developer_uid: azuruce
submission_id: chaiml-mistral-nemo-dpo-_6396_v2
model_name: chaiml-mistral-nemo-dpo-_6396_v2
model_group: ChaiML/mistral_nemo_dpo_
status: torndown
timestamp: 2024-12-22T06:58:40+00:00
num_battles: 16492
num_wins: 8104
celo_rating: 1258.88
family_friendly_score: 0.5851999999999999
family_friendly_standard_error: 0.006967653263474008
submission_type: basic
model_repo: ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-6250
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6480963262473899, 'latency_mean': 1.5428863275051117, 'latency_p50': 1.537920355796814, 'latency_p90': 1.7022336959838866}, {'batch_size': 4, 'throughput': 1.5101422338184227, 'latency_mean': 2.6320827126502992, 'latency_p50': 2.640379309654236, 'latency_p90': 2.9710629701614377}, {'batch_size': 5, 'throughput': 1.6466444496619304, 'latency_mean': 3.0183859968185427, 'latency_p50': 3.0294774770736694, 'latency_p90': 3.3797263860702516}, {'batch_size': 8, 'throughput': 1.934700299293372, 'latency_mean': 4.108243788480759, 'latency_p50': 4.112337350845337, 'latency_p90': 4.659814739227295}, {'batch_size': 10, 'throughput': 2.0175638814589343, 'latency_mean': 4.922562724351883, 'latency_p50': 4.918514370918274, 'latency_p90': 5.588677000999451}, {'batch_size': 12, 'throughput': 2.092658925264627, 'latency_mean': 5.69527806520462, 'latency_p50': 5.688898801803589, 'latency_p90': 6.364826703071595}, {'batch_size': 15, 'throughput': 2.1301388942376915, 'latency_mean': 6.967460330724716, 'latency_p50': 6.979354977607727, 'latency_p90': 7.943059611320495}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-mistral-nemo-dpo-_6396_v2
is_internal_developer: True
language_model: ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-6250
model_size: 13B
ranking_group: single
throughput_3p7s: 1.86
us_pacific_date: 2024-12-21
win_ratio: 0.4913897647344167
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-6396-v2-mkmlizer
Waiting for job on chaiml-mistral-nemo-dpo-6396-v2-mkmlizer to finish
chaiml-mistral-nemo-dpo-6396-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-dpo-6396-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral-nemo-dpo-6396-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral-nemo-dpo-6396-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral-nemo-dpo-6396-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral-nemo-dpo-6396-v2-mkmlizer: ║       /___/                                                         ║
chaiml-mistral-nemo-dpo-6396-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-6396-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-mistral-nemo-dpo-6396-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral-nemo-dpo-6396-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-nemo-dpo-6396-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-6396-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-nemo-dpo-6396-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-nemo-dpo-6396-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-6396-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-nemo-dpo-6396-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-nemo-dpo-6396-v2-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-mistral-nemo-dpo-6396-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-6396-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-dpo-6396-v2-mkmlizer: Downloaded to shared memory in 47.883s
chaiml-mistral-nemo-dpo-6396-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpohqhmgtw, device:0
chaiml-mistral-nemo-dpo-6396-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-nemo-dpo-6396-v2-mkmlizer: quantized model in 37.450s
chaiml-mistral-nemo-dpo-6396-v2-mkmlizer: Processed model ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-6250 in 85.333s
chaiml-mistral-nemo-dpo-6396-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-dpo-6396-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-dpo-6396-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-6396-v2
chaiml-mistral-nemo-dpo-6396-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-6396-v2/config.json
chaiml-mistral-nemo-dpo-6396-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-6396-v2/special_tokens_map.json
chaiml-mistral-nemo-dpo-6396-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-6396-v2/tokenizer_config.json
chaiml-mistral-nemo-dpo-6396-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-6396-v2/tokenizer.json
chaiml-mistral-nemo-dpo-6396-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-6396-v2/flywheel_model.0.safetensors
chaiml-mistral-nemo-dpo-6396-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 28.99it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 48.43it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:08, 39.84it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 39.17it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:07, 43.75it/s]
Loading 0:  10%|▉         | 35/363 [00:00<00:07, 43.95it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:07, 44.73it/s]
Loading 0:  12%|█▏        | 45/363 [00:01<00:07, 45.40it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:08, 36.75it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:07, 41.23it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 30.56it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 30.07it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:08, 34.90it/s]
Loading 0:  21%|██        | 75/363 [00:01<00:08, 35.12it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:07, 38.03it/s]
Loading 0:  23%|██▎       | 85/363 [00:02<00:07, 38.00it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 39.40it/s]
Loading 0:  26%|██▌       | 95/363 [00:02<00:09, 29.70it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:08, 30.52it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:08, 32.14it/s]
Loading 0:  29%|██▉       | 107/363 [00:02<00:07, 33.69it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:06, 35.89it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:07, 35.19it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:06, 35.44it/s]
Loading 0:  35%|███▍      | 126/363 [00:03<00:05, 40.50it/s]
Loading 0:  36%|███▌      | 131/363 [00:03<00:05, 42.77it/s]
Loading 0:  37%|███▋      | 136/363 [00:03<00:06, 35.23it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:07, 30.41it/s]
Loading 0:  40%|████      | 146/363 [00:04<00:06, 32.04it/s]
Loading 0:  41%|████▏     | 150/363 [00:04<00:06, 31.30it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:05, 37.51it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 38.64it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:04, 40.43it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 41.80it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 35.21it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:04, 38.38it/s]
Loading 0:  51%|█████     | 186/363 [00:05<00:04, 37.62it/s]
Loading 0:  53%|█████▎    | 192/363 [00:05<00:04, 42.51it/s]
Loading 0:  54%|█████▍    | 197/363 [00:05<00:03, 42.25it/s]
Loading 0:  56%|█████▌    | 202/363 [00:05<00:03, 41.84it/s]
Loading 0:  57%|█████▋    | 207/363 [00:05<00:03, 43.52it/s]
Loading 0:  58%|█████▊    | 212/363 [00:05<00:04, 36.06it/s]
Loading 0:  60%|██████    | 218/363 [00:05<00:03, 40.75it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:04, 31.07it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:04, 31.95it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:04, 30.75it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 36.24it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 35.60it/s]
Loading 0:  68%|██████▊   | 246/363 [00:06<00:03, 38.33it/s]
Loading 0:  69%|██████▉   | 251/363 [00:06<00:02, 39.46it/s]
Loading 0:  71%|███████   | 256/363 [00:06<00:02, 39.98it/s]
Loading 0:  72%|███████▏  | 261/363 [00:07<00:02, 41.78it/s]
Loading 0:  73%|███████▎  | 266/363 [00:07<00:02, 34.69it/s]
Loading 0:  75%|███████▌  | 273/363 [00:07<00:02, 40.84it/s]
Loading 0:  77%|███████▋  | 278/363 [00:07<00:02, 39.22it/s]
Loading 0:  78%|███████▊  | 283/363 [00:07<00:02, 39.76it/s]
Loading 0:  79%|███████▉  | 288/363 [00:07<00:01, 41.60it/s]
Loading 0:  81%|████████  | 293/363 [00:07<00:02, 34.13it/s]
Loading 0:  82%|████████▏ | 299/363 [00:08<00:01, 38.67it/s]
Loading 0:  84%|████████▎ | 304/363 [00:14<00:24,  2.44it/s]
Loading 0:  85%|████████▍ | 307/363 [00:15<00:18,  2.95it/s]
Loading 0:  86%|████████▌ | 312/363 [00:15<00:12,  4.18it/s]
Loading 0:  87%|████████▋ | 317/363 [00:15<00:07,  5.85it/s]
Loading 0:  88%|████████▊ | 321/363 [00:15<00:05,  7.43it/s]
Loading 0:  90%|█████████ | 328/363 [00:15<00:03, 11.49it/s]
Loading 0:  92%|█████████▏| 333/363 [00:15<00:02, 14.58it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:01, 18.00it/s]
Loading 0:  94%|█████████▍| 343/363 [00:15<00:00, 21.93it/s]
Loading 0:  96%|█████████▌| 348/363 [00:16<00:00, 22.67it/s]
Loading 0:  98%|█████████▊| 355/363 [00:16<00:00, 29.71it/s]
Loading 0:  99%|█████████▉| 360/363 [00:16<00:00, 31.94it/s]
                                                            

Job chaiml-mistral-nemo-dpo-6396-v2-mkmlizer completed after 114.89s with status: succeeded
Stopping job with name chaiml-mistral-nemo-dpo-6396-v2-mkmlizer
Pipeline stage MKMLizer completed in 115.47s
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-6396-v2
Waiting for inference service chaiml-mistral-nemo-dpo-6396-v2 to be ready
Inference service chaiml-mistral-nemo-dpo-6396-v2 ready after 270.9469039440155s
Pipeline stage MKMLDeployer completed in 271.46s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.2173807621002197s
Received healthy response to inference request in 1.1803545951843262s
Received healthy response to inference request in 1.202934741973877s
Received healthy response to inference request in 0.7759866714477539s
Received healthy response to inference request in 0.8943338394165039s
5 requests
0 failed requests
5th percentile: 0.7996561050415039
10th percentile: 0.8233255386352539
20th percentile: 0.870664405822754
30th percentile: 0.9515379905700684
40th percentile: 1.0659462928771972
50th percentile: 1.1803545951843262
60th percentile: 1.1893866539001465
70th percentile: 1.1984187126159669
80th percentile: 1.2058239459991456
90th percentile: 1.2116023540496825
95th percentile: 1.2144915580749511
99th percentile: 1.216802921295166
mean time: 1.0541981220245362
Pipeline stage StressChecker completed in 6.76s
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 1.03s
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-_6396_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 0.11s
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-6396-v2-profiler
Waiting for inference service chaiml-mistral-nemo-dpo-6396-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 2451.56s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_6396_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral-nemo-dpo-_6396_v2 status is now torndown due to DeploymentManager action
chaiml-mistral-nemo-dpo-_6396_v2 status is now torndown due to DeploymentManager action
chaiml-mistral-nemo-dpo-_6396_v2 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1