chaiml-mistral-nemo-dpo-_1412

developer_uid: azuruce

submission_id: chaiml-mistral-nemo-dpo-_1412_v2

model_name: chaiml-mistral-nemo-dpo-_1412_v2

model_group: ChaiML/mistral_nemo_dpo_

status: inactive

timestamp: 2024-12-19T09:25:28+00:00

num_battles: 12444

num_wins: 6100

celo_rating: 1257.16

family_friendly_score: 0.5778

family_friendly_standard_error: 0.006984943235273999

submission_type: basic

model_repo: ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-4992

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6363337564016497, 'latency_mean': 1.5714231419563294, 'latency_p50': 1.5795648097991943, 'latency_p90': 1.7333555698394776}, {'batch_size': 3, 'throughput': 1.2599056601216063, 'latency_mean': 2.37470263004303, 'latency_p50': 2.4033501148223877, 'latency_p90': 2.597274398803711}, {'batch_size': 5, 'throughput': 1.6078214560806765, 'latency_mean': 3.098768665790558, 'latency_p50': 3.1037687063217163, 'latency_p90': 3.4345755577087402}, {'batch_size': 6, 'throughput': 1.706949578140021, 'latency_mean': 3.4794349133968354, 'latency_p50': 3.4816980361938477, 'latency_p90': 3.8874770402908325}, {'batch_size': 8, 'throughput': 1.8842212022279368, 'latency_mean': 4.215754648447037, 'latency_p50': 4.2255295515060425, 'latency_p90': 4.7560369014739985}, {'batch_size': 10, 'throughput': 1.958909279438002, 'latency_mean': 5.055743745565414, 'latency_p50': 5.114397644996643, 'latency_p90': 5.757452273368836}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-mistral-nemo-dpo-_1412_v2

is_internal_developer: True

language_model: ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-4992

model_size: 13B

ranking_group: single

throughput_3p7s: 1.78

us_pacific_date: 2024-12-19

win_ratio: 0.49019607843137253

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-1412-v2-mkmlizer
Waiting for job on chaiml-mistral-nemo-dpo-1412-v2-mkmlizer to finish
chaiml-mistral-nemo-dpo-1412-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-dpo-1412-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral-nemo-dpo-1412-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral-nemo-dpo-1412-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral-nemo-dpo-1412-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral-nemo-dpo-1412-v2-mkmlizer: ║       /___/                                                         ║
chaiml-mistral-nemo-dpo-1412-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-1412-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-mistral-nemo-dpo-1412-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral-nemo-dpo-1412-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-nemo-dpo-1412-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-1412-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-nemo-dpo-1412-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-nemo-dpo-1412-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-1412-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-nemo-dpo-1412-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-nemo-dpo-1412-v2-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-mistral-nemo-dpo-1412-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-1412-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-dpo-1412-v2-mkmlizer: Downloaded to shared memory in 32.428s
chaiml-mistral-nemo-dpo-1412-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpuc0qzycz, device:0
chaiml-mistral-nemo-dpo-1412-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-nemo-dpo-1412-v2-mkmlizer: quantized model in 35.924s
chaiml-mistral-nemo-dpo-1412-v2-mkmlizer: Processed model ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-4992 in 68.352s
chaiml-mistral-nemo-dpo-1412-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-dpo-1412-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-dpo-1412-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-1412-v2
chaiml-mistral-nemo-dpo-1412-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-1412-v2/config.json
chaiml-mistral-nemo-dpo-1412-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-1412-v2/special_tokens_map.json
chaiml-mistral-nemo-dpo-1412-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-1412-v2/tokenizer_config.json
chaiml-mistral-nemo-dpo-1412-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-1412-v2/tokenizer.json
chaiml-mistral-nemo-dpo-1412-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-1412-v2/flywheel_model.0.safetensors
chaiml-mistral-nemo-dpo-1412-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 27.44it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 48.82it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 47.86it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:06, 49.47it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 52.25it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 50.23it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:06, 50.43it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:05, 52.44it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 48.96it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 35.86it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 36.33it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 41.09it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:06, 42.85it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 43.77it/s]
Loading 0:  25%|██▍       | 90/363 [00:01<00:05, 48.95it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:05, 47.73it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:05, 46.50it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:04, 54.57it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:05, 48.24it/s]
Loading 0:  33%|███▎      | 121/363 [00:02<00:05, 47.57it/s]
Loading 0:  35%|███▍      | 127/363 [00:02<00:05, 42.53it/s]
Loading 0:  37%|███▋      | 134/363 [00:02<00:04, 47.89it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:04, 47.05it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:07, 28.42it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 28.46it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:05, 37.00it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:05, 37.61it/s]
Loading 0:  46%|████▋     | 168/363 [00:03<00:05, 36.48it/s]
Loading 0:  48%|████▊     | 174/363 [00:04<00:04, 40.65it/s]
Loading 0:  49%|████▉     | 179/363 [00:04<00:04, 40.53it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:04, 41.16it/s]
Loading 0:  52%|█████▏    | 190/363 [00:04<00:04, 41.42it/s]
Loading 0:  54%|█████▎    | 195/363 [00:04<00:04, 40.33it/s]
Loading 0:  55%|█████▌    | 201/363 [00:04<00:03, 44.03it/s]
Loading 0:  57%|█████▋    | 206/363 [00:04<00:03, 43.15it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:03, 44.20it/s]
Loading 0:  60%|█████▉    | 216/363 [00:05<00:03, 45.43it/s]
Loading 0:  61%|██████    | 222/363 [00:05<00:03, 42.58it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 30.90it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:04, 30.86it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 37.60it/s]
Loading 0:  67%|██████▋   | 244/363 [00:05<00:03, 38.55it/s]
Loading 0:  69%|██████▊   | 249/363 [00:06<00:03, 37.22it/s]
Loading 0:  70%|███████   | 255/363 [00:06<00:02, 41.60it/s]
Loading 0:  72%|███████▏  | 260/363 [00:06<00:02, 41.33it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 42.86it/s]
Loading 0:  75%|███████▍  | 271/363 [00:06<00:02, 41.81it/s]
Loading 0:  76%|███████▌  | 276/363 [00:06<00:02, 40.90it/s]
Loading 0:  78%|███████▊  | 282/363 [00:06<00:01, 45.49it/s]
Loading 0:  79%|███████▉  | 287/363 [00:06<00:01, 44.98it/s]
Loading 0:  80%|████████  | 292/363 [00:06<00:01, 45.10it/s]
Loading 0:  82%|████████▏ | 297/363 [00:07<00:01, 46.14it/s]
Loading 0:  83%|████████▎ | 303/363 [00:07<00:01, 43.41it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:22,  2.47it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:15,  3.19it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:08,  5.25it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:05,  7.16it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:03,  9.18it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 13.05it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:01, 16.49it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 19.38it/s]
Loading 0:  98%|█████████▊| 355/363 [00:15<00:00, 24.46it/s]
Loading 0:  99%|█████████▉| 360/363 [00:15<00:00, 27.35it/s]
                                                            
Job chaiml-mistral-nemo-dpo-1412-v2-mkmlizer completed after 94.7s with status: succeeded
Stopping job with name chaiml-mistral-nemo-dpo-1412-v2-mkmlizer
Pipeline stage MKMLizer completed in 95.33s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mistral-nemo-dpo-1412-v2
Waiting for inference service chaiml-mistral-nemo-dpo-1412-v2 to be ready
Inference service chaiml-mistral-nemo-dpo-1412-v2 ready after 251.39035773277283s
Pipeline stage MKMLDeployer completed in 251.93s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.4259164333343506s
Received healthy response to inference request in 1.2254338264465332s
Received healthy response to inference request in 1.1454718112945557s
Received healthy response to inference request in 0.9953246116638184s
Received healthy response to inference request in 1.0408587455749512s
5 requests
0 failed requests
5th percentile: 1.0044314384460449
10th percentile: 1.0135382652282714
20th percentile: 1.0317519187927247
30th percentile: 1.061781358718872
40th percentile: 1.103626585006714
50th percentile: 1.1454718112945557
60th percentile: 1.1774566173553467
70th percentile: 1.2094414234161377
80th percentile: 1.2655303478240967
90th percentile: 1.3457233905792236
95th percentile: 1.385819911956787
99th percentile: 1.4178971290588378
mean time: 1.1666010856628417
Pipeline stage StressChecker completed in 7.13s
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 2.59s
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 2.34s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_1412_v2 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 2898.48s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_1412_v2 status is now inactive due to auto deactivation removed underperforming models