developer_uid: leosheng
submission_id: alexxi19-ft-v1-nemo-base-dpo_v5
model_name: alexxi19-ft-v1-nemo-base-dpo_v5
model_group: alexxi19/ft-v1-nemo-base
status: torndown
timestamp: 2025-02-22T08:03:55+00:00
num_battles: 8635
num_wins: 3982
celo_rating: 1247.51
family_friendly_score: 0.5558000000000001
family_friendly_standard_error: 0.0070268963276826565
submission_type: basic
model_repo: alexxi19/ft-v1-nemo-base-dpo
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.5979499988922546, 'latency_mean': 1.6723100006580354, 'latency_p50': 1.6754975318908691, 'latency_p90': 1.8436369180679322}, {'batch_size': 3, 'throughput': 1.0815118355548576, 'latency_mean': 2.7638932526111604, 'latency_p50': 2.7769731283187866, 'latency_p90': 3.0376907348632813}, {'batch_size': 5, 'throughput': 1.3107718758450677, 'latency_mean': 3.7986009025573733, 'latency_p50': 3.8267436027526855, 'latency_p90': 4.17763545513153}, {'batch_size': 6, 'throughput': 1.3741259119221252, 'latency_mean': 4.349434372186661, 'latency_p50': 4.352740526199341, 'latency_p90': 4.9155831098556515}, {'batch_size': 8, 'throughput': 1.4477429528366712, 'latency_mean': 5.491958048343658, 'latency_p50': 5.486425757408142, 'latency_p90': 6.205685997009278}, {'batch_size': 10, 'throughput': 1.4611096410501223, 'latency_mean': 6.796295084953308, 'latency_p50': 6.780749797821045, 'latency_p90': 7.701131296157837}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: alexxi19-ft-v1-nemo-base-dpo_v5
is_internal_developer: False
language_model: alexxi19/ft-v1-nemo-base-dpo
model_size: 13B
ranking_group: single
throughput_3p7s: 1.3
us_pacific_date: 2025-02-22
win_ratio: 0.46114649681528663
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': False}
Resubmit model
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name alexxi19-ft-v1-nemo-base-dpo-v5-mkmlizer
Waiting for job on alexxi19-ft-v1-nemo-base-dpo-v5-mkmlizer to finish
alexxi19-ft-v1-nemo-base-dpo-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexxi19-ft-v1-nemo-base-dpo-v5-mkmlizer: ║ _____ __ __ ║
alexxi19-ft-v1-nemo-base-dpo-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
alexxi19-ft-v1-nemo-base-dpo-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
alexxi19-ft-v1-nemo-base-dpo-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
alexxi19-ft-v1-nemo-base-dpo-v5-mkmlizer: ║ /___/ ║
alexxi19-ft-v1-nemo-base-dpo-v5-mkmlizer: ║ ║
alexxi19-ft-v1-nemo-base-dpo-v5-mkmlizer: ║ Version: 0.12.8 ║
alexxi19-ft-v1-nemo-base-dpo-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
alexxi19-ft-v1-nemo-base-dpo-v5-mkmlizer: ║ https://mk1.ai ║
alexxi19-ft-v1-nemo-base-dpo-v5-mkmlizer: ║ ║
alexxi19-ft-v1-nemo-base-dpo-v5-mkmlizer: ║ The license key for the current software has been verified as ║
alexxi19-ft-v1-nemo-base-dpo-v5-mkmlizer: ║ belonging to: ║
alexxi19-ft-v1-nemo-base-dpo-v5-mkmlizer: ║ ║
alexxi19-ft-v1-nemo-base-dpo-v5-mkmlizer: ║ Chai Research Corp. ║
alexxi19-ft-v1-nemo-base-dpo-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
alexxi19-ft-v1-nemo-base-dpo-v5-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
alexxi19-ft-v1-nemo-base-dpo-v5-mkmlizer: ║ ║
alexxi19-ft-v1-nemo-base-dpo-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexxi19-ft-v1-nemo-base-dpo-v5-mkmlizer: Downloaded to shared memory in 49.760s
alexxi19-ft-v1-nemo-base-dpo-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpedroc30k, device:0
alexxi19-ft-v1-nemo-base-dpo-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexxi19-ft-v1-nemo-base-dpo-v5-mkmlizer: quantized model in 37.366s
alexxi19-ft-v1-nemo-base-dpo-v5-mkmlizer: Processed model alexxi19/ft-v1-nemo-base-dpo in 87.127s
alexxi19-ft-v1-nemo-base-dpo-v5-mkmlizer: creating bucket guanaco-mkml-models
alexxi19-ft-v1-nemo-base-dpo-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexxi19-ft-v1-nemo-base-dpo-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-base-dpo-v5
alexxi19-ft-v1-nemo-base-dpo-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-base-dpo-v5/config.json
alexxi19-ft-v1-nemo-base-dpo-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-base-dpo-v5/special_tokens_map.json
alexxi19-ft-v1-nemo-base-dpo-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-base-dpo-v5/tokenizer_config.json
alexxi19-ft-v1-nemo-base-dpo-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-base-dpo-v5/tokenizer.json
alexxi19-ft-v1-nemo-base-dpo-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-base-dpo-v5/flywheel_model.0.safetensors
alexxi19-ft-v1-nemo-base-dpo-v5-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:12, 28.61it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:07, 45.00it/s] Loading 0: 5%|▍ | 17/363 [00:00<00:08, 42.51it/s] Loading 0: 6%|▌ | 22/363 [00:00<00:08, 41.69it/s] Loading 0: 7%|▋ | 27/363 [00:00<00:08, 41.66it/s] Loading 0: 9%|▉ | 32/363 [00:00<00:09, 33.28it/s] Loading 0: 11%|█ | 39/363 [00:00<00:07, 41.27it/s] Loading 0: 12%|█▏ | 44/363 [00:01<00:07, 40.77it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:07, 40.43it/s] Loading 0: 15%|█▍ | 54/363 [00:01<00:07, 42.43it/s] Loading 0: 16%|█▋ | 59/363 [00:01<00:06, 43.53it/s] Loading 0: 18%|█▊ | 64/363 [00:01<00:12, 24.58it/s] Loading 0: 20%|█▉ | 71/363 [00:01<00:09, 31.74it/s] Loading 0: 21%|██ | 76/363 [00:02<00:08, 33.28it/s] Loading 0: 22%|██▏ | 81/363 [00:02<00:08, 34.60it/s] Loading 0: 24%|██▎ | 86/363 [00:02<00:07, 36.80it/s] Loading 0: 25%|██▌ | 91/363 [00:02<00:08, 31.73it/s] Loading 0: 27%|██▋ | 98/363 [00:02<00:06, 38.14it/s] Loading 0: 28%|██▊ | 103/363 [00:02<00:06, 37.73it/s] Loading 0: 30%|██▉ | 108/363 [00:02<00:06, 39.48it/s] Loading 0: 31%|███ | 113/363 [00:03<00:07, 33.68it/s] Loading 0: 33%|███▎ | 118/363 [00:03<00:07, 33.40it/s] Loading 0: 34%|███▍ | 125/363 [00:03<00:05, 39.86it/s] Loading 0: 36%|███▌ | 130/363 [00:03<00:05, 39.68it/s] Loading 0: 37%|███▋ | 135/363 [00:03<00:05, 39.59it/s] Loading 0: 39%|███▊ | 140/363 [00:03<00:05, 41.20it/s] Loading 0: 40%|███▉ | 145/363 [00:04<00:08, 25.39it/s] Loading 0: 41%|████ | 149/363 [00:04<00:08, 25.52it/s] Loading 0: 43%|████▎ | 156/363 [00:04<00:06, 32.37it/s] Loading 0: 44%|████▍ | 160/363 [00:04<00:06, 32.28it/s] Loading 0: 45%|████▌ | 165/363 [00:04<00:05, 34.96it/s] Loading 0: 47%|████▋ | 169/363 [00:04<00:05, 34.55it/s] Loading 0: 48%|████▊ | 174/363 [00:04<00:05, 37.11it/s] Loading 0: 49%|████▉ | 178/363 [00:05<00:05, 35.67it/s] Loading 0: 50%|█████ | 183/363 [00:05<00:04, 37.61it/s] Loading 0: 52%|█████▏ | 187/363 [00:05<00:04, 36.25it/s] Loading 0: 53%|█████▎ | 192/363 [00:05<00:04, 38.54it/s] Loading 0: 54%|█████▍ | 196/363 [00:05<00:04, 36.90it/s] Loading 0: 55%|█████▌ | 201/363 [00:05<00:04, 38.69it/s] Loading 0: 56%|█████▋ | 205/363 [00:05<00:04, 36.25it/s] Loading 0: 58%|█████▊ | 210/363 [00:05<00:03, 38.32it/s] Loading 0: 59%|█████▉ | 214/363 [00:05<00:03, 37.32it/s] Loading 0: 60%|██████ | 218/363 [00:06<00:03, 36.76it/s] Loading 0: 61%|██████▏ | 223/363 [00:06<00:05, 26.96it/s] Loading 0: 63%|██████▎ | 227/363 [00:06<00:04, 28.05it/s] Loading 0: 64%|██████▎ | 231/363 [00:06<00:04, 27.85it/s] Loading 0: 65%|██████▌ | 237/363 [00:06<00:03, 32.84it/s] Loading 0: 66%|██████▋ | 241/363 [00:06<00:03, 31.99it/s] Loading 0: 68%|██████▊ | 246/363 [00:07<00:03, 35.24it/s] Loading 0: 69%|██████▉ | 250/363 [00:07<00:03, 34.45it/s] Loading 0: 70%|███████ | 255/363 [00:07<00:02, 36.99it/s] Loading 0: 71%|███████▏ | 259/363 [00:07<00:02, 35.79it/s] Loading 0: 73%|███████▎ | 264/363 [00:07<00:02, 38.25it/s] Loading 0: 74%|███████▍ | 268/363 [00:07<00:02, 35.41it/s] Loading 0: 75%|███████▌ | 273/363 [00:07<00:02, 37.21it/s] Loading 0: 76%|███████▋ | 277/363 [00:07<00:02, 35.47it/s] Loading 0: 78%|███████▊ | 282/363 [00:07<00:02, 37.17it/s] Loading 0: 79%|███████▉ | 286/363 [00:08<00:02, 35.59it/s] Loading 0: 80%|████████ | 291/363 [00:08<00:01, 37.41it/s] Loading 0: 81%|████████▏ | 295/363 [00:08<00:01, 36.60it/s] Loading 0: 82%|████████▏ | 299/363 [00:08<00:01, 35.76it/s] Loading 0: 84%|████████▎ | 304/363 [00:15<00:27, 2.16it/s] Loading 0: 85%|████████▍ | 307/363 [00:15<00:20, 2.70it/s] Loading 0: 86%|████████▌ | 312/363 [00:15<00:12, 3.97it/s] Loading 0: 88%|████████▊ | 319/363 [00:15<00:06, 6.44it/s] Loading 0: 89%|████████▉ | 323/363 [00:15<00:04, 8.08it/s] Loading 0: 90%|█████████ | 328/363 [00:15<00:03, 10.88it/s] Loading 0: 92%|█████████▏| 333/363 [00:15<00:02, 14.00it/s] Loading 0: 93%|█████████▎| 338/363 [00:15<00:01, 17.56it/s] Loading 0: 94%|█████████▍| 343/363 [00:16<00:00, 21.59it/s] Loading 0: 96%|█████████▌| 348/363 [00:16<00:00, 22.10it/s] Loading 0: 98%|█████████▊| 355/363 [00:16<00:00, 29.38it/s] Loading 0: 99%|█████████▉| 360/363 [00:16<00:00, 32.43it/s]
Job alexxi19-ft-v1-nemo-base-dpo-v5-mkmlizer completed after 114.11s with status: succeeded
Stopping job with name alexxi19-ft-v1-nemo-base-dpo-v5-mkmlizer
Pipeline stage MKMLizer completed in 114.60s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service alexxi19-ft-v1-nemo-base-dpo-v5
Waiting for inference service alexxi19-ft-v1-nemo-base-dpo-v5 to be ready
Inference service alexxi19-ft-v1-nemo-base-dpo-v5 ready after 231.1387596130371s
Pipeline stage MKMLDeployer completed in 231.67s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.467097043991089s
Received healthy response to inference request in 1.8389463424682617s
Received healthy response to inference request in 1.563066005706787s
Received healthy response to inference request in 1.6316258907318115s
Received healthy response to inference request in 1.547861099243164s
5 requests
0 failed requests
5th percentile: 1.5509020805358886
10th percentile: 1.5539430618286132
20th percentile: 1.5600250244140625
30th percentile: 1.576777982711792
40th percentile: 1.6042019367218017
50th percentile: 1.6316258907318115
60th percentile: 1.7145540714263916
70th percentile: 1.7974822521209717
80th percentile: 1.9645764827728271
90th percentile: 2.215836763381958
95th percentile: 2.3414669036865234
99th percentile: 2.441971015930176
mean time: 1.8097192764282226
Pipeline stage StressChecker completed in 10.38s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.67s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.69s
Shutdown handler de-registered
alexxi19-ft-v1-nemo-base-dpo_v5 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service alexxi19-ft-v1-nemo-base-dpo-v5-profiler
Waiting for inference service alexxi19-ft-v1-nemo-base-dpo-v5-profiler to be ready
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4170.54s
Shutdown handler de-registered
alexxi19-ft-v1-nemo-base-dpo_v5 status is now inactive due to auto deactivation removed underperforming models
alexxi19-ft-v1-nemo-base-dpo_v5 status is now torndown due to DeploymentManager action