developer_uid: azuruce
submission_id: chaiml-espresso-ant-lla_1666_v11
model_name: chaiml-espresso-ant-lla_1666_v11
model_group: ChaiML/espresso_ant_llam
status: inactive
timestamp: 2024-12-05T08:53:53+00:00
num_battles: 9745
num_wins: 4869
celo_rating: 1264.34
family_friendly_score: 0.5862
family_friendly_standard_error: 0.006965192890365636
submission_type: basic
model_repo: ChaiML/espresso_ant_llama_241204_albert_v2_sft_2epoch_128alpha
model_architecture: MistralForCausalLM
model_num_parameters: 22247282688.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.3840951893327174, 'latency_mean': 2.6034587347507476, 'latency_p50': 2.600214123725891, 'latency_p90': 2.8691986322402956}, {'batch_size': 3, 'throughput': 0.8199753699910751, 'latency_mean': 3.642546570301056, 'latency_p50': 3.628066301345825, 'latency_p90': 4.044736671447754}, {'batch_size': 5, 'throughput': 1.0857782846688426, 'latency_mean': 4.5769969797134396, 'latency_p50': 4.5772916078567505, 'latency_p90': 5.169416975975037}, {'batch_size': 6, 'throughput': 1.1571234575560814, 'latency_mean': 5.134471005201339, 'latency_p50': 5.108373284339905, 'latency_p90': 5.725088000297546}, {'batch_size': 10, 'throughput': 1.368901692867278, 'latency_mean': 7.245184319019318, 'latency_p50': 7.244012117385864, 'latency_p90': 8.203548073768616}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-espresso-ant-lla_1666_v11
is_internal_developer: True
language_model: ChaiML/espresso_ant_llama_241204_albert_v2_sft_2epoch_128alpha
model_size: 22B
ranking_group: single
throughput_3p7s: 0.84
us_pacific_date: 2024-12-05
win_ratio: 0.49964084145715754
generation_params: {'temperature': 0.78, '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-espresso-ant-lla-1666-v11-mkmlizer
Waiting for job on chaiml-espresso-ant-lla-1666-v11-mkmlizer to finish
chaiml-espresso-ant-lla-1666-v11-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-espresso-ant-lla-1666-v11-mkmlizer: ║ _____ __ __ ║
chaiml-espresso-ant-lla-1666-v11-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-espresso-ant-lla-1666-v11-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-espresso-ant-lla-1666-v11-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-espresso-ant-lla-1666-v11-mkmlizer: ║ /___/ ║
chaiml-espresso-ant-lla-1666-v11-mkmlizer: ║ ║
chaiml-espresso-ant-lla-1666-v11-mkmlizer: ║ Version: 0.11.12 ║
chaiml-espresso-ant-lla-1666-v11-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-espresso-ant-lla-1666-v11-mkmlizer: ║ https://mk1.ai ║
chaiml-espresso-ant-lla-1666-v11-mkmlizer: ║ ║
chaiml-espresso-ant-lla-1666-v11-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-espresso-ant-lla-1666-v11-mkmlizer: ║ belonging to: ║
chaiml-espresso-ant-lla-1666-v11-mkmlizer: ║ ║
chaiml-espresso-ant-lla-1666-v11-mkmlizer: ║ Chai Research Corp. ║
chaiml-espresso-ant-lla-1666-v11-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-espresso-ant-lla-1666-v11-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
chaiml-espresso-ant-lla-1666-v11-mkmlizer: ║ ║
chaiml-espresso-ant-lla-1666-v11-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-espresso-ant-lla-1666-v11-mkmlizer: Downloaded to shared memory in 42.366s
chaiml-espresso-ant-lla-1666-v11-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpee00vh9q, device:0
chaiml-espresso-ant-lla-1666-v11-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-espresso-ant-lla-1666-v11-mkmlizer: quantized model in 45.755s
chaiml-espresso-ant-lla-1666-v11-mkmlizer: Processed model ChaiML/espresso_ant_llama_241204_albert_v2_sft_2epoch_128alpha in 88.121s
chaiml-espresso-ant-lla-1666-v11-mkmlizer: creating bucket guanaco-mkml-models
chaiml-espresso-ant-lla-1666-v11-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-espresso-ant-lla-1666-v11-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-espresso-ant-lla-1666-v11
chaiml-espresso-ant-lla-1666-v11-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-espresso-ant-lla-1666-v11/config.json
chaiml-espresso-ant-lla-1666-v11-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-espresso-ant-lla-1666-v11/special_tokens_map.json
chaiml-espresso-ant-lla-1666-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-espresso-ant-lla-1666-v11/tokenizer_config.json
chaiml-espresso-ant-lla-1666-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-espresso-ant-lla-1666-v11/tokenizer.json
chaiml-espresso-ant-lla-1666-v11-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-lla-1666-v11/flywheel_model.1.safetensors
chaiml-espresso-ant-lla-1666-v11-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-lla-1666-v11/flywheel_model.0.safetensors
chaiml-espresso-ant-lla-1666-v11-mkmlizer: Loading 0: 0%| | 0/507 [00:00<?, ?it/s] Loading 0: 1%| | 5/507 [00:00<00:19, 26.02it/s] Loading 0: 2%|▏ | 10/507 [00:00<00:14, 35.40it/s] Loading 0: 3%|▎ | 14/507 [00:00<00:16, 30.25it/s] Loading 0: 4%|▍ | 21/507 [00:00<00:12, 38.99it/s] Loading 0: 5%|▌ | 26/507 [00:00<00:12, 37.13it/s] Loading 0: 6%|▌ | 31/507 [00:00<00:12, 37.13it/s] Loading 0: 7%|▋ | 35/507 [00:00<00:13, 35.32it/s] Loading 0: 8%|▊ | 39/507 [00:01<00:12, 36.12it/s] Loading 0: 8%|▊ | 43/507 [00:01<00:13, 34.55it/s] Loading 0: 9%|▉ | 47/507 [00:01<00:13, 34.78it/s] Loading 0: 10%|█ | 51/507 [00:01<00:13, 33.80it/s] Loading 0: 11%|█ | 55/507 [00:01<00:19, 22.96it/s] Loading 0: 11%|█▏ | 58/507 [00:01<00:18, 24.13it/s] Loading 0: 12%|█▏ | 63/507 [00:02<00:15, 28.31it/s] Loading 0: 13%|█▎ | 67/507 [00:02<00:15, 28.85it/s] Loading 0: 14%|█▍ | 72/507 [00:02<00:13, 33.32it/s] Loading 0: 15%|█▌ | 78/507 [00:02<00:11, 38.27it/s] Loading 0: 16%|█▋ | 83/507 [00:02<00:11, 36.97it/s] Loading 0: 17%|█▋ | 87/507 [00:02<00:11, 36.58it/s] Loading 0: 18%|█▊ | 91/507 [00:02<00:11, 34.72it/s] Loading 0: 19%|█▉ | 96/507 [00:02<00:11, 36.38it/s] Loading 0: 20%|█▉ | 100/507 [00:03<00:11, 34.38it/s] Loading 0: 21%|██ | 105/507 [00:03<00:11, 35.69it/s] Loading 0: 21%|██▏ | 109/507 [00:03<00:11, 34.34it/s] Loading 0: 22%|██▏ | 113/507 [00:03<00:15, 25.50it/s] Loading 0: 23%|██▎ | 116/507 [00:03<00:16, 23.65it/s] Loading 0: 24%|██▍ | 122/507 [00:03<00:14, 27.16it/s] Loading 0: 25%|██▌ | 127/507 [00:03<00:11, 31.69it/s] Loading 0: 26%|██▌ | 131/507 [00:04<00:13, 28.66it/s] Loading 0: 27%|██▋ | 138/507 [00:04<00:10, 35.88it/s] Loading 0: 28%|██▊ | 142/507 [00:04<00:10, 34.66it/s] Loading 0: 29%|██▉ | 147/507 [00:04<00:09, 37.29it/s] Loading 0: 30%|██▉ | 151/507 [00:04<00:10, 34.77it/s] Loading 0: 31%|███ | 156/507 [00:04<00:09, 37.33it/s] Loading 0: 32%|███▏ | 160/507 [00:04<00:09, 34.83it/s] Loading 0: 32%|███▏ | 164/507 [00:04<00:09, 35.42it/s] Loading 0: 33%|███▎ | 169/507 [00:05<00:12, 28.06it/s] Loading 0: 34%|███▍ | 173/507 [00:05<00:11, 28.85it/s] Loading 0: 35%|███▍ | 177/507 [00:05<00:11, 28.10it/s] Loading 0: 36%|███▌ | 183/507 [00:05<00:09, 33.98it/s] Loading 0: 37%|███▋ | 187/507 [00:05<00:09, 33.49it/s] Loading 0: 38%|███▊ | 192/507 [00:05<00:08, 36.49it/s] Loading 0: 39%|███▊ | 196/507 [00:06<00:08, 34.56it/s] Loading 0: 40%|███▉ | 201/507 [00:06<00:08, 37.56it/s] Loading 0: 40%|████ | 205/507 [00:06<00:08, 35.96it/s] Loading 0: 41%|████▏ | 210/507 [00:06<00:07, 38.41it/s] Loading 0: 42%|████▏ | 214/507 [00:06<00:07, 36.66it/s] Loading 0: 43%|████▎ | 218/507 [00:06<00:07, 36.86it/s] Loading 0: 44%|████▍ | 222/507 [00:06<00:07, 36.13it/s] Loading 0: 45%|████▍ | 226/507 [00:06<00:10, 26.32it/s] Loading 0: 45%|████▌ | 230/507 [00:07<00:10, 26.04it/s] Loading 0: 47%|████▋ | 237/507 [00:07<00:08, 33.54it/s] Loading 0: 48%|████▊ | 241/507 [00:07<00:08, 33.21it/s] Loading 0: 49%|████▊ | 246/507 [00:07<00:07, 34.36it/s] Loading 0: 49%|████▉ | 250/507 [00:07<00:07, 33.26it/s] Loading 0: 50%|█████ | 255/507 [00:07<00:07, 35.70it/s] Loading 0: 51%|█████ | 259/507 [00:07<00:07, 34.40it/s] Loading 0: 52%|█████▏ | 264/507 [00:07<00:06, 36.86it/s] Loading 0: 53%|█████▎ | 268/507 [00:08<00:06, 35.47it/s] Loading 0: 54%|█████▍ | 273/507 [00:08<00:06, 37.69it/s] Loading 0: 55%|█████▍ | 277/507 [00:08<00:06, 35.42it/s] Loading 0: 56%|█████▌ | 283/507 [00:08<00:06, 37.24it/s] Loading 0: 57%|█████▋ | 287/507 [00:08<00:09, 24.02it/s] Loading 0: 58%|█████▊ | 293/507 [00:09<00:07, 27.18it/s] Loading 0: 59%|█████▉ | 299/507 [00:23<00:07, 27.18it/s] Loading 0: 59%|█████▉ | 300/507 [00:23<02:48, 1.23it/s] Loading 0: 60%|█████▉ | 302/507 [00:24<02:27, 1.39it/s] Loading 0: 61%|██████ | 307/507 [00:24<01:39, 2.01it/s] Loading 0: 61%|██████ | 310/507 [00:24<01:18, 2.50it/s] Loading 0: 62%|██████▏ | 314/507 [00:24<00:56, 3.42it/s] Loading 0: 63%|██████▎ | 318/507 [00:24<00:40, 4.67it/s] Loading 0: 64%|██████▎ | 322/507 [00:24<00:29, 6.23it/s] Loading 0: 64%|██████▍ | 327/507 [00:24<00:20, 8.83it/s] Loading 0: 65%|██████▌ | 331/507 [00:24<00:15, 11.03it/s] Loading 0: 66%|██████▌ | 335/507 [00:25<00:12, 13.51it/s] Loading 0: 67%|██████▋ | 339/507 [00:25<00:10, 16.74it/s] Loading 0: 68%|██████▊ | 343/507 [00:25<00:10, 15.09it/s] Loading 0: 68%|██████▊ | 347/507 [00:25<00:09, 16.96it/s] Loading 0: 70%|██████▉ | 354/507 [00:25<00:06, 24.06it/s] Loading 0: 71%|███████ | 358/507 [00:25<00:05, 25.17it/s] Loading 0: 72%|███████▏ | 363/507 [00:26<00:04, 28.89it/s] Loading 0: 72%|███████▏ | 367/507 [00:26<00:04, 28.30it/s] Loading 0: 73%|███████▎ | 372/507 [00:26<00:04, 31.38it/s] Loading 0: 74%|███████▍ | 376/507 [00:26<00:04, 31.09it/s] Loading 0: 75%|███████▌ | 381/507 [00:26<00:03, 33.89it/s] Loading 0: 76%|███████▌ | 385/507 [00:26<00:03, 32.86it/s] Loading 0: 77%|███████▋ | 389/507 [00:26<00:03, 33.15it/s] Loading 0: 78%|███████▊ | 393/507 [00:26<00:03, 32.44it/s] Loading 0: 78%|███████▊ | 397/507 [00:27<00:04, 24.05it/s] Loading 0: 79%|███████▉ | 401/507 [00:27<00:04, 24.01it/s] Loading 0: 80%|████████ | 408/507 [00:27<00:03, 31.01it/s] Loading 0: 81%|████████▏ | 412/507 [00:27<00:03, 30.45it/s] Loading 0: 82%|████████▏ | 417/507 [00:27<00:02, 33.03it/s] Loading 0: 83%|████████▎ | 421/507 [00:27<00:02, 30.89it/s] Loading 0: 84%|████████▍ | 426/507 [00:28<00:02, 32.85it/s] Loading 0: 85%|████████▍ | 430/507 [00:28<00:02, 31.82it/s] Loading 0: 86%|████████▌ | 435/507 [00:28<00:02, 34.24it/s] Loading 0: 87%|████████▋ | 439/507 [00:28<00:02, 32.82it/s] Loading 0: 88%|████████▊ | 444/507 [00:28<00:01, 34.83it/s] Loading 0: 88%|████████▊ | 448/507 [00:28<00:01, 33.28it/s] Loading 0: 89%|████████▉ | 453/507 [00:28<00:01, 36.80it/s] Loading 0: 90%|█████████ | 457/507 [00:31<00:08, 5.80it/s] Loading 0: 91%|█████████ | 460/507 [00:31<00:06, 6.97it/s] Loading 0: 92%|█████████▏| 465/507 [00:31<00:04, 9.41it/s] Loading 0: 93%|█████████▎| 470/507 [00:31<00:02, 12.80it/s] Loading 0: 93%|█████████▎| 474/507 [00:31<00:02, 14.65it/s] Loading 0: 95%|█████████▍| 481/507 [00:31<00:01, 20.69it/s] Loading 0: 96%|█████████▌| 485/507 [00:31<00:00, 22.41it/s] Loading 0: 97%|█████████▋| 490/507 [00:32<00:00, 26.15it/s] Loading 0: 97%|█████████▋| 494/507 [00:32<00:00, 27.58it/s] Loading 0: 98%|█████████▊| 499/507 [00:32<00:00, 31.25it/s] Loading 0: 99%|█████████▉| 503/507 [00:32<00:00, 31.35it/s]
Job chaiml-espresso-ant-lla-1666-v11-mkmlizer completed after 122.02s with status: succeeded
Stopping job with name chaiml-espresso-ant-lla-1666-v11-mkmlizer
Pipeline stage MKMLizer completed in 123.18s
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-espresso-ant-lla-1666-v11
Waiting for inference service chaiml-espresso-ant-lla-1666-v11 to be ready
Inference service chaiml-espresso-ant-lla-1666-v11 ready after 164.42822241783142s
Pipeline stage MKMLDeployer completed in 166.69s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.0194334983825684s
Received healthy response to inference request in 2.2322182655334473s
Received healthy response to inference request in 2.387134075164795s
Received healthy response to inference request in 2.59671688079834s
Received healthy response to inference request in 2.4459328651428223s
5 requests
0 failed requests
5th percentile: 2.263201427459717
10th percentile: 2.2941845893859862
20th percentile: 2.356150913238525
30th percentile: 2.3988938331604004
40th percentile: 2.4224133491516113
50th percentile: 2.4459328651428223
60th percentile: 2.506246471405029
70th percentile: 2.566560077667236
80th percentile: 2.6812602043151856
90th percentile: 2.8503468513488768
95th percentile: 2.9348901748657226
99th percentile: 3.002524833679199
mean time: 2.5362871170043944
Pipeline stage StressChecker completed in 14.03s
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 2.10s
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 2.05s
Shutdown handler de-registered
chaiml-espresso-ant-lla_1666_v11 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 3212.70s
Shutdown handler de-registered
chaiml-espresso-ant-lla_1666_v11 status is now inactive due to auto deactivation removed underperforming models