chaiml-mistral-nemo-dpo-_5165

developer_uid: azuruce

submission_id: chaiml-mistral-nemo-dpo-_5165_v1

model_name: chaiml-mistral-nemo-dpo-_5165_v1

model_group: ChaiML/mistral_nemo_dpo_

status: inactive

timestamp: 2024-12-19T09:06:18+00:00

num_battles: 12473

num_wins: 6274

celo_rating: 1265.98

family_friendly_score: 0.5766

family_friendly_standard_error: 0.00698759529452014

submission_type: basic

model_repo: ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-4680

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6373280529987907, 'latency_mean': 1.5689832937717438, 'latency_p50': 1.5657504796981812, 'latency_p90': 1.719053363800049}, {'batch_size': 3, 'throughput': 1.2718127712664697, 'latency_mean': 2.3531887233257294, 'latency_p50': 2.3361202478408813, 'latency_p90': 2.5703270196914674}, {'batch_size': 5, 'throughput': 1.611775214302868, 'latency_mean': 3.089323630332947, 'latency_p50': 3.1182518005371094, 'latency_p90': 3.491788864135742}, {'batch_size': 6, 'throughput': 1.7230657429534595, 'latency_mean': 3.4752508783340454, 'latency_p50': 3.4846447706222534, 'latency_p90': 3.9684956312179565}, {'batch_size': 8, 'throughput': 1.8765017790857805, 'latency_mean': 4.232622071504593, 'latency_p50': 4.240822672843933, 'latency_p90': 4.716949057579041}, {'batch_size': 10, 'throughput': 1.9600777641173177, 'latency_mean': 5.052811797857284, 'latency_p50': 5.052800178527832, 'latency_p90': 5.6866921186447135}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-mistral-nemo-dpo-_5165_v1

is_internal_developer: True

language_model: ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-4680

model_size: 13B

ranking_group: single

throughput_3p7s: 1.78

us_pacific_date: 2024-12-19

win_ratio: 0.5030064940270985

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-5165-v1-mkmlizer
Waiting for job on chaiml-mistral-nemo-dpo-5165-v1-mkmlizer to finish
chaiml-mistral-nemo-dpo-5165-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-dpo-5165-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral-nemo-dpo-5165-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral-nemo-dpo-5165-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral-nemo-dpo-5165-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral-nemo-dpo-5165-v1-mkmlizer: ║       /___/                                                         ║
chaiml-mistral-nemo-dpo-5165-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-5165-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-mistral-nemo-dpo-5165-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral-nemo-dpo-5165-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-nemo-dpo-5165-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-5165-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-nemo-dpo-5165-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-nemo-dpo-5165-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-5165-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-nemo-dpo-5165-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-nemo-dpo-5165-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-mistral-nemo-dpo-5165-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-5165-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-dpo-5165-v1-mkmlizer: Downloaded to shared memory in 45.310s
chaiml-mistral-nemo-dpo-5165-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpodf9nnx0, device:0
chaiml-mistral-nemo-dpo-5165-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-nemo-dpo-5165-v1-mkmlizer: quantized model in 35.922s
chaiml-mistral-nemo-dpo-5165-v1-mkmlizer: Processed model ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-4680 in 81.232s
chaiml-mistral-nemo-dpo-5165-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-dpo-5165-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-dpo-5165-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-5165-v1
chaiml-mistral-nemo-dpo-5165-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-5165-v1/special_tokens_map.json
chaiml-mistral-nemo-dpo-5165-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-5165-v1/tokenizer.json
chaiml-mistral-nemo-dpo-5165-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-5165-v1/flywheel_model.0.safetensors
chaiml-mistral-nemo-dpo-5165-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 27.84it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 48.89it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 46.11it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 44.33it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 51.07it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 47.62it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 45.54it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 50.45it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 47.80it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 35.23it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 35.81it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 40.58it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:06, 41.30it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 40.12it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 45.17it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:06, 43.26it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 41.10it/s]
Loading 0:  29%|██▉       | 107/363 [00:02<00:05, 45.33it/s]
Loading 0:  31%|███       | 113/363 [00:02<00:06, 41.23it/s]
Loading 0:  33%|███▎      | 118/363 [00:02<00:06, 39.40it/s]
Loading 0:  34%|███▍      | 125/363 [00:02<00:05, 45.40it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 43.34it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 44.14it/s]
Loading 0:  39%|███▉      | 141/363 [00:03<00:05, 43.03it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:07, 30.56it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 30.51it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:05, 37.29it/s]
Loading 0:  45%|████▍     | 162/363 [00:03<00:05, 39.36it/s]
Loading 0:  46%|████▌     | 167/363 [00:04<00:05, 35.21it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 43.05it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:04, 42.07it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:04, 40.29it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 44.90it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 43.40it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 42.64it/s]
Loading 0:  58%|█████▊    | 211/363 [00:05<00:03, 47.66it/s]
Loading 0:  60%|█████▉    | 217/363 [00:05<00:03, 46.27it/s]
Loading 0:  61%|██████    | 222/363 [00:05<00:02, 47.04it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 32.48it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:04, 32.10it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 39.09it/s]
Loading 0:  67%|██████▋   | 244/363 [00:05<00:02, 40.19it/s]
Loading 0:  69%|██████▊   | 249/363 [00:06<00:02, 40.25it/s]
Loading 0:  71%|███████   | 256/363 [00:06<00:02, 45.33it/s]
Loading 0:  72%|███████▏  | 262/363 [00:06<00:02, 44.83it/s]
Loading 0:  74%|███████▎  | 267/363 [00:06<00:02, 42.77it/s]
Loading 0:  75%|███████▌  | 273/363 [00:06<00:01, 46.09it/s]
Loading 0:  77%|███████▋  | 278/363 [00:06<00:01, 46.05it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 47.08it/s]
Loading 0:  79%|███████▉  | 288/363 [00:06<00:01, 46.59it/s]
Loading 0:  81%|████████  | 293/363 [00:07<00:01, 38.43it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 48.05it/s]
Loading 0:  85%|████████▍ | 307/363 [00:14<00:20,  2.78it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:13,  3.67it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:07,  5.70it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:04,  7.56it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:03,  9.48it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 13.21it/s]
Loading 0:  94%|█████████▍| 343/363 [00:14<00:01, 16.18it/s]
Loading 0:  96%|█████████▌| 348/363 [00:15<00:00, 18.19it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 25.17it/s]
Loading 0:  99%|█████████▉| 361/363 [00:15<00:00, 28.64it/s]
                                                            
Job chaiml-mistral-nemo-dpo-5165-v1-mkmlizer completed after 103.96s with status: succeeded
Stopping job with name chaiml-mistral-nemo-dpo-5165-v1-mkmlizer
Pipeline stage MKMLizer completed in 104.45s
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 chaiml-mistral-nemo-dpo-5165-v1
Waiting for inference service chaiml-mistral-nemo-dpo-5165-v1 to be ready
Inference service chaiml-mistral-nemo-dpo-5165-v1 ready after 241.60572624206543s
Pipeline stage MKMLDeployer completed in 242.15s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.4838037490844727s
Received healthy response to inference request in 0.6216175556182861s
Received healthy response to inference request in 1.2695972919464111s
Received healthy response to inference request in 1.0137760639190674s
Received healthy response to inference request in 0.7104496955871582s
5 requests
0 failed requests
5th percentile: 0.6393839836120605
10th percentile: 0.657150411605835
20th percentile: 0.6926832675933838
30th percentile: 0.7711149692535401
40th percentile: 0.8924455165863038
50th percentile: 1.0137760639190674
60th percentile: 1.1161045551300048
70th percentile: 1.2184330463409423
80th percentile: 1.3124385833740235
90th percentile: 1.398121166229248
95th percentile: 1.4409624576568603
99th percentile: 1.4752354907989502
mean time: 1.0198488712310791
Pipeline stage StressChecker completed in 6.59s
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 2.41s
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 3.05s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_5165_v1 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 0.11s
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-5165-v1-profiler
Waiting for inference service chaiml-mistral-nemo-dpo-5165-v1-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 3177.54s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_5165_v1 status is now inactive due to auto deactivation removed underperforming models