chaiml-mistral-nemo-dpo-_7200

developer_uid: azuruce

submission_id: chaiml-mistral-nemo-dpo-_7200_v4

model_name: chaiml-mistral-nemo-dpo-_7200_v4

model_group: ChaiML/mistral_nemo_dpo_

status: inactive

timestamp: 2024-12-20T23:14:26+00:00

num_battles: 15308

num_wins: 7164

celo_rating: 1227.74

family_friendly_score: 0.601

family_friendly_standard_error: 0.006925301437482704

submission_type: basic

model_repo: ChaiML/mistral_nemo_dpo_round2_albert_20241220_v1-checkpoint-138

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6293697272136946, 'latency_mean': 1.5888226699829102, 'latency_p50': 1.5967066287994385, 'latency_p90': 1.7371542692184447}, {'batch_size': 3, 'throughput': 1.2562446806843248, 'latency_mean': 2.3790073084831236, 'latency_p50': 2.387833833694458, 'latency_p90': 2.6046214580535887}, {'batch_size': 5, 'throughput': 1.5927906845116344, 'latency_mean': 3.115818313360214, 'latency_p50': 3.106439709663391, 'latency_p90': 3.4871475219726564}, {'batch_size': 6, 'throughput': 1.6933913699475478, 'latency_mean': 3.524445095062256, 'latency_p50': 3.5112481117248535, 'latency_p90': 4.010095548629761}, {'batch_size': 8, 'throughput': 1.8396177930243973, 'latency_mean': 4.32766108751297, 'latency_p50': 4.320491671562195, 'latency_p90': 4.938111710548401}, {'batch_size': 10, 'throughput': 1.9231333110769178, 'latency_mean': 5.1596124231815335, 'latency_p50': 5.163783431053162, 'latency_p90': 5.876967978477478}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-mistral-nemo-dpo-_7200_v4

is_internal_developer: True

language_model: ChaiML/mistral_nemo_dpo_round2_albert_20241220_v1-checkpoint-138

model_size: 13B

ranking_group: single

throughput_3p7s: 1.74

us_pacific_date: 2024-12-20

win_ratio: 0.46799059315390645

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-7200-v4-mkmlizer
Waiting for job on chaiml-mistral-nemo-dpo-7200-v4-mkmlizer to finish
chaiml-mistral-nemo-dpo-7200-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-dpo-7200-v4-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral-nemo-dpo-7200-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral-nemo-dpo-7200-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral-nemo-dpo-7200-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral-nemo-dpo-7200-v4-mkmlizer: ║       /___/                                                         ║
chaiml-mistral-nemo-dpo-7200-v4-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-7200-v4-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-mistral-nemo-dpo-7200-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral-nemo-dpo-7200-v4-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-nemo-dpo-7200-v4-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-7200-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-nemo-dpo-7200-v4-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-nemo-dpo-7200-v4-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-7200-v4-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-nemo-dpo-7200-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-nemo-dpo-7200-v4-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-mistral-nemo-dpo-7200-v4-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-7200-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-dpo-7200-v4-mkmlizer: Downloaded to shared memory in 30.754s
chaiml-mistral-nemo-dpo-7200-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpt1k5a_oc, device:0
chaiml-mistral-nemo-dpo-7200-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-nemo-dpo-7200-v4-mkmlizer: quantized model in 37.900s
chaiml-mistral-nemo-dpo-7200-v4-mkmlizer: Processed model ChaiML/mistral_nemo_dpo_round2_albert_20241220_v1-checkpoint-138 in 68.654s
chaiml-mistral-nemo-dpo-7200-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-dpo-7200-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-dpo-7200-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-7200-v4
chaiml-mistral-nemo-dpo-7200-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-7200-v4/config.json
chaiml-mistral-nemo-dpo-7200-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-7200-v4/special_tokens_map.json
chaiml-mistral-nemo-dpo-7200-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-7200-v4/tokenizer_config.json
chaiml-mistral-nemo-dpo-7200-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-7200-v4/tokenizer.json
chaiml-mistral-nemo-dpo-7200-v4-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 26.59it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 44.92it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:07, 46.16it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:09, 34.76it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:07, 43.32it/s]
Loading 0:  10%|▉         | 35/363 [00:00<00:07, 42.95it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:07, 42.71it/s]
Loading 0:  12%|█▏        | 45/363 [00:01<00:07, 44.31it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:08, 35.31it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:07, 40.40it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:10, 29.76it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:10, 29.63it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:08, 35.05it/s]
Loading 0:  21%|██        | 76/363 [00:02<00:07, 36.71it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:07, 38.27it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:06, 40.36it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 34.28it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 41.14it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 40.29it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:06, 41.80it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:07, 35.63it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:06, 35.63it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 40.89it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:06, 33.47it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:06, 36.06it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 38.78it/s]
Loading 0:  40%|███▉      | 145/363 [00:04<00:08, 26.38it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:07, 27.35it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:05, 35.24it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 36.98it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 38.90it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 41.40it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 35.75it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 42.48it/s]
Loading 0:  52%|█████▏    | 188/363 [00:05<00:04, 42.23it/s]
Loading 0:  53%|█████▎    | 193/363 [00:05<00:03, 42.89it/s]
Loading 0:  55%|█████▍    | 198/363 [00:05<00:03, 44.32it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:04, 36.68it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 44.39it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 43.99it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 44.62it/s]
Loading 0:  62%|██████▏   | 225/363 [00:06<00:05, 27.09it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 29.37it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 37.13it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 38.45it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 39.95it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 42.32it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:03, 35.07it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 41.51it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 41.54it/s]
Loading 0:  75%|███████▌  | 274/363 [00:07<00:02, 41.57it/s]
Loading 0:  77%|███████▋  | 279/363 [00:07<00:01, 42.69it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 34.99it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 41.17it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 41.09it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 40.95it/s]
Loading 0:  84%|████████▍ | 306/363 [00:14<00:23,  2.39it/s]
Loading 0:  85%|████████▌ | 310/363 [00:15<00:17,  3.04it/s]
Loading 0:  86%|████████▌ | 313/363 [00:15<00:13,  3.67it/s]
Loading 0:  87%|████████▋ | 317/363 [00:15<00:09,  4.87it/s]
Loading 0:  88%|████████▊ | 321/363 [00:15<00:06,  6.23it/s]
Loading 0:  90%|████████▉ | 326/363 [00:15<00:04,  8.70it/s]
Loading 0:  91%|█████████ | 330/363 [00:16<00:03, 10.40it/s]
Loading 0:  92%|█████████▏| 335/363 [00:16<00:02, 13.78it/s]
Loading 0:  93%|█████████▎| 339/363 [00:16<00:01, 15.08it/s]
Loading 0:  95%|█████████▌| 346/363 [00:16<00:00, 21.88it/s]
Loading 0:  96%|█████████▋| 350/363 [00:16<00:00, 24.17it/s]
Loading 0:  98%|█████████▊| 356/363 [00:16<00:00, 29.51it/s]
Loading 0:  99%|█████████▉| 361/363 [00:16<00:00, 33.15it/s]
                                                            
Job chaiml-mistral-nemo-dpo-7200-v4-mkmlizer completed after 94.28s with status: succeeded
Stopping job with name chaiml-mistral-nemo-dpo-7200-v4-mkmlizer
Pipeline stage MKMLizer completed in 94.84s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mistral-nemo-dpo-7200-v4
Waiting for inference service chaiml-mistral-nemo-dpo-7200-v4 to be ready
Inference service chaiml-mistral-nemo-dpo-7200-v4 ready after 260.9721577167511s
Pipeline stage MKMLDeployer completed in 261.71s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8427379131317139s
Received healthy response to inference request in 0.9761664867401123s
Received healthy response to inference request in 1.2768614292144775s
Received healthy response to inference request in 0.4954700469970703s
Received healthy response to inference request in 1.1287755966186523s
5 requests
0 failed requests
5th percentile: 0.5916093349456787
10th percentile: 0.6877486228942871
20th percentile: 0.8800271987915039
30th percentile: 1.0066883087158203
40th percentile: 1.0677319526672364
50th percentile: 1.1287755966186523
60th percentile: 1.1880099296569824
70th percentile: 1.2472442626953124
80th percentile: 1.390036725997925
90th percentile: 1.6163873195648193
95th percentile: 1.7295626163482665
99th percentile: 1.8201028537750243
mean time: 1.1440022945404054
Pipeline stage StressChecker completed in 7.48s
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 0.70s
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 0.73s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_7200_v4 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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-mistral-nemo-dpo-7200-v4-profiler
Waiting for inference service chaiml-mistral-nemo-dpo-7200-v4-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 2106.13s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_7200_v4 status is now inactive due to auto deactivation removed underperforming models