chaiml-mistral-nemo-dpo-_9616

developer_uid: azuruce

submission_id: chaiml-mistral-nemo-dpo-_9616_v2

model_name: chaiml-mistral-nemo-dpo-_9616_v2

model_group: ChaiML/mistral_nemo_dpo_

status: inactive

timestamp: 2024-12-12T18:03:13+00:00

num_battles: 12122

num_wins: 5911

celo_rating: 1252.88

family_friendly_score: 0.5800000000000001

family_friendly_standard_error: 0.006979971346646059

submission_type: basic

model_repo: ChaiML/mistral_nemo_dpo_baseline_albert_241210_20k_v5

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6381795829045387, 'latency_mean': 1.566901193857193, 'latency_p50': 1.5603872537612915, 'latency_p90': 1.738725471496582}, {'batch_size': 3, 'throughput': 1.262961069913305, 'latency_mean': 2.369664785861969, 'latency_p50': 2.369754672050476, 'latency_p90': 2.5801558971405028}, {'batch_size': 5, 'throughput': 1.59361531057107, 'latency_mean': 3.1178812170028687, 'latency_p50': 3.1222686767578125, 'latency_p90': 3.4867688179016114}, {'batch_size': 6, 'throughput': 1.718887184490291, 'latency_mean': 3.4723239278793336, 'latency_p50': 3.4804292917251587, 'latency_p90': 3.9594863414764405}, {'batch_size': 8, 'throughput': 1.861763030559373, 'latency_mean': 4.270443196296692, 'latency_p50': 4.2745184898376465, 'latency_p90': 4.842871117591858}, {'batch_size': 10, 'throughput': 1.940127611687541, 'latency_mean': 5.122069903612137, 'latency_p50': 5.087543606758118, 'latency_p90': 5.777979755401612}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-mistral-nemo-dpo-_9616_v2

is_internal_developer: True

language_model: ChaiML/mistral_nemo_dpo_baseline_albert_241210_20k_v5

model_size: 13B

ranking_group: single

throughput_3p7s: 1.78

us_pacific_date: 2024-12-12

win_ratio: 0.487625804322719

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '####', 'Bot:', 'User:', 'You:', '<|im_end|>', '<|eot_id|>'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', '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 chaiml-mistral-nemo-dpo-9616-v2-mkmlizer
Waiting for job on chaiml-mistral-nemo-dpo-9616-v2-mkmlizer to finish
chaiml-mistral-nemo-dpo-9616-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-dpo-9616-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral-nemo-dpo-9616-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral-nemo-dpo-9616-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral-nemo-dpo-9616-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral-nemo-dpo-9616-v2-mkmlizer: ║       /___/                                                         ║
chaiml-mistral-nemo-dpo-9616-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-9616-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-mistral-nemo-dpo-9616-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral-nemo-dpo-9616-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-nemo-dpo-9616-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-9616-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-nemo-dpo-9616-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-nemo-dpo-9616-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-9616-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-nemo-dpo-9616-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-nemo-dpo-9616-v2-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-mistral-nemo-dpo-9616-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-9616-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-dpo-9616-v2-mkmlizer: Downloaded to shared memory in 33.191s
chaiml-mistral-nemo-dpo-9616-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpuyf511fe, device:0
chaiml-mistral-nemo-dpo-9616-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-nemo-dpo-9616-v2-mkmlizer: quantized model in 37.328s
chaiml-mistral-nemo-dpo-9616-v2-mkmlizer: Processed model ChaiML/mistral_nemo_dpo_baseline_albert_241210_20k_v5 in 70.519s
chaiml-mistral-nemo-dpo-9616-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-dpo-9616-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-dpo-9616-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-9616-v2
chaiml-mistral-nemo-dpo-9616-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-9616-v2/config.json
chaiml-mistral-nemo-dpo-9616-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-9616-v2/special_tokens_map.json
chaiml-mistral-nemo-dpo-9616-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-9616-v2/tokenizer_config.json
chaiml-mistral-nemo-dpo-9616-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-9616-v2/tokenizer.json
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-mistral-nemo-dpo-9616-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-9616-v2/flywheel_model.0.safetensors
chaiml-mistral-nemo-dpo-9616-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 27.29it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 46.64it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 43.18it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 41.41it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 47.80it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 46.61it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 44.75it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 49.95it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 47.48it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:06, 48.03it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:10, 27.50it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:08, 33.83it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:08, 35.52it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:07, 36.32it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 41.90it/s]
Loading 0:  26%|██▌       | 95/363 [00:02<00:06, 42.96it/s]
Loading 0:  28%|██▊       | 100/363 [00:02<00:07, 36.89it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:06, 41.40it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:05, 44.82it/s]
Loading 0:  32%|███▏      | 117/363 [00:02<00:05, 41.14it/s]
Loading 0:  34%|███▎      | 122/363 [00:02<00:05, 43.14it/s]
Loading 0:  35%|███▍      | 127/363 [00:03<00:06, 37.27it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 45.03it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:04, 45.90it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:07, 27.79it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 27.30it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:06, 34.11it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 34.56it/s]
Loading 0:  45%|████▌     | 165/363 [00:04<00:05, 34.90it/s]
Loading 0:  47%|████▋     | 169/363 [00:04<00:05, 34.39it/s]
Loading 0:  48%|████▊     | 174/363 [00:04<00:05, 37.26it/s]
Loading 0:  49%|████▉     | 178/363 [00:04<00:05, 35.90it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:04, 39.58it/s]
Loading 0:  52%|█████▏    | 190/363 [00:04<00:04, 40.09it/s]
Loading 0:  54%|█████▎    | 195/363 [00:05<00:04, 40.72it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:03, 45.17it/s]
Loading 0:  57%|█████▋    | 206/363 [00:05<00:03, 45.01it/s]
Loading 0:  58%|█████▊    | 211/363 [00:05<00:03, 45.97it/s]
Loading 0:  60%|█████▉    | 217/363 [00:05<00:03, 44.60it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:04, 31.91it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 31.52it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:04, 31.29it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 37.32it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 38.89it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 40.32it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 42.40it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:02, 36.37it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 43.72it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 41.98it/s]
Loading 0:  75%|███████▌  | 274/363 [00:07<00:02, 41.43it/s]
Loading 0:  77%|███████▋  | 279/363 [00:07<00:01, 42.54it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 37.50it/s]
Loading 0:  80%|████████  | 292/363 [00:07<00:01, 45.31it/s]
Loading 0:  82%|████████▏ | 298/363 [00:07<00:01, 44.48it/s]
Loading 0:  84%|████████▎ | 304/363 [00:14<00:21,  2.73it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:16,  3.43it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:11,  4.38it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:06,  7.12it/s]
Loading 0:  90%|████████▉ | 326/363 [00:15<00:03,  9.59it/s]
Loading 0:  91%|█████████ | 331/363 [00:15<00:02, 12.12it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:01, 16.91it/s]
Loading 0:  95%|█████████▍| 344/363 [00:15<00:00, 20.58it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 23.72it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 30.07it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 32.94it/s]
                                                            
Job chaiml-mistral-nemo-dpo-9616-v2-mkmlizer completed after 95.32s with status: succeeded
Stopping job with name chaiml-mistral-nemo-dpo-9616-v2-mkmlizer
Pipeline stage MKMLizer completed in 95.82s
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 chaiml-mistral-nemo-dpo-9616-v2
Waiting for inference service chaiml-mistral-nemo-dpo-9616-v2 to be ready
Inference service chaiml-mistral-nemo-dpo-9616-v2 ready after 180.67198729515076s
Pipeline stage MKMLDeployer completed in 181.22s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.4526135921478271s
Received healthy response to inference request in 1.0627832412719727s
Received healthy response to inference request in 1.0815870761871338s
Received healthy response to inference request in 0.6133072376251221s
Received healthy response to inference request in 5.023229598999023s
5 requests
0 failed requests
5th percentile: 0.7032024383544921
10th percentile: 0.7930976390838623
20th percentile: 0.9728880405426026
30th percentile: 1.0665440082550048
40th percentile: 1.0740655422210694
50th percentile: 1.0815870761871338
60th percentile: 1.2299976825714112
70th percentile: 1.3784082889556883
80th percentile: 2.166736793518067
90th percentile: 3.5949831962585455
95th percentile: 4.309106397628783
99th percentile: 4.880404958724975
mean time: 1.8467041492462157
Pipeline stage StressChecker completed in 10.64s
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 2.44s
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 2.36s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_9616_v2 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 chaiml-mistral-nemo-dpo-9616-v2-profiler
Waiting for inference service chaiml-mistral-nemo-dpo-9616-v2-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 2377.22s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_9616_v2 status is now inactive due to auto deactivation removed underperforming models