developer_uid: azuruce
submission_id: chaiml-espresso-llama-24_7737_v1
model_name: chaiml-espresso-llama-24_7737_v1
model_group: ChaiML/espresso_llama_24
status: inactive
timestamp: 2024-12-04T17:05:43+00:00
num_battles: 17772
num_wins: 8429
celo_rating: 1244.78
family_friendly_score: 0.5878
family_friendly_standard_error: 0.006961194725045407
submission_type: basic
model_repo: ChaiML/espresso_llama_241204_albert_v1
model_architecture: MistralForCausalLM
model_num_parameters: 22247282688.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.3902309954371971, 'latency_mean': 2.562498383522034, 'latency_p50': 2.551735997200012, 'latency_p90': 2.862570571899414}, {'batch_size': 3, 'throughput': 0.8244098743024094, 'latency_mean': 3.6276393914222718, 'latency_p50': 3.6307733058929443, 'latency_p90': 4.023322510719299}, {'batch_size': 5, 'throughput': 1.0886624638836482, 'latency_mean': 4.565535749197006, 'latency_p50': 4.558944463729858, 'latency_p90': 5.189053535461426}, {'batch_size': 6, 'throughput': 1.1743340408486427, 'latency_mean': 5.073320192098618, 'latency_p50': 5.076887249946594, 'latency_p90': 5.61307270526886}, {'batch_size': 10, 'throughput': 1.39257246785094, 'latency_mean': 7.108261491060257, 'latency_p50': 7.080124497413635, 'latency_p90': 8.006571412086487}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-espresso-llama-24_7737_v1
is_internal_developer: True
language_model: ChaiML/espresso_llama_241204_albert_v1
model_size: 22B
ranking_group: single
throughput_3p7s: 0.85
us_pacific_date: 2024-12-04
win_ratio: 0.4742853927526446
generation_params: {'temperature': 0.9, '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-llama-24-7737-v1-mkmlizer
Waiting for job on chaiml-espresso-llama-24-7737-v1-mkmlizer to finish
chaiml-espresso-llama-24-7737-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-espresso-llama-24-7737-v1-mkmlizer: ║ _____ __ __ ║
chaiml-espresso-llama-24-7737-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-espresso-llama-24-7737-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-espresso-llama-24-7737-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-espresso-llama-24-7737-v1-mkmlizer: ║ /___/ ║
chaiml-espresso-llama-24-7737-v1-mkmlizer: ║ ║
chaiml-espresso-llama-24-7737-v1-mkmlizer: ║ Version: 0.11.12 ║
chaiml-espresso-llama-24-7737-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-espresso-llama-24-7737-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-espresso-llama-24-7737-v1-mkmlizer: ║ ║
chaiml-espresso-llama-24-7737-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-espresso-llama-24-7737-v1-mkmlizer: ║ belonging to: ║
chaiml-espresso-llama-24-7737-v1-mkmlizer: ║ ║
chaiml-espresso-llama-24-7737-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-espresso-llama-24-7737-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-espresso-llama-24-7737-v1-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
chaiml-espresso-llama-24-7737-v1-mkmlizer: ║ ║
chaiml-espresso-llama-24-7737-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-espresso-llama-24-7737-v1-mkmlizer: Downloaded to shared memory in 92.570s
chaiml-espresso-llama-24-7737-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpcal43qtv, device:0
chaiml-espresso-llama-24-7737-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-espresso-llama-24-7737-v1-mkmlizer: quantized model in 58.700s
chaiml-espresso-llama-24-7737-v1-mkmlizer: Processed model ChaiML/espresso_llama_241204_albert_v1 in 151.270s
chaiml-espresso-llama-24-7737-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-espresso-llama-24-7737-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-espresso-llama-24-7737-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-espresso-llama-24-7737-v1
chaiml-espresso-llama-24-7737-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-espresso-llama-24-7737-v1/config.json
chaiml-espresso-llama-24-7737-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-espresso-llama-24-7737-v1/special_tokens_map.json
chaiml-espresso-llama-24-7737-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-espresso-llama-24-7737-v1/tokenizer_config.json
chaiml-espresso-llama-24-7737-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-espresso-llama-24-7737-v1/tokenizer.json
chaiml-espresso-llama-24-7737-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-espresso-llama-24-7737-v1/flywheel_model.1.safetensors
chaiml-espresso-llama-24-7737-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-espresso-llama-24-7737-v1/flywheel_model.0.safetensors
chaiml-espresso-llama-24-7737-v1-mkmlizer: Loading 0: 0%| | 0/507 [00:00<?, ?it/s] Loading 0: 1%| | 5/507 [00:00<00:21, 22.85it/s] Loading 0: 2%|▏ | 10/507 [00:00<00:15, 32.99it/s] Loading 0: 3%|▎ | 14/507 [00:00<00:16, 29.16it/s] Loading 0: 4%|▍ | 21/507 [00:00<00:12, 39.11it/s] Loading 0: 5%|▌ | 26/507 [00:00<00:12, 37.49it/s] Loading 0: 6%|▌ | 30/507 [00:00<00:12, 37.99it/s] Loading 0: 7%|▋ | 34/507 [00:00<00:13, 35.84it/s] Loading 0: 8%|▊ | 39/507 [00:01<00:12, 38.35it/s] Loading 0: 8%|▊ | 43/507 [00:01<00:12, 36.83it/s] Loading 0: 9%|▉ | 47/507 [00:01<00:12, 36.60it/s] Loading 0: 10%|█ | 51/507 [00:01<00:13, 34.67it/s] Loading 0: 11%|█ | 55/507 [00:01<00:20, 22.05it/s] Loading 0: 11%|█▏ | 58/507 [00:01<00:19, 23.02it/s] Loading 0: 12%|█▏ | 61/507 [00:02<00:18, 24.44it/s] Loading 0: 13%|█▎ | 65/507 [00:02<00:18, 24.12it/s] Loading 0: 14%|█▍ | 71/507 [00:02<00:13, 31.58it/s] Loading 0: 15%|█▍ | 75/507 [00:02<00:13, 33.10it/s] Loading 0: 16%|█▌ | 80/507 [00:02<00:13, 32.24it/s] Loading 0: 17%|█▋ | 85/507 [00:02<00:11, 35.34it/s] Loading 0: 18%|█▊ | 89/507 [00:02<00:13, 30.86it/s] Loading 0: 19%|█▉ | 96/507 [00:02<00:11, 37.01it/s] Loading 0: 20%|█▉ | 100/507 [00:03<00:11, 35.33it/s] Loading 0: 21%|██ | 105/507 [00:03<00:10, 37.25it/s] Loading 0: 21%|██▏ | 109/507 [00:03<00:11, 34.70it/s] Loading 0: 22%|██▏ | 113/507 [00:03<00:16, 23.56it/s] Loading 0: 23%|██▎ | 116/507 [00:03<00:17, 21.77it/s] Loading 0: 24%|██▍ | 122/507 [00:04<00:15, 24.61it/s] Loading 0: 25%|██▌ | 127/507 [00:04<00:13, 28.34it/s] Loading 0: 26%|██▌ | 131/507 [00:04<00:14, 26.03it/s] Loading 0: 27%|██▋ | 136/507 [00:04<00:12, 29.87it/s] Loading 0: 28%|██▊ | 140/507 [00:04<00:13, 27.29it/s] Loading 0: 29%|██▊ | 145/507 [00:04<00:11, 30.86it/s] Loading 0: 29%|██▉ | 149/507 [00:04<00:12, 27.92it/s] Loading 0: 30%|███ | 154/507 [00:05<00:11, 31.34it/s] Loading 0: 31%|███ | 158/507 [00:05<00:12, 28.34it/s] Loading 0: 32%|███▏ | 163/507 [00:05<00:10, 32.08it/s] Loading 0: 33%|███▎ | 168/507 [00:05<00:10, 33.03it/s] Loading 0: 34%|███▍ | 172/507 [00:05<00:15, 22.17it/s] Loading 0: 35%|███▍ | 176/507 [00:06<00:14, 22.70it/s] Loading 0: 36%|███▌ | 181/507 [00:06<00:11, 27.32it/s] Loading 0: 36%|███▋ | 185/507 [00:06<00:12, 26.23it/s] Loading 0: 37%|███▋ | 190/507 [00:06<00:10, 30.52it/s] Loading 0: 38%|███▊ | 194/507 [00:06<00:10, 28.61it/s] Loading 0: 39%|███▉ | 199/507 [00:06<00:09, 32.89it/s] Loading 0: 40%|████ | 203/507 [00:06<00:10, 29.46it/s] Loading 0: 41%|████▏ | 210/507 [00:06<00:08, 36.34it/s] Loading 0: 42%|████▏ | 214/507 [00:07<00:08, 34.43it/s] Loading 0: 43%|████▎ | 218/507 [00:07<00:08, 33.70it/s] Loading 0: 44%|████▍ | 222/507 [00:07<00:08, 32.64it/s] Loading 0: 45%|████▍ | 226/507 [00:07<00:12, 22.85it/s] Loading 0: 45%|████▌ | 230/507 [00:07<00:12, 22.02it/s] Loading 0: 46%|████▋ | 235/507 [00:07<00:10, 26.20it/s] Loading 0: 47%|████▋ | 239/507 [00:08<00:10, 24.98it/s] Loading 0: 48%|████▊ | 244/507 [00:08<00:08, 29.65it/s] Loading 0: 49%|████▉ | 248/507 [00:08<00:09, 27.37it/s] Loading 0: 50%|████▉ | 253/507 [00:08<00:08, 31.70it/s] Loading 0: 51%|█████ | 257/507 [00:08<00:09, 27.43it/s] Loading 0: 52%|█████▏ | 262/507 [00:08<00:08, 30.53it/s] Loading 0: 52%|█████▏ | 266/507 [00:09<00:08, 27.73it/s] Loading 0: 53%|█████▎ | 271/507 [00:09<00:07, 31.43it/s] Loading 0: 54%|█████▍ | 275/507 [00:09<00:08, 28.68it/s] Loading 0: 55%|█████▌ | 280/507 [00:09<00:06, 32.73it/s] Loading 0: 56%|█████▌ | 284/507 [00:09<00:09, 23.44it/s] Loading 0: 57%|█████▋ | 287/507 [00:09<00:10, 21.69it/s] Loading 0: 58%|█████▊ | 293/507 [00:10<00:08, 24.65it/s] Loading 0: 59%|█████▉ | 298/507 [00:10<00:07, 28.72it/s] Loading 0: 59%|█████▉ | 299/507 [00:26<00:07, 28.72it/s] Loading 0: 59%|█████▉ | 300/507 [00:32<05:53, 1.71s/it] Loading 0: 60%|█████▉ | 302/507 [00:32<04:49, 1.41s/it] Loading 0: 61%|██████ | 307/507 [00:32<02:54, 1.15it/s] Loading 0: 61%|██████ | 310/507 [00:32<02:11, 1.50it/s] Loading 0: 62%|██████▏ | 313/507 [00:32<01:36, 2.00it/s] Loading 0: 63%|██████▎ | 318/507 [00:32<00:59, 3.17it/s] Loading 0: 64%|██████▎ | 322/507 [00:32<00:42, 4.37it/s] Loading 0: 64%|██████▍ | 327/507 [00:32<00:28, 6.40it/s] Loading 0: 65%|██████▌ | 331/507 [00:33<00:21, 8.29it/s] Loading 0: 66%|██████▌ | 335/507 [00:33<00:16, 10.64it/s] Loading 0: 67%|██████▋ | 340/507 [00:33<00:13, 12.56it/s] Loading 0: 68%|██████▊ | 343/507 [00:33<00:11, 14.06it/s] Loading 0: 68%|██████▊ | 347/507 [00:33<00:09, 16.19it/s] Loading 0: 70%|██████▉ | 354/507 [00:33<00:06, 23.35it/s] Loading 0: 71%|███████ | 358/507 [00:34<00:05, 24.87it/s] Loading 0: 72%|███████▏ | 363/507 [00:34<00:05, 28.60it/s] Loading 0: 72%|███████▏ | 367/507 [00:34<00:04, 29.05it/s] Loading 0: 73%|███████▎ | 371/507 [00:34<00:04, 31.35it/s] Loading 0: 74%|███████▍ | 375/507 [00:34<00:04, 29.32it/s] Loading 0: 75%|███████▌ | 381/507 [00:34<00:03, 34.81it/s] Loading 0: 76%|███████▌ | 385/507 [00:34<00:03, 34.05it/s] Loading 0: 77%|███████▋ | 389/507 [00:34<00:03, 34.58it/s] Loading 0: 78%|███████▊ | 393/507 [00:34<00:03, 33.75it/s] Loading 0: 78%|███████▊ | 397/507 [00:35<00:04, 24.71it/s] Loading 0: 79%|███████▉ | 401/507 [00:35<00:04, 24.90it/s] Loading 0: 80%|████████ | 406/507 [00:35<00:03, 29.58it/s] Loading 0: 81%|████████ | 410/507 [00:35<00:03, 27.30it/s] Loading 0: 82%|████████▏ | 415/507 [00:35<00:02, 31.52it/s] Loading 0: 83%|████████▎ | 419/507 [00:35<00:03, 28.86it/s] Loading 0: 84%|████████▎ | 424/507 [00:36<00:02, 33.31it/s] Loading 0: 84%|████████▍ | 428/507 [00:36<00:02, 30.42it/s] Loading 0: 85%|████████▌ | 433/507 [00:36<00:02, 34.29it/s] Loading 0: 86%|████████▌ | 437/507 [00:36<00:02, 31.25it/s] Loading 0: 88%|████████▊ | 444/507 [00:36<00:01, 37.79it/s] Loading 0: 88%|████████▊ | 448/507 [00:36<00:01, 35.46it/s] Loading 0: 89%|████████▉ | 453/507 [00:36<00:01, 38.31it/s] Loading 0: 90%|█████████ | 457/507 [00:39<00:08, 5.77it/s] Loading 0: 91%|█████████ | 460/507 [00:39<00:06, 6.86it/s] Loading 0: 92%|█████████▏| 465/507 [00:39<00:04, 9.25it/s] Loading 0: 93%|█████████▎| 472/507 [00:39<00:02, 13.90it/s] Loading 0: 94%|█████████▍| 476/507 [00:39<00:01, 15.99it/s] Loading 0: 95%|█████████▍| 481/507 [00:39<00:01, 19.62it/s] Loading 0: 96%|█████████▌| 485/507 [00:40<00:01, 21.43it/s] Loading 0: 97%|█████████▋| 490/507 [00:40<00:00, 24.77it/s] Loading 0: 97%|█████████▋| 494/507 [00:40<00:00, 25.61it/s] Loading 0: 98%|█████████▊| 499/507 [00:40<00:00, 28.43it/s] Loading 0: 99%|█████████▉| 503/507 [00:40<00:00, 28.27it/s]
Job chaiml-espresso-llama-24-7737-v1-mkmlizer completed after 186.28s with status: succeeded
Stopping job with name chaiml-espresso-llama-24-7737-v1-mkmlizer
Pipeline stage MKMLizer completed in 187.17s
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-espresso-llama-24-7737-v1
Waiting for inference service chaiml-espresso-llama-24-7737-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
Inference service chaiml-espresso-llama-24-7737-v1 ready after 220.74752640724182s
Pipeline stage MKMLDeployer completed in 221.38s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.345057725906372s
Received healthy response to inference request in 2.3938770294189453s
Received healthy response to inference request in 3.0460832118988037s
Received healthy response to inference request in 2.2119219303131104s
Received healthy response to inference request in 2.395639181137085s
5 requests
0 failed requests
5th percentile: 2.2483129501342773
10th percentile: 2.2847039699554443
20th percentile: 2.3574860095977783
30th percentile: 2.394229459762573
40th percentile: 2.394934320449829
50th percentile: 2.395639181137085
60th percentile: 2.6558167934417725
70th percentile: 2.91599440574646
80th percentile: 3.1058781147003174
90th percentile: 3.2254679203033447
95th percentile: 3.2852628231048584
99th percentile: 3.3330987453460694
mean time: 2.678515815734863
Pipeline stage StressChecker completed in 14.84s
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 2.14s
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 2.21s
Shutdown handler de-registered
chaiml-espresso-llama-24_7737_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 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-espresso-llama-24-7737-v1-profiler
Waiting for inference service chaiml-espresso-llama-24-7737-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 3157.83s
Shutdown handler de-registered
chaiml-espresso-llama-24_7737_v1 status is now inactive due to auto deactivation removed underperforming models