developer_uid: azuruce
submission_id: chaiml-mistral-nemo-dpo-_3716_v2
model_name: chaiml-mistral-nemo-dpo-_3716_v2
model_group: ChaiML/mistral_nemo_dpo_
status: inactive
timestamp: 2024-12-18T17:14:54+00:00
num_battles: 13961
num_wins: 6934
celo_rating: 1259.74
family_friendly_score: 0.5734
family_friendly_standard_error: 0.006994461237293406
submission_type: basic
model_repo: ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-3432
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6381180774645732, 'latency_mean': 1.5670164716243744, 'latency_p50': 1.5618430376052856, 'latency_p90': 1.7544719696044921}, {'batch_size': 3, 'throughput': 1.2501759292399965, 'latency_mean': 2.3860565173625945, 'latency_p50': 2.397005319595337, 'latency_p90': 2.5885655879974365}, {'batch_size': 5, 'throughput': 1.5892870386632514, 'latency_mean': 3.131159349679947, 'latency_p50': 3.132434844970703, 'latency_p90': 3.518223595619202}, {'batch_size': 6, 'throughput': 1.6966415008867242, 'latency_mean': 3.5221761369705202, 'latency_p50': 3.5013498067855835, 'latency_p90': 3.9529032468795777}, {'batch_size': 8, 'throughput': 1.8558921414197667, 'latency_mean': 4.2771770465374, 'latency_p50': 4.2985053062438965, 'latency_p90': 4.851802277565002}, {'batch_size': 10, 'throughput': 1.9253597012660586, 'latency_mean': 5.150634384155273, 'latency_p50': 5.163932204246521, 'latency_p90': 5.7754301071167}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-mistral-nemo-dpo-_3716_v2
is_internal_developer: True
language_model: ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-3432
model_size: 13B
ranking_group: single
throughput_3p7s: 1.75
us_pacific_date: 2024-12-18
win_ratio: 0.4966692930305852
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-3716-v2-mkmlizer
Waiting for job on chaiml-mistral-nemo-dpo-3716-v2-mkmlizer to finish
chaiml-mistral-nemo-dpo-3716-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-dpo-3716-v2-mkmlizer: ║ _____ __ __ ║
chaiml-mistral-nemo-dpo-3716-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-mistral-nemo-dpo-3716-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-mistral-nemo-dpo-3716-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-mistral-nemo-dpo-3716-v2-mkmlizer: ║ /___/ ║
chaiml-mistral-nemo-dpo-3716-v2-mkmlizer: ║ ║
chaiml-mistral-nemo-dpo-3716-v2-mkmlizer: ║ Version: 0.11.12 ║
chaiml-mistral-nemo-dpo-3716-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-mistral-nemo-dpo-3716-v2-mkmlizer: ║ https://mk1.ai ║
chaiml-mistral-nemo-dpo-3716-v2-mkmlizer: ║ ║
chaiml-mistral-nemo-dpo-3716-v2-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-mistral-nemo-dpo-3716-v2-mkmlizer: ║ belonging to: ║
chaiml-mistral-nemo-dpo-3716-v2-mkmlizer: ║ ║
chaiml-mistral-nemo-dpo-3716-v2-mkmlizer: ║ Chai Research Corp. ║
chaiml-mistral-nemo-dpo-3716-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-mistral-nemo-dpo-3716-v2-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
chaiml-mistral-nemo-dpo-3716-v2-mkmlizer: ║ ║
chaiml-mistral-nemo-dpo-3716-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-dpo-3716-v2-mkmlizer: Downloaded to shared memory in 32.560s
chaiml-mistral-nemo-dpo-3716-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpaofjhr1p, device:0
chaiml-mistral-nemo-dpo-3716-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-nemo-dpo-3716-v2-mkmlizer: quantized model in 36.367s
chaiml-mistral-nemo-dpo-3716-v2-mkmlizer: Processed model ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-3432 in 68.928s
chaiml-mistral-nemo-dpo-3716-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-dpo-3716-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-dpo-3716-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-3716-v2
chaiml-mistral-nemo-dpo-3716-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-3716-v2/config.json
chaiml-mistral-nemo-dpo-3716-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-3716-v2/special_tokens_map.json
chaiml-mistral-nemo-dpo-3716-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-3716-v2/tokenizer_config.json
chaiml-mistral-nemo-dpo-3716-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-3716-v2/tokenizer.json
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-mistral-nemo-dpo-3716-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-3716-v2/flywheel_model.0.safetensors
chaiml-mistral-nemo-dpo-3716-v2-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:13, 27.50it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:07, 46.49it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:08, 41.32it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:08, 40.29it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:07, 46.75it/s] Loading 0: 10%|█ | 37/363 [00:00<00:07, 43.86it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 41.90it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:06, 46.23it/s] Loading 0: 15%|█▍ | 53/363 [00:01<00:06, 44.40it/s] Loading 0: 16%|█▌ | 58/363 [00:01<00:06, 45.09it/s] Loading 0: 17%|█▋ | 63/363 [00:01<00:09, 30.14it/s] Loading 0: 18%|█▊ | 67/363 [00:01<00:09, 31.18it/s] Loading 0: 20%|█▉ | 71/363 [00:01<00:08, 32.67it/s] Loading 0: 21%|██ | 75/363 [00:01<00:08, 33.40it/s] Loading 0: 22%|██▏ | 81/363 [00:02<00:07, 38.15it/s] Loading 0: 24%|██▎ | 86/363 [00:02<00:06, 40.42it/s] Loading 0: 25%|██▌ | 91/363 [00:02<00:08, 33.94it/s] Loading 0: 27%|██▋ | 98/363 [00:02<00:06, 40.78it/s] Loading 0: 28%|██▊ | 103/363 [00:02<00:06, 41.67it/s] Loading 0: 30%|███ | 109/363 [00:02<00:05, 45.68it/s] Loading 0: 31%|███▏ | 114/363 [00:02<00:06, 39.58it/s] Loading 0: 33%|███▎ | 119/363 [00:03<00:06, 39.16it/s] Loading 0: 34%|███▍ | 125/363 [00:03<00:05, 43.45it/s] Loading 0: 36%|███▌ | 130/363 [00:03<00:05, 43.15it/s] Loading 0: 37%|███▋ | 135/363 [00:03<00:05, 44.26it/s] Loading 0: 39%|███▉ | 141/363 [00:03<00:05, 42.80it/s] Loading 0: 40%|████ | 146/363 [00:03<00:07, 30.80it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:07, 30.32it/s] Loading 0: 43%|████▎ | 157/363 [00:04<00:05, 37.25it/s] Loading 0: 45%|████▍ | 163/363 [00:04<00:05, 37.94it/s] Loading 0: 46%|████▋ | 168/363 [00:04<00:05, 38.50it/s] Loading 0: 48%|████▊ | 174/363 [00:04<00:04, 43.19it/s] Loading 0: 49%|████▉ | 179/363 [00:04<00:04, 42.71it/s] Loading 0: 51%|█████ | 184/363 [00:04<00:04, 42.82it/s] Loading 0: 52%|█████▏ | 189/363 [00:04<00:03, 44.27it/s] Loading 0: 53%|█████▎ | 194/363 [00:04<00:04, 37.51it/s] Loading 0: 55%|█████▌ | 201/363 [00:05<00:03, 44.78it/s] Loading 0: 57%|█████▋ | 206/363 [00:05<00:03, 44.24it/s] Loading 0: 58%|█████▊ | 211/363 [00:05<00:03, 44.42it/s] Loading 0: 60%|█████▉ | 216/363 [00:05<00:03, 43.39it/s] Loading 0: 61%|██████ | 222/363 [00:05<00:03, 41.67it/s] Loading 0: 63%|██████▎ | 227/363 [00:05<00:04, 30.75it/s] Loading 0: 64%|██████▎ | 231/363 [00:05<00:04, 30.34it/s] Loading 0: 65%|██████▌ | 237/363 [00:06<00:03, 36.51it/s] Loading 0: 67%|██████▋ | 242/363 [00:06<00:03, 38.37it/s] Loading 0: 68%|██████▊ | 247/363 [00:06<00:02, 39.50it/s] Loading 0: 70%|██████▉ | 253/363 [00:06<00:02, 39.20it/s] Loading 0: 71%|███████ | 258/363 [00:06<00:02, 39.42it/s] Loading 0: 73%|███████▎ | 265/363 [00:06<00:02, 44.56it/s] Loading 0: 75%|███████▍ | 271/363 [00:06<00:02, 42.02it/s] Loading 0: 76%|███████▌ | 276/363 [00:06<00:02, 41.01it/s] Loading 0: 78%|███████▊ | 282/363 [00:07<00:01, 44.90it/s] Loading 0: 79%|███████▉ | 287/363 [00:07<00:01, 42.58it/s] Loading 0: 80%|████████ | 292/363 [00:07<00:01, 42.52it/s] Loading 0: 82%|████████▏ | 297/363 [00:07<00:01, 44.29it/s] Loading 0: 83%|████████▎ | 303/363 [00:07<00:01, 42.22it/s] Loading 0: 85%|████████▍ | 308/363 [00:14<00:21, 2.52it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:15, 3.25it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:08, 5.34it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:05, 7.26it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:03, 9.26it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 13.11it/s] Loading 0: 94%|█████████▍| 343/363 [00:15<00:01, 16.17it/s] Loading 0: 96%|█████████▌| 348/363 [00:15<00:00, 18.22it/s] Loading 0: 98%|█████████▊| 355/363 [00:15<00:00, 24.57it/s] Loading 0: 99%|█████████▉| 360/363 [00:15<00:00, 27.26it/s]
Job chaiml-mistral-nemo-dpo-3716-v2-mkmlizer completed after 94.59s with status: succeeded
Stopping job with name chaiml-mistral-nemo-dpo-3716-v2-mkmlizer
Pipeline stage MKMLizer completed in 95.11s
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-3716-v2
Waiting for inference service chaiml-mistral-nemo-dpo-3716-v2 to be ready
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-mistral-nemo-dpo-3716-v2 ready after 242.19040513038635s
Pipeline stage MKMLDeployer completed in 242.84s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7804815769195557s
Received healthy response to inference request in 0.704089879989624s
Received healthy response to inference request in 1.3917350769042969s
Received healthy response to inference request in 1.4744298458099365s
Received healthy response to inference request in 1.079756259918213s
5 requests
0 failed requests
5th percentile: 0.7792231559753418
10th percentile: 0.8543564319610596
20th percentile: 1.0046229839324952
30th percentile: 1.1421520233154296
40th percentile: 1.2669435501098634
50th percentile: 1.3917350769042969
60th percentile: 1.4248129844665527
70th percentile: 1.4578908920288085
80th percentile: 1.5356401920318603
90th percentile: 1.658060884475708
95th percentile: 1.7192712306976319
99th percentile: 1.768239507675171
mean time: 1.2860985279083252
Pipeline stage StressChecker completed in 8.40s
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 2.41s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_3716_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-3716-v2-profiler
Waiting for inference service chaiml-mistral-nemo-dpo-3716-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 2994.70s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_3716_v2 status is now inactive due to auto deactivation removed underperforming models