developer_uid: azuruce
submission_id: chaiml-nemo-espresso-sto_6854_v3
model_name: chaiml-nemo-espresso-sto_6854_v3
model_group: ChaiML/nemo-espresso_sto
status: inactive
timestamp: 2024-12-06T02:25:05+00:00
num_battles: 7856
num_wins: 4145
celo_rating: 1282.91
family_friendly_score: 0.571
family_friendly_standard_error: 0.006999414261207862
submission_type: basic
model_repo: ChaiML/nemo-espresso_story_241205_albert_v1_sft_2epoch_128alpha
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6100453229731913, 'latency_mean': 1.6391267454624177, 'latency_p50': 1.6462925672531128, 'latency_p90': 1.8159889459609986}, {'batch_size': 3, 'throughput': 1.1009790782386624, 'latency_mean': 2.717414493560791, 'latency_p50': 2.726663589477539, 'latency_p90': 2.959580183029175}, {'batch_size': 5, 'throughput': 1.3263859276111918, 'latency_mean': 3.752459406852722, 'latency_p50': 3.7297340631484985, 'latency_p90': 4.2511824607849125}, {'batch_size': 6, 'throughput': 1.3946828193015293, 'latency_mean': 4.281468813419342, 'latency_p50': 4.310077667236328, 'latency_p90': 4.749601984024047}, {'batch_size': 8, 'throughput': 1.4537269219923123, 'latency_mean': 5.476007736921311, 'latency_p50': 5.429688334465027, 'latency_p90': 6.075672626495361}, {'batch_size': 10, 'throughput': 1.480539931144528, 'latency_mean': 6.704445499181747, 'latency_p50': 6.731319785118103, 'latency_p90': 7.51242733001709}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-nemo-espresso-sto_6854_v3
is_internal_developer: True
language_model: ChaiML/nemo-espresso_story_241205_albert_v1_sft_2epoch_128alpha
model_size: 13B
ranking_group: single
throughput_3p7s: 1.32
us_pacific_date: 2024-12-05
win_ratio: 0.527622199592668
generation_params: {'temperature': 0.8, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>', '<|end_of_text|>', 'You:'], 'max_input_tokens': 1024, 'best_of': 8, '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-nemo-espresso-sto-6854-v3-mkmlizer
Waiting for job on chaiml-nemo-espresso-sto-6854-v3-mkmlizer to finish
chaiml-nemo-espresso-sto-6854-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-espresso-sto-6854-v3-mkmlizer: ║ _____ __ __ ║
chaiml-nemo-espresso-sto-6854-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-nemo-espresso-sto-6854-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-nemo-espresso-sto-6854-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-nemo-espresso-sto-6854-v3-mkmlizer: ║ /___/ ║
chaiml-nemo-espresso-sto-6854-v3-mkmlizer: ║ ║
chaiml-nemo-espresso-sto-6854-v3-mkmlizer: ║ Version: 0.11.12 ║
chaiml-nemo-espresso-sto-6854-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-nemo-espresso-sto-6854-v3-mkmlizer: ║ https://mk1.ai ║
chaiml-nemo-espresso-sto-6854-v3-mkmlizer: ║ ║
chaiml-nemo-espresso-sto-6854-v3-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-nemo-espresso-sto-6854-v3-mkmlizer: ║ belonging to: ║
chaiml-nemo-espresso-sto-6854-v3-mkmlizer: ║ ║
chaiml-nemo-espresso-sto-6854-v3-mkmlizer: ║ Chai Research Corp. ║
chaiml-nemo-espresso-sto-6854-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-nemo-espresso-sto-6854-v3-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
chaiml-nemo-espresso-sto-6854-v3-mkmlizer: ║ ║
chaiml-nemo-espresso-sto-6854-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-espresso-sto-6854-v3-mkmlizer: Downloaded to shared memory in 37.809s
chaiml-nemo-espresso-sto-6854-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmprr9pno7h, device:0
chaiml-nemo-espresso-sto-6854-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-espresso-sto-6854-v3-mkmlizer: quantized model in 36.283s
chaiml-nemo-espresso-sto-6854-v3-mkmlizer: Processed model ChaiML/nemo-espresso_story_241205_albert_v1_sft_2epoch_128alpha in 74.093s
chaiml-nemo-espresso-sto-6854-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-espresso-sto-6854-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-espresso-sto-6854-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-espresso-sto-6854-v3
chaiml-nemo-espresso-sto-6854-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-espresso-sto-6854-v3/config.json
chaiml-nemo-espresso-sto-6854-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-espresso-sto-6854-v3/special_tokens_map.json
chaiml-nemo-espresso-sto-6854-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-espresso-sto-6854-v3/tokenizer_config.json
chaiml-nemo-espresso-sto-6854-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-espresso-sto-6854-v3/tokenizer.json
chaiml-nemo-espresso-sto-6854-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-espresso-sto-6854-v3/flywheel_model.0.safetensors
chaiml-nemo-espresso-sto-6854-v3-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:13, 26.44it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:07, 47.51it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 45.83it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:07, 44.59it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 51.03it/s] Loading 0: 10%|█ | 37/363 [00:00<00:06, 48.82it/s] Loading 0: 12%|█▏ | 43/363 [00:00<00:06, 49.59it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 51.58it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 48.43it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 35.85it/s] Loading 0: 18%|█▊ | 66/363 [00:01<00:08, 35.10it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 38.87it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:07, 40.21it/s] Loading 0: 23%|██▎ | 83/363 [00:01<00:06, 40.56it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:05, 45.72it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:06, 44.48it/s] Loading 0: 28%|██▊ | 101/363 [00:02<00:06, 42.81it/s] Loading 0: 30%|██▉ | 108/363 [00:02<00:05, 48.95it/s] Loading 0: 31%|███▏ | 114/363 [00:02<00:05, 44.31it/s] Loading 0: 33%|███▎ | 119/363 [00:02<00:05, 42.33it/s] Loading 0: 35%|███▍ | 126/363 [00:02<00:05, 46.74it/s] Loading 0: 36%|███▋ | 132/363 [00:03<00:05, 44.85it/s] Loading 0: 38%|███▊ | 137/363 [00:03<00:05, 44.12it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 34.15it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 34.60it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 33.74it/s] Loading 0: 43%|████▎ | 157/363 [00:03<00:05, 40.82it/s] Loading 0: 45%|████▍ | 163/363 [00:03<00:04, 41.48it/s] Loading 0: 46%|████▋ | 168/363 [00:03<00:04, 40.38it/s] Loading 0: 48%|████▊ | 173/363 [00:04<00:04, 42.22it/s] Loading 0: 49%|████▉ | 178/363 [00:04<00:04, 40.14it/s] Loading 0: 51%|█████ | 184/363 [00:04<00:04, 43.55it/s] Loading 0: 52%|█████▏ | 190/363 [00:04<00:04, 43.21it/s] Loading 0: 54%|█████▎ | 195/363 [00:04<00:03, 42.78it/s] Loading 0: 55%|█████▌ | 200/363 [00:04<00:03, 44.40it/s] Loading 0: 56%|█████▋ | 205/363 [00:04<00:03, 41.96it/s] Loading 0: 58%|█████▊ | 211/363 [00:04<00:03, 45.57it/s] Loading 0: 60%|█████▉ | 216/363 [00:05<00:03, 46.39it/s] Loading 0: 61%|██████ | 222/363 [00:05<00:03, 43.76it/s] Loading 0: 63%|██████▎ | 227/363 [00:05<00:04, 30.65it/s] Loading 0: 64%|██████▎ | 231/363 [00:05<00:04, 30.59it/s] Loading 0: 66%|██████▌ | 238/363 [00:05<00:03, 37.78it/s] Loading 0: 67%|██████▋ | 244/363 [00:05<00:03, 39.00it/s] Loading 0: 69%|██████▊ | 249/363 [00:06<00:02, 38.92it/s] Loading 0: 71%|███████ | 256/363 [00:06<00:02, 44.29it/s] Loading 0: 72%|███████▏ | 262/363 [00:06<00:02, 43.73it/s] Loading 0: 74%|███████▎ | 267/363 [00:06<00:02, 40.70it/s] Loading 0: 75%|███████▍ | 272/363 [00:06<00:02, 42.83it/s] Loading 0: 76%|███████▋ | 277/363 [00:06<00:02, 40.44it/s] Loading 0: 78%|███████▊ | 283/363 [00:06<00:01, 44.16it/s] Loading 0: 80%|███████▉ | 289/363 [00:06<00:01, 43.51it/s] Loading 0: 81%|████████ | 294/363 [00:07<00:01, 40.38it/s] Loading 0: 82%|████████▏ | 299/363 [00:07<00:01, 41.19it/s] Loading 0: 84%|████████▎ | 304/363 [00:14<00:24, 2.44it/s] Loading 0: 85%|████████▍ | 307/363 [00:14<00:18, 2.96it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:12, 4.21it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:06, 6.99it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:03, 9.49it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:02, 12.03it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 16.82it/s] Loading 0: 95%|█████████▍| 344/363 [00:14<00:00, 20.47it/s] Loading 0: 96%|█████████▌| 349/363 [00:15<00:00, 23.69it/s] Loading 0: 98%|█████████▊| 355/363 [00:15<00:00, 28.81it/s] Loading 0: 99%|█████████▉| 360/363 [00:15<00:00, 31.59it/s]
Job chaiml-nemo-espresso-sto-6854-v3-mkmlizer completed after 105.09s with status: succeeded
Stopping job with name chaiml-nemo-espresso-sto-6854-v3-mkmlizer
Pipeline stage MKMLizer completed in 107.62s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nemo-espresso-sto-6854-v3
Waiting for inference service chaiml-nemo-espresso-sto-6854-v3 to be ready
Failed to get response for submission chaiml-lexical-viral-v5a_3966_v3: ('http://chaiml-lexical-viral-v5a-3966-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:53184->127.0.0.1:8080: read: connection reset by peer\n')
Inference service chaiml-nemo-espresso-sto-6854-v3 ready after 188.57756805419922s
Pipeline stage MKMLDeployer completed in 191.74s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9128916263580322s
Received healthy response to inference request in 1.693627119064331s
Received healthy response to inference request in 1.834228277206421s
Received healthy response to inference request in 1.694974422454834s
Received healthy response to inference request in 1.7528369426727295s
5 requests
0 failed requests
5th percentile: 1.6938965797424317
10th percentile: 1.6941660404205323
20th percentile: 1.6947049617767334
30th percentile: 1.706546926498413
40th percentile: 1.7296919345855712
50th percentile: 1.7528369426727295
60th percentile: 1.785393476486206
70th percentile: 1.8179500102996826
80th percentile: 1.849960947036743
90th percentile: 1.8814262866973877
95th percentile: 1.89715895652771
99th percentile: 1.9097450923919679
mean time: 1.7777116775512696
Pipeline stage StressChecker completed in 10.07s
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 2.12s
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 1.94s
Shutdown handler de-registered
chaiml-nemo-espresso-sto_6854_v3 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 0.09s
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-nemo-espresso-sto-6854-v3-profiler
Waiting for inference service chaiml-nemo-espresso-sto-6854-v3-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 2459.50s
Shutdown handler de-registered
chaiml-nemo-espresso-sto_6854_v3 status is now inactive due to auto deactivation removed underperforming models