developer_uid: cloudyu
submission_id: cloudyu-chaiml-nemo-dpo-v7_v7
model_name: cloudyu-chaiml-nemo-dpo-v7_v7
model_group: cloudyu/ChaiML-Nemo-DPO-
status: inactive
timestamp: 2024-12-03T09:02:39+00:00
num_battles: 13906
num_wins: 7130
celo_rating: 1274.03
family_friendly_score: 0.5596
family_friendly_standard_error: 0.0070206529610856
submission_type: basic
model_repo: cloudyu/ChaiML-Nemo-DPO-V7
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6023492387770825, 'latency_mean': 1.6600994741916657, 'latency_p50': 1.653707504272461, 'latency_p90': 1.8379626750946045}, {'batch_size': 3, 'throughput': 1.1016840397142127, 'latency_mean': 2.715997499227524, 'latency_p50': 2.710150361061096, 'latency_p90': 2.9911635160446166}, {'batch_size': 5, 'throughput': 1.3218504142198988, 'latency_mean': 3.7666901099681853, 'latency_p50': 3.7411850690841675, 'latency_p90': 4.270422458648682}, {'batch_size': 6, 'throughput': 1.3791197655736034, 'latency_mean': 4.324531168937683, 'latency_p50': 4.358944416046143, 'latency_p90': 4.858091568946838}, {'batch_size': 8, 'throughput': 1.4554308137290721, 'latency_mean': 5.471309616565704, 'latency_p50': 5.523176670074463, 'latency_p90': 6.1011751890182495}, {'batch_size': 10, 'throughput': 1.4949444608952256, 'latency_mean': 6.649377405643463, 'latency_p50': 6.672138929367065, 'latency_p90': 7.455443096160889}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: cloudyu-chaiml-nemo-dpo-v7_v7
is_internal_developer: False
language_model: cloudyu/ChaiML-Nemo-DPO-V7
model_size: 13B
ranking_group: single
throughput_3p7s: 1.32
us_pacific_date: 2024-12-03
win_ratio: 0.5127283187113476
generation_params: {'temperature': 0.99, 'top_p': 0.99, 'min_p': 0.01, 'top_k': 80, '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': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{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 cloudyu-chaiml-nemo-dpo-v7-v7-mkmlizer
Waiting for job on cloudyu-chaiml-nemo-dpo-v7-v7-mkmlizer to finish
cloudyu-chaiml-nemo-dpo-v7-v7-mkmlizer: Downloaded to shared memory in 47.465s
cloudyu-chaiml-nemo-dpo-v7-v7-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmppk683oyt, device:0
cloudyu-chaiml-nemo-dpo-v7-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-chaiml-nemo-dpo-v7-v7-mkmlizer: quantized model in 35.656s
cloudyu-chaiml-nemo-dpo-v7-v7-mkmlizer: Processed model cloudyu/ChaiML-Nemo-DPO-V7 in 83.121s
cloudyu-chaiml-nemo-dpo-v7-v7-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-chaiml-nemo-dpo-v7-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-chaiml-nemo-dpo-v7-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v7-v7
cloudyu-chaiml-nemo-dpo-v7-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v7-v7/config.json
cloudyu-chaiml-nemo-dpo-v7-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v7-v7/special_tokens_map.json
cloudyu-chaiml-nemo-dpo-v7-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v7-v7/tokenizer_config.json
cloudyu-chaiml-nemo-dpo-v7-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v7-v7/tokenizer.json
cloudyu-chaiml-nemo-dpo-v7-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v7-v7/flywheel_model.0.safetensors
cloudyu-chaiml-nemo-dpo-v7-v7-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 28.40it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 49.67it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 48.32it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:06, 50.02it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 46.65it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:05, 54.64it/s]
Loading 0:  13%|█▎        | 46/363 [00:00<00:06, 51.92it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:06, 50.14it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:05, 54.61it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 34.06it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 40.02it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:06, 41.62it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 42.15it/s]
Loading 0:  25%|██▍       | 90/363 [00:01<00:05, 46.94it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:05, 46.16it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:05, 45.05it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:04, 51.22it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:05, 46.39it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:05, 43.72it/s]
Loading 0:  34%|███▍      | 125/363 [00:02<00:04, 47.65it/s]
Loading 0:  36%|███▌      | 130/363 [00:02<00:05, 45.72it/s]
Loading 0:  37%|███▋      | 135/363 [00:02<00:04, 46.75it/s]
Loading 0:  39%|███▉      | 141/363 [00:03<00:04, 46.24it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 32.27it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 31.75it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:05, 38.71it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:04, 40.16it/s]
Loading 0:  46%|████▋     | 168/363 [00:03<00:04, 41.15it/s]
Loading 0:  48%|████▊     | 175/363 [00:03<00:04, 46.46it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:04, 45.15it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:03, 44.31it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 49.40it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 45.33it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 43.72it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:03, 49.02it/s]
Loading 0:  60%|█████▉    | 217/363 [00:04<00:03, 47.29it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:03, 35.97it/s]
Loading 0:  63%|██████▎   | 228/363 [00:05<00:04, 32.97it/s]
Loading 0:  64%|██████▍   | 232/363 [00:05<00:03, 32.76it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 37.61it/s]
Loading 0:  67%|██████▋   | 244/363 [00:05<00:03, 39.40it/s]
Loading 0:  69%|██████▊   | 249/363 [00:05<00:02, 40.00it/s]
Loading 0:  71%|███████   | 256/363 [00:05<00:02, 45.34it/s]
Loading 0:  72%|███████▏  | 262/363 [00:06<00:02, 44.50it/s]
Loading 0:  74%|███████▎  | 267/363 [00:06<00:02, 44.41it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:01, 48.51it/s]
Loading 0:  77%|███████▋  | 280/363 [00:06<00:01, 46.73it/s]
Loading 0:  79%|███████▊  | 285/363 [00:06<00:01, 46.04it/s]
Loading 0:  80%|████████  | 292/363 [00:06<00:01, 50.00it/s]
Loading 0:  82%|████████▏ | 298/363 [00:06<00:01, 47.87it/s]
Loading 0:  84%|████████▎ | 304/363 [00:13<00:20,  2.85it/s]
Loading 0:  85%|████████▍ | 308/363 [00:13<00:15,  3.56it/s]
Loading 0:  86%|████████▌ | 312/363 [00:13<00:11,  4.54it/s]
Loading 0:  88%|████████▊ | 320/363 [00:13<00:05,  7.34it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:03,  9.80it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:02, 12.34it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 17.05it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:00, 20.62it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 23.48it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 29.65it/s]
Loading 0:  99%|█████████▉| 361/363 [00:14<00:00, 32.64it/s]
                                                            

Job cloudyu-chaiml-nemo-dpo-v7-v7-mkmlizer completed after 113.66s with status: succeeded
Stopping job with name cloudyu-chaiml-nemo-dpo-v7-v7-mkmlizer
Pipeline stage MKMLizer completed in 114.74s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cloudyu-chaiml-nemo-dpo-v7-v7
Waiting for inference service cloudyu-chaiml-nemo-dpo-v7-v7 to be ready
Inference service cloudyu-chaiml-nemo-dpo-v7-v7 ready after 150.5002191066742s
Pipeline stage MKMLDeployer completed in 151.03s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1075267791748047s
Received healthy response to inference request in 1.755964756011963s
Received healthy response to inference request in 1.779911994934082s
Received healthy response to inference request in 2.118518114089966s
Received healthy response to inference request in 1.665632963180542s
5 requests
0 failed requests
5th percentile: 1.6836993217468261
10th percentile: 1.7017656803131103
20th percentile: 1.7378983974456788
30th percentile: 1.7607542037963868
40th percentile: 1.7703330993652344
50th percentile: 1.779911994934082
60th percentile: 1.9109579086303712
70th percentile: 2.04200382232666
80th percentile: 2.1097250461578367
90th percentile: 2.1141215801239013
95th percentile: 2.1163198471069338
99th percentile: 2.1180784606933596
mean time: 1.8855109214782715
Pipeline stage StressChecker completed in 11.67s
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 2.29s
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 2.09s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v7_v7 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 3167.12s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v7_v7 status is now inactive due to auto deactivation removed underperforming models