cloudyu-chaiml-nemo-dpo-v7

developer_uid: cloudyu

submission_id: cloudyu-chaiml-nemo-dpo-v7_v9

model_name: cloudyu-chaiml-nemo-dpo-v7_v7

model_group: cloudyu/ChaiML-Nemo-DPO-

status: inactive

timestamp: 2024-12-03T23:56:34+00:00

num_battles: 13095

num_wins: 6711

celo_rating: 1272.0

family_friendly_score: 0.5568

family_friendly_standard_error: 0.007025293730514049

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': 0.6118282685999886, 'latency_mean': 1.6343779492378234, 'latency_p50': 1.6315878629684448, 'latency_p90': 1.7937003374099731}, {'batch_size': 3, 'throughput': 1.1395209985410066, 'latency_mean': 2.6206315422058104, 'latency_p50': 2.6070988178253174, 'latency_p90': 2.8631388902664185}, {'batch_size': 5, 'throughput': 1.3751370533432115, 'latency_mean': 3.627817634344101, 'latency_p50': 3.634147882461548, 'latency_p90': 3.9982117652893066}, {'batch_size': 6, 'throughput': 1.429466796221138, 'latency_mean': 4.182575939893723, 'latency_p50': 4.194812655448914, 'latency_p90': 4.714811229705811}, {'batch_size': 8, 'throughput': 1.5156493884276714, 'latency_mean': 5.227564748525619, 'latency_p50': 5.193113327026367, 'latency_p90': 6.000126695632934}, {'batch_size': 10, 'throughput': 1.5517784049675938, 'latency_mean': 6.409228011369705, 'latency_p50': 6.468030571937561, 'latency_p90': 7.185372018814087}]

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: 1.39

us_pacific_date: 2024-12-03

win_ratio: 0.5124856815578465

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-v9-mkmlizer
Waiting for job on cloudyu-chaiml-nemo-dpo-v7-v9-mkmlizer to finish
cloudyu-chaiml-nemo-dpo-v7-v9-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-chaiml-nemo-dpo-v7-v9-mkmlizer: ║     _____            __           __                                ║
cloudyu-chaiml-nemo-dpo-v7-v9-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-chaiml-nemo-dpo-v7-v9-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-chaiml-nemo-dpo-v7-v9-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-chaiml-nemo-dpo-v7-v9-mkmlizer: ║       /___/                                                         ║
cloudyu-chaiml-nemo-dpo-v7-v9-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v7-v9-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-chaiml-nemo-dpo-v7-v9-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-chaiml-nemo-dpo-v7-v9-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-chaiml-nemo-dpo-v7-v9-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v7-v9-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-chaiml-nemo-dpo-v7-v9-mkmlizer: ║  belonging to:                                                      ║
cloudyu-chaiml-nemo-dpo-v7-v9-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v7-v9-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-chaiml-nemo-dpo-v7-v9-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-chaiml-nemo-dpo-v7-v9-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-chaiml-nemo-dpo-v7-v9-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v7-v9-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-chaiml-nemo-dpo-v7-v9-mkmlizer: Downloaded to shared memory in 52.038s
cloudyu-chaiml-nemo-dpo-v7-v9-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp1vicwxda, device:0
cloudyu-chaiml-nemo-dpo-v7-v9-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-chaiml-nemo-dpo-v7-v9-mkmlizer: quantized model in 38.142s
cloudyu-chaiml-nemo-dpo-v7-v9-mkmlizer: Processed model cloudyu/ChaiML-Nemo-DPO-V7 in 90.180s
cloudyu-chaiml-nemo-dpo-v7-v9-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-chaiml-nemo-dpo-v7-v9-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-chaiml-nemo-dpo-v7-v9-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v7-v9
cloudyu-chaiml-nemo-dpo-v7-v9-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v7-v9/config.json
cloudyu-chaiml-nemo-dpo-v7-v9-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v7-v9/special_tokens_map.json
cloudyu-chaiml-nemo-dpo-v7-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v7-v9/tokenizer_config.json
cloudyu-chaiml-nemo-dpo-v7-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v7-v9/tokenizer.json
cloudyu-chaiml-nemo-dpo-v7-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v7-v9/flywheel_model.0.safetensors
cloudyu-chaiml-nemo-dpo-v7-v9-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 26.49it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 45.00it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:07, 44.93it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:09, 34.35it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:07, 43.00it/s]
Loading 0:  10%|▉         | 35/363 [00:00<00:07, 41.55it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:07, 41.15it/s]
Loading 0:  12%|█▏        | 45/363 [00:01<00:07, 41.98it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:09, 33.75it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:07, 38.53it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:11, 26.14it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:11, 26.33it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:09, 32.13it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:08, 32.99it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:07, 36.75it/s]
Loading 0:  23%|██▎       | 85/363 [00:02<00:07, 37.10it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:07, 38.73it/s]
Loading 0:  26%|██▌       | 95/363 [00:02<00:06, 40.83it/s]
Loading 0:  28%|██▊       | 100/363 [00:02<00:07, 33.25it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:06, 38.04it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:05, 42.53it/s]
Loading 0:  32%|███▏      | 117/363 [00:03<00:06, 40.64it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:05, 42.25it/s]
Loading 0:  35%|███▍      | 127/363 [00:03<00:06, 34.57it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:05, 41.04it/s]
Loading 0:  38%|███▊      | 139/363 [00:03<00:05, 40.96it/s]
Loading 0:  40%|███▉      | 144/363 [00:04<00:08, 24.75it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:07, 27.21it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:06, 34.49it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 35.74it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 37.71it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 40.20it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 34.61it/s]
Loading 0:  50%|█████     | 183/363 [00:05<00:04, 41.00it/s]
Loading 0:  52%|█████▏    | 188/363 [00:05<00:04, 40.78it/s]
Loading 0:  53%|█████▎    | 193/363 [00:05<00:04, 41.28it/s]
Loading 0:  55%|█████▍    | 198/363 [00:05<00:03, 42.77it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:04, 33.28it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 39.91it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 39.10it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 41.03it/s]
Loading 0:  62%|██████▏   | 225/363 [00:06<00:05, 24.63it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 26.78it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 33.84it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 34.59it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:03, 35.63it/s]
Loading 0:  69%|██████▉   | 252/363 [00:07<00:02, 38.06it/s]
Loading 0:  71%|███████   | 257/363 [00:07<00:03, 31.42it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 37.84it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 37.12it/s]
Loading 0:  75%|███████▌  | 274/363 [00:07<00:02, 37.68it/s]
Loading 0:  77%|███████▋  | 279/363 [00:07<00:02, 39.53it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 32.91it/s]
Loading 0:  80%|████████  | 291/363 [00:08<00:01, 39.52it/s]
Loading 0:  82%|████████▏ | 296/363 [00:08<00:01, 39.26it/s]
Loading 0:  83%|████████▎ | 301/363 [00:08<00:01, 40.93it/s]
Loading 0:  84%|████████▍ | 306/363 [00:15<00:23,  2.41it/s]
Loading 0:  85%|████████▌ | 310/363 [00:15<00:17,  3.12it/s]
Loading 0:  87%|████████▋ | 314/363 [00:15<00:12,  4.08it/s]
Loading 0:  88%|████████▊ | 319/363 [00:15<00:07,  5.74it/s]
Loading 0:  89%|████████▉ | 323/363 [00:15<00:05,  7.37it/s]
Loading 0:  90%|█████████ | 328/363 [00:15<00:03, 10.14it/s]
Loading 0:  91%|█████████▏| 332/363 [00:15<00:02, 12.50it/s]
Loading 0:  93%|█████████▎| 337/363 [00:16<00:01, 16.48it/s]
Loading 0:  94%|█████████▍| 342/363 [00:16<00:01, 20.10it/s]
Loading 0:  96%|█████████▌| 347/363 [00:16<00:00, 23.87it/s]
Loading 0:  97%|█████████▋| 352/363 [00:16<00:00, 27.79it/s]
Loading 0:  98%|█████████▊| 357/363 [00:16<00:00, 26.26it/s]
                                                            
Job cloudyu-chaiml-nemo-dpo-v7-v9-mkmlizer completed after 114.46s with status: succeeded
Stopping job with name cloudyu-chaiml-nemo-dpo-v7-v9-mkmlizer
Pipeline stage MKMLizer completed in 115.39s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cloudyu-chaiml-nemo-dpo-v7-v9
Waiting for inference service cloudyu-chaiml-nemo-dpo-v7-v9 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-v7-v9 ready after 140.71605396270752s
Pipeline stage MKMLDeployer completed in 141.22s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1743459701538086s
Received healthy response to inference request in 1.702807903289795s
Received healthy response to inference request in 1.7625906467437744s
Received healthy response to inference request in 1.7744781970977783s
Received healthy response to inference request in 1.874359130859375s
5 requests
0 failed requests
5th percentile: 1.714764451980591
10th percentile: 1.7267210006713867
20th percentile: 1.7506340980529784
30th percentile: 1.7649681568145752
40th percentile: 1.7697231769561768
50th percentile: 1.7744781970977783
60th percentile: 1.814430570602417
70th percentile: 1.8543829441070556
80th percentile: 1.9343564987182618
90th percentile: 2.054351234436035
95th percentile: 2.1143486022949216
99th percentile: 2.1623464965820314
mean time: 1.8577163696289063
Pipeline stage StressChecker completed in 10.80s
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 2.60s
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 2.24s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v7_v9 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 0.12s
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-v7-v9-profiler
Waiting for inference service cloudyu-chaiml-nemo-dpo-v7-v9-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 3637.11s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v7_v9 status is now inactive due to auto deactivation removed underperforming models