train_batch_size": null,
"trial_name": null,
"trial_params": null
}