developer_uid: azuruce
submission_id: chaiml-mistral-nemo-dpo-_8396_v1
model_name: chaiml-mistral-nemo-dpo-_8396_v1
model_group: ChaiML/mistral_nemo_dpo_
status: torndown
timestamp: 2024-12-21T20:22:44+00:00
num_battles: 16278
num_wins: 7493
celo_rating: 1228.75
family_friendly_score: 0.5982000000000001
family_friendly_standard_error: 0.0069333507051064424
submission_type: basic
model_repo: ChaiML/mistral_nemo_dpo_round2_albert_20241220_v3-checkpoint-621
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6367009523191562, 'latency_mean': 1.570531109571457, 'latency_p50': 1.5646916627883911, 'latency_p90': 1.7359524965286255}, {'batch_size': 3, 'throughput': 1.2651562573040869, 'latency_mean': 2.364518918991089, 'latency_p50': 2.357005000114441, 'latency_p90': 2.5876393556594848}, {'batch_size': 5, 'throughput': 1.6022781842834222, 'latency_mean': 3.1097030460834505, 'latency_p50': 3.0965654850006104, 'latency_p90': 3.481790375709534}, {'batch_size': 6, 'throughput': 1.7020938166814974, 'latency_mean': 3.5132392048835754, 'latency_p50': 3.539265990257263, 'latency_p90': 3.917214560508728}, {'batch_size': 8, 'throughput': 1.862528229367555, 'latency_mean': 4.271529411077499, 'latency_p50': 4.302569508552551, 'latency_p90': 4.817303204536438}, {'batch_size': 10, 'throughput': 1.9444711843940339, 'latency_mean': 5.09785626411438, 'latency_p50': 5.077077746391296, 'latency_p90': 5.713291978836059}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-mistral-nemo-dpo-_8396_v1
is_internal_developer: True
language_model: ChaiML/mistral_nemo_dpo_round2_albert_20241220_v3-checkpoint-621
model_size: 13B
ranking_group: single
throughput_3p7s: 1.75
us_pacific_date: 2024-12-21
win_ratio: 0.4603145349551542
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-8396-v1-mkmlizer
Waiting for job on chaiml-mistral-nemo-dpo-8396-v1-mkmlizer to finish
chaiml-mistral-nemo-dpo-8396-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-dpo-8396-v1-mkmlizer: ║ _____ __ __ ║
chaiml-mistral-nemo-dpo-8396-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-mistral-nemo-dpo-8396-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-mistral-nemo-dpo-8396-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-mistral-nemo-dpo-8396-v1-mkmlizer: ║ /___/ ║
chaiml-mistral-nemo-dpo-8396-v1-mkmlizer: ║ ║
chaiml-mistral-nemo-dpo-8396-v1-mkmlizer: ║ Version: 0.11.12 ║
chaiml-mistral-nemo-dpo-8396-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-mistral-nemo-dpo-8396-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-mistral-nemo-dpo-8396-v1-mkmlizer: ║ ║
chaiml-mistral-nemo-dpo-8396-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-mistral-nemo-dpo-8396-v1-mkmlizer: ║ belonging to: ║
chaiml-mistral-nemo-dpo-8396-v1-mkmlizer: ║ ║
chaiml-mistral-nemo-dpo-8396-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-mistral-nemo-dpo-8396-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-mistral-nemo-dpo-8396-v1-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
chaiml-mistral-nemo-dpo-8396-v1-mkmlizer: ║ ║
chaiml-mistral-nemo-dpo-8396-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-dpo-8396-v1-mkmlizer: Downloaded to shared memory in 54.002s
chaiml-mistral-nemo-dpo-8396-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpv1_ee2fn, device:0
chaiml-mistral-nemo-dpo-8396-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-nemo-dpo-8396-v1-mkmlizer: quantized model in 37.206s
chaiml-mistral-nemo-dpo-8396-v1-mkmlizer: Processed model ChaiML/mistral_nemo_dpo_round2_albert_20241220_v3-checkpoint-621 in 91.208s
chaiml-mistral-nemo-dpo-8396-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-dpo-8396-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-dpo-8396-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-8396-v1
chaiml-mistral-nemo-dpo-8396-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-8396-v1/special_tokens_map.json
chaiml-mistral-nemo-dpo-8396-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-8396-v1/config.json
chaiml-mistral-nemo-dpo-8396-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-8396-v1/tokenizer_config.json
chaiml-mistral-nemo-dpo-8396-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-8396-v1/tokenizer.json
chaiml-mistral-nemo-dpo-8396-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-8396-v1/flywheel_model.0.safetensors
chaiml-mistral-nemo-dpo-8396-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:12, 27.71it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:07, 47.03it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 43.36it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:08, 41.72it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 48.11it/s] Loading 0: 10%|█ | 37/363 [00:00<00:07, 45.34it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 43.81it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 48.68it/s] Loading 0: 15%|█▍ | 54/363 [00:01<00:06, 48.85it/s] Loading 0: 17%|█▋ | 60/363 [00:01<00:06, 44.86it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:10, 29.56it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:08, 35.71it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:07, 37.40it/s] Loading 0: 23%|██▎ | 83/363 [00:02<00:07, 37.60it/s] Loading 0: 25%|██▍ | 89/363 [00:02<00:06, 41.23it/s] Loading 0: 26%|██▌ | 94/363 [00:02<00:06, 38.95it/s] Loading 0: 27%|██▋ | 99/363 [00:02<00:06, 39.81it/s] Loading 0: 29%|██▊ | 104/363 [00:02<00:06, 41.76it/s] Loading 0: 30%|███ | 110/363 [00:02<00:06, 40.22it/s] Loading 0: 32%|███▏ | 115/363 [00:02<00:05, 41.46it/s] Loading 0: 33%|███▎ | 120/363 [00:02<00:06, 39.89it/s] Loading 0: 35%|███▍ | 126/363 [00:03<00:05, 43.51it/s] Loading 0: 36%|███▌ | 131/363 [00:03<00:05, 42.19it/s] Loading 0: 37%|███▋ | 136/363 [00:03<00:06, 36.12it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:07, 30.83it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 31.80it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 31.07it/s] Loading 0: 43%|████▎ | 157/363 [00:04<00:05, 37.91it/s] Loading 0: 45%|████▍ | 162/363 [00:04<00:04, 40.50it/s] Loading 0: 46%|████▌ | 167/363 [00:04<00:05, 34.76it/s] Loading 0: 48%|████▊ | 174/363 [00:04<00:04, 42.14it/s] Loading 0: 49%|████▉ | 179/363 [00:04<00:04, 41.85it/s] Loading 0: 51%|█████ | 184/363 [00:04<00:04, 41.29it/s] Loading 0: 52%|█████▏ | 189/363 [00:04<00:04, 42.47it/s] Loading 0: 53%|█████▎ | 194/363 [00:04<00:04, 36.36it/s] Loading 0: 55%|█████▌ | 201/363 [00:05<00:03, 44.03it/s] Loading 0: 57%|█████▋ | 206/363 [00:05<00:03, 43.24it/s] Loading 0: 58%|█████▊ | 211/363 [00:05<00:03, 42.75it/s] Loading 0: 60%|█████▉ | 216/363 [00:05<00:03, 42.68it/s] Loading 0: 61%|██████ | 221/363 [00:05<00:03, 44.53it/s] Loading 0: 62%|██████▏ | 226/363 [00:05<00:05, 26.05it/s] Loading 0: 63%|██████▎ | 230/363 [00:06<00:04, 26.64it/s] Loading 0: 65%|██████▌ | 237/363 [00:06<00:03, 34.36it/s] Loading 0: 67%|██████▋ | 242/363 [00:06<00:03, 35.98it/s] Loading 0: 68%|██████▊ | 247/363 [00:06<00:03, 38.31it/s] Loading 0: 69%|██████▉ | 252/363 [00:06<00:02, 39.84it/s] Loading 0: 71%|███████ | 257/363 [00:06<00:03, 34.95it/s] Loading 0: 73%|███████▎ | 264/363 [00:06<00:02, 42.84it/s] Loading 0: 74%|███████▍ | 269/363 [00:06<00:02, 43.14it/s] Loading 0: 75%|███████▌ | 274/363 [00:07<00:02, 43.17it/s] Loading 0: 77%|███████▋ | 279/363 [00:07<00:01, 44.38it/s] Loading 0: 78%|███████▊ | 284/363 [00:07<00:02, 37.93it/s] Loading 0: 80%|████████ | 292/363 [00:07<00:01, 45.61it/s] Loading 0: 82%|████████▏ | 297/363 [00:07<00:01, 46.56it/s] Loading 0: 83%|████████▎ | 303/363 [00:07<00:01, 44.23it/s] Loading 0: 85%|████████▍ | 308/363 [00:14<00:21, 2.54it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:15, 3.24it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:08, 5.25it/s] Loading 0: 90%|████████▉ | 325/363 [00:14<00:05, 6.88it/s] Loading 0: 91%|█████████ | 330/363 [00:15<00:03, 8.67it/s] Loading 0: 93%|█████████▎| 338/363 [00:15<00:01, 13.11it/s] Loading 0: 95%|█████████▍| 344/363 [00:15<00:01, 16.40it/s] Loading 0: 96%|█████████▌| 349/363 [00:15<00:00, 19.44it/s] Loading 0: 98%|█████████▊| 356/363 [00:15<00:00, 25.31it/s] Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 28.53it/s]
Job chaiml-mistral-nemo-dpo-8396-v1-mkmlizer completed after 114.65s with status: succeeded
Stopping job with name chaiml-mistral-nemo-dpo-8396-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.24s
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-8396-v1
Waiting for inference service chaiml-mistral-nemo-dpo-8396-v1 to be ready
Inference service chaiml-mistral-nemo-dpo-8396-v1 ready after 251.7956783771515s
Pipeline stage MKMLDeployer completed in 252.34s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7794761657714844s
Received healthy response to inference request in 1.355226755142212s
Received healthy response to inference request in 1.3521482944488525s
Received healthy response to inference request in 0.5956432819366455s
Received healthy response to inference request in 1.5929365158081055s
5 requests
0 failed requests
5th percentile: 0.7469442844390869
10th percentile: 0.8982452869415283
20th percentile: 1.200847291946411
30th percentile: 1.3527639865875245
40th percentile: 1.3539953708648682
50th percentile: 1.355226755142212
60th percentile: 1.4503106594085693
70th percentile: 1.5453945636749267
80th percentile: 1.6302444458007812
90th percentile: 1.704860305786133
95th percentile: 1.7421682357788086
99th percentile: 1.7720145797729492
mean time: 1.33508620262146
Pipeline stage StressChecker completed in 8.02s
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 0.89s
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 0.62s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_8396_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-8396-v1-profiler
Waiting for inference service chaiml-mistral-nemo-dpo-8396-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 2426.35s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_8396_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral-nemo-dpo-_8396_v1 status is now torndown due to DeploymentManager action
chaiml-mistral-nemo-dpo-_8396_v1 status is now torndown due to DeploymentManager action
chaiml-mistral-nemo-dpo-_8396_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1