cloudyu-chaiml-nemo-dpo-v6

developer_uid: cloudyu

submission_id: cloudyu-chaiml-nemo-dpo-v6_v11

model_name: cloudyu-chaiml-nemo-dpo-v6_v11

model_group: cloudyu/ChaiML-Nemo-DPO-

status: inactive

timestamp: 2024-12-03T02:34:46+00:00

num_battles: 16491

num_wins: 7246

celo_rating: 1221.0

family_friendly_score: 0.5722

family_friendly_standard_error: 0.006996958767921961

submission_type: basic

model_repo: cloudyu/ChaiML-Nemo-DPO-V6

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6160552889728558, 'latency_mean': 1.6231600487232207, 'latency_p50': 1.6207908391952515, 'latency_p90': 1.7951817512512207}, {'batch_size': 3, 'throughput': 1.1410791549596924, 'latency_mean': 2.6247011041641235, 'latency_p50': 2.6334136724472046, 'latency_p90': 2.8675929069519044}, {'batch_size': 5, 'throughput': 1.3799094943022274, 'latency_mean': 3.606271332502365, 'latency_p50': 3.6219708919525146, 'latency_p90': 4.027841544151306}, {'batch_size': 6, 'throughput': 1.4648606611691866, 'latency_mean': 4.06987167596817, 'latency_p50': 4.078609943389893, 'latency_p90': 4.591513919830322}, {'batch_size': 8, 'throughput': 1.5161693881564329, 'latency_mean': 5.239200060367584, 'latency_p50': 5.253686904907227, 'latency_p90': 5.922393822669983}, {'batch_size': 10, 'throughput': 1.553898582338141, 'latency_mean': 6.375976648330688, 'latency_p50': 6.365588307380676, 'latency_p90': 7.255023550987244}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: cloudyu-chaiml-nemo-dpo-v6_v11

is_internal_developer: False

language_model: cloudyu/ChaiML-Nemo-DPO-V6

model_size: 13B

ranking_group: single

throughput_3p7s: 1.41

us_pacific_date: 2024-12-02

win_ratio: 0.4393911830695531

generation_params: {'temperature': 0.96, 'top_p': 0.05, 'min_p': 0.05, '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-v6-v11-mkmlizer
Waiting for job on cloudyu-chaiml-nemo-dpo-v6-v11-mkmlizer to finish
cloudyu-chaiml-nemo-dpo-v6-v11-mkmlizer: Downloaded to shared memory in 57.593s
cloudyu-chaiml-nemo-dpo-v6-v11-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmprmyhpoir, device:0
cloudyu-chaiml-nemo-dpo-v6-v11-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-chaiml-nemo-dpo-v6-v11-mkmlizer: quantized model in 35.754s
cloudyu-chaiml-nemo-dpo-v6-v11-mkmlizer: Processed model cloudyu/ChaiML-Nemo-DPO-V6 in 93.348s
cloudyu-chaiml-nemo-dpo-v6-v11-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-chaiml-nemo-dpo-v6-v11-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-chaiml-nemo-dpo-v6-v11-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v11
cloudyu-chaiml-nemo-dpo-v6-v11-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v11/config.json
cloudyu-chaiml-nemo-dpo-v6-v11-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v11/special_tokens_map.json
cloudyu-chaiml-nemo-dpo-v6-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v11/tokenizer_config.json
cloudyu-chaiml-nemo-dpo-v6-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v11/tokenizer.json
cloudyu-chaiml-nemo-dpo-v6-v11-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v11/flywheel_model.0.safetensors
cloudyu-chaiml-nemo-dpo-v6-v11-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 28.38it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 49.29it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 44.66it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 43.01it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 48.93it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 44.50it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 43.90it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 49.94it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 46.51it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 35.36it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 35.98it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 40.57it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:06, 41.56it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 41.81it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:05, 47.35it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:05, 45.44it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:05, 43.69it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:05, 49.95it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:05, 45.70it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:05, 44.50it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:04, 48.57it/s]
Loading 0:  36%|███▋      | 132/363 [00:02<00:05, 45.79it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:05, 44.11it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 34.69it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 35.16it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 34.50it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:05, 40.97it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:04, 41.02it/s]
Loading 0:  46%|████▋     | 168/363 [00:03<00:04, 41.31it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:03, 47.10it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:03, 45.89it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:03, 44.40it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 49.05it/s]
Loading 0:  55%|█████▍    | 198/363 [00:04<00:03, 49.14it/s]
Loading 0:  56%|█████▌    | 203/363 [00:04<00:03, 41.12it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:03, 48.58it/s]
Loading 0:  60%|█████▉    | 217/363 [00:04<00:03, 46.19it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:03, 36.07it/s]
Loading 0:  63%|██████▎   | 228/363 [00:05<00:03, 35.22it/s]
Loading 0:  64%|██████▍   | 232/363 [00:05<00:03, 36.03it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 40.09it/s]
Loading 0:  67%|██████▋   | 244/363 [00:05<00:02, 40.65it/s]
Loading 0:  69%|██████▊   | 249/363 [00:05<00:02, 40.55it/s]
Loading 0:  71%|███████   | 256/363 [00:05<00:02, 45.43it/s]
Loading 0:  72%|███████▏  | 262/363 [00:06<00:02, 44.46it/s]
Loading 0:  74%|███████▎  | 267/363 [00:06<00:02, 43.41it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:01, 47.28it/s]
Loading 0:  77%|███████▋  | 280/363 [00:06<00:01, 44.46it/s]
Loading 0:  79%|███████▊  | 285/363 [00:06<00:01, 42.81it/s]
Loading 0:  80%|████████  | 291/363 [00:06<00:01, 45.55it/s]
Loading 0:  82%|████████▏ | 296/363 [00:06<00:01, 45.30it/s]
Loading 0:  83%|████████▎ | 303/363 [00:07<00:01, 46.02it/s]
Loading 0:  85%|████████▍ | 308/363 [00:13<00:20,  2.67it/s]
Loading 0:  86%|████████▌ | 312/363 [00:13<00:15,  3.39it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:07,  5.48it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:04,  7.44it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:03,  9.53it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 13.51it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:01, 16.84it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 19.99it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 26.02it/s]
Loading 0: 100%|█████████▉| 362/363 [00:14<00:00, 28.25it/s]
                                                            
Job cloudyu-chaiml-nemo-dpo-v6-v11-mkmlizer completed after 124.01s with status: succeeded
Stopping job with name cloudyu-chaiml-nemo-dpo-v6-v11-mkmlizer
Pipeline stage MKMLizer completed in 124.49s
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-v6-v11
Waiting for inference service cloudyu-chaiml-nemo-dpo-v6-v11 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service cloudyu-chaiml-nemo-dpo-v6-v11 ready after 140.65301823616028s
Pipeline stage MKMLDeployer completed in 141.18s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4212543964385986s
Received healthy response to inference request in 1.7503130435943604s
Received healthy response to inference request in 1.658484935760498s
Received healthy response to inference request in 1.815342903137207s
Received healthy response to inference request in 1.6723332405090332s
5 requests
0 failed requests
5th percentile: 1.661254596710205
10th percentile: 1.664024257659912
20th percentile: 1.6695635795593262
30th percentile: 1.6879292011260987
40th percentile: 1.7191211223602294
50th percentile: 1.7503130435943604
60th percentile: 1.776324987411499
70th percentile: 1.8023369312286377
80th percentile: 1.9365252017974854
90th percentile: 2.178889799118042
95th percentile: 2.3000720977783202
99th percentile: 2.397017936706543
mean time: 1.8635457038879395
Pipeline stage StressChecker completed in 10.60s
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 2.17s
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 2.03s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v6_v11 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 0.10s
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 cloudyu-chaiml-nemo-dpo-v6-v11-profiler
Waiting for inference service cloudyu-chaiml-nemo-dpo-v6-v11-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3174.06s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v6_v11 status is now inactive due to auto deactivation removed underperforming models