developer_uid: azuruce
submission_id: chaiml-mistral-nemo-dpo-_7200_v1
model_name: chaiml-mistral-nemo-dpo-_7200_v1
model_group: ChaiML/mistral_nemo_dpo_
status: inactive
timestamp: 2024-12-20T16:26:34+00:00
num_battles: 17361
num_wins: 7980
celo_rating: 1234.54
family_friendly_score: 0.5988
family_friendly_standard_error: 0.006931645692041681
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': 0.6230317531150821, 'latency_mean': 1.6049911820888518, 'latency_p50': 1.6090643405914307, 'latency_p90': 1.7626805782318116}, {'batch_size': 3, 'throughput': 1.2466494525990153, 'latency_mean': 2.402417491674423, 'latency_p50': 2.3932846784591675, 'latency_p90': 2.6496510982513426}, {'batch_size': 5, 'throughput': 1.5754437951224272, 'latency_mean': 3.162148587703705, 'latency_p50': 3.142746925354004, 'latency_p90': 3.5329548835754396}, {'batch_size': 6, 'throughput': 1.671593188336987, 'latency_mean': 3.5687145042419433, 'latency_p50': 3.578950524330139, 'latency_p90': 4.096894979476929}, {'batch_size': 8, 'throughput': 1.8277530728826834, 'latency_mean': 4.348825296163559, 'latency_p50': 4.331069350242615, 'latency_p90': 4.899503874778747}, {'batch_size': 10, 'throughput': 1.9045631330687993, 'latency_mean': 5.203641642332077, 'latency_p50': 5.204535484313965, 'latency_p90': 5.831193518638611}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-mistral-nemo-dpo-_7200_v1
is_internal_developer: True
language_model: ChaiML/mistral_nemo_dpo_round2_albert_20241220_v1-checkpoint-138
model_size: 13B
ranking_group: single
throughput_3p7s: 1.71
us_pacific_date: 2024-12-20
win_ratio: 0.4596509417660273
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-v1-mkmlizer
Waiting for job on chaiml-mistral-nemo-dpo-7200-v1-mkmlizer to finish
chaiml-mistral-nemo-dpo-7200-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-dpo-7200-v1-mkmlizer: ║ _____ __ __ ║
chaiml-mistral-nemo-dpo-7200-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-mistral-nemo-dpo-7200-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-mistral-nemo-dpo-7200-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-mistral-nemo-dpo-7200-v1-mkmlizer: ║ /___/ ║
chaiml-mistral-nemo-dpo-7200-v1-mkmlizer: ║ ║
chaiml-mistral-nemo-dpo-7200-v1-mkmlizer: ║ Version: 0.11.12 ║
chaiml-mistral-nemo-dpo-7200-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-mistral-nemo-dpo-7200-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-mistral-nemo-dpo-7200-v1-mkmlizer: ║ ║
chaiml-mistral-nemo-dpo-7200-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-mistral-nemo-dpo-7200-v1-mkmlizer: ║ belonging to: ║
chaiml-mistral-nemo-dpo-7200-v1-mkmlizer: ║ ║
chaiml-mistral-nemo-dpo-7200-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-mistral-nemo-dpo-7200-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-mistral-nemo-dpo-7200-v1-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
chaiml-mistral-nemo-dpo-7200-v1-mkmlizer: ║ ║
chaiml-mistral-nemo-dpo-7200-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-dpo-7200-v1-mkmlizer: Downloaded to shared memory in 49.622s
chaiml-mistral-nemo-dpo-7200-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpexgrnmj_, device:0
chaiml-mistral-nemo-dpo-7200-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-nemo-dpo-7200-v1-mkmlizer: quantized model in 36.724s
chaiml-mistral-nemo-dpo-7200-v1-mkmlizer: Processed model ChaiML/mistral_nemo_dpo_round2_albert_20241220_v1-checkpoint-138 in 86.346s
chaiml-mistral-nemo-dpo-7200-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-dpo-7200-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-dpo-7200-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-7200-v1
chaiml-mistral-nemo-dpo-7200-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-7200-v1/config.json
chaiml-mistral-nemo-dpo-7200-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-7200-v1/special_tokens_map.json
chaiml-mistral-nemo-dpo-7200-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-7200-v1/tokenizer_config.json
chaiml-mistral-nemo-dpo-7200-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-7200-v1/tokenizer.json
chaiml-mistral-nemo-dpo-7200-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-7200-v1/flywheel_model.0.safetensors
chaiml-mistral-nemo-dpo-7200-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:13, 27.40it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:07, 47.71it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 43.35it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:08, 42.22it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 47.76it/s] Loading 0: 10%|▉ | 36/363 [00:00<00:06, 47.79it/s] Loading 0: 11%|█▏ | 41/363 [00:01<00:08, 36.81it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:07, 44.58it/s] Loading 0: 15%|█▍ | 53/363 [00:01<00:07, 43.91it/s] Loading 0: 16%|█▋ | 59/363 [00:01<00:06, 47.39it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:10, 29.60it/s] Loading 0: 20%|█▉ | 71/363 [00:01<00:08, 34.64it/s] Loading 0: 21%|██ | 76/363 [00:01<00:07, 36.48it/s] Loading 0: 22%|██▏ | 81/363 [00:02<00:07, 38.31it/s] Loading 0: 24%|██▍ | 87/363 [00:02<00:07, 38.23it/s] Loading 0: 25%|██▌ | 92/363 [00:02<00:06, 39.10it/s] Loading 0: 27%|██▋ | 98/363 [00:02<00:06, 43.52it/s] Loading 0: 28%|██▊ | 103/363 [00:02<00:05, 43.46it/s] Loading 0: 30%|██▉ | 108/363 [00:02<00:05, 45.07it/s] Loading 0: 31%|███ | 113/363 [00:02<00:06, 38.02it/s] Loading 0: 33%|███▎ | 118/363 [00:02<00:06, 38.04it/s] Loading 0: 35%|███▍ | 126/363 [00:03<00:05, 45.97it/s] Loading 0: 36%|███▋ | 132/363 [00:03<00:05, 43.27it/s] Loading 0: 38%|███▊ | 137/363 [00:03<00:05, 42.54it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 31.92it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 32.98it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 32.09it/s] Loading 0: 43%|████▎ | 156/363 [00:03<00:05, 38.03it/s] Loading 0: 44%|████▍ | 161/363 [00:04<00:05, 39.08it/s] Loading 0: 46%|████▌ | 166/363 [00:04<00:04, 40.53it/s] Loading 0: 47%|████▋ | 171/363 [00:04<00:04, 41.46it/s] Loading 0: 48%|████▊ | 176/363 [00:04<00:05, 33.47it/s] Loading 0: 50%|█████ | 183/363 [00:04<00:04, 40.42it/s] Loading 0: 52%|█████▏ | 188/363 [00:04<00:04, 40.75it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:04, 42.00it/s] Loading 0: 55%|█████▍ | 198/363 [00:04<00:03, 43.03it/s] Loading 0: 56%|█████▌ | 203/363 [00:05<00:04, 35.75it/s] Loading 0: 58%|█████▊ | 211/363 [00:05<00:03, 43.82it/s] Loading 0: 60%|█████▉ | 216/363 [00:05<00:03, 44.96it/s] Loading 0: 61%|██████ | 221/363 [00:05<00:03, 45.25it/s] Loading 0: 62%|██████▏ | 226/363 [00:05<00:04, 27.62it/s] Loading 0: 63%|██████▎ | 230/363 [00:06<00:04, 27.84it/s] Loading 0: 65%|██████▌ | 237/363 [00:06<00:03, 35.95it/s] Loading 0: 67%|██████▋ | 242/363 [00:06<00:03, 37.70it/s] Loading 0: 68%|██████▊ | 247/363 [00:06<00:02, 38.95it/s] Loading 0: 69%|██████▉ | 252/363 [00:06<00:02, 41.23it/s] Loading 0: 71%|███████ | 257/363 [00:06<00:03, 34.92it/s] Loading 0: 73%|███████▎ | 264/363 [00:06<00:02, 42.17it/s] Loading 0: 74%|███████▍ | 269/363 [00:06<00:02, 40.55it/s] Loading 0: 75%|███████▌ | 274/363 [00:07<00:02, 39.78it/s] Loading 0: 77%|███████▋ | 279/363 [00:07<00:01, 42.13it/s] Loading 0: 78%|███████▊ | 284/363 [00:07<00:02, 36.23it/s] Loading 0: 80%|████████ | 291/363 [00:07<00:01, 43.20it/s] Loading 0: 82%|████████▏ | 296/363 [00:07<00:01, 42.74it/s] Loading 0: 83%|████████▎ | 301/363 [00:07<00:01, 43.28it/s] Loading 0: 84%|████████▍ | 306/363 [00:14<00:23, 2.47it/s] Loading 0: 85%|████████▌ | 310/363 [00:14<00:16, 3.21it/s] Loading 0: 87%|████████▋ | 314/363 [00:14<00:11, 4.21it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:06, 6.28it/s] Loading 0: 90%|████████▉ | 325/363 [00:14<00:04, 8.49it/s] Loading 0: 91%|█████████ | 330/363 [00:15<00:03, 10.54it/s] Loading 0: 93%|█████████▎| 337/363 [00:15<00:01, 15.44it/s] Loading 0: 94%|█████████▍| 342/363 [00:15<00:01, 18.61it/s] Loading 0: 96%|█████████▌| 347/363 [00:15<00:00, 22.26it/s] Loading 0: 97%|█████████▋| 352/363 [00:15<00:00, 26.26it/s] Loading 0: 98%|█████████▊| 357/363 [00:15<00:00, 26.06it/s]
Job chaiml-mistral-nemo-dpo-7200-v1-mkmlizer completed after 115.29s with status: succeeded
Stopping job with name chaiml-mistral-nemo-dpo-7200-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.79s
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-7200-v1
Waiting for inference service chaiml-mistral-nemo-dpo-7200-v1 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
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-7200-v1 ready after 250.98318767547607s
Pipeline stage MKMLDeployer completed in 251.99s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.5315546989440918s
Received healthy response to inference request in 0.7462849617004395s
Received healthy response to inference request in 1.1648156642913818s
Received healthy response to inference request in 1.949702501296997s
Received healthy response to inference request in 1.2284901142120361s
5 requests
0 failed requests
5th percentile: 0.8299911022186279
10th percentile: 0.9136972427368164
20th percentile: 1.0811095237731934
30th percentile: 1.1775505542755127
40th percentile: 1.2030203342437744
50th percentile: 1.2284901142120361
60th percentile: 1.3497159481048584
70th percentile: 1.4709417819976807
80th percentile: 1.615184259414673
90th percentile: 1.782443380355835
95th percentile: 1.8660729408264158
99th percentile: 1.9329765892028807
mean time: 1.3241695880889892
Pipeline stage StressChecker completed in 7.98s
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 0.75s
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 0.68s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_7200_v1 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 2380.65s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_7200_v1 status is now inactive due to auto deactivation removed underperforming models