chaiml-espresso-ant-llam_1666

developer_uid: azuruce

submission_id: chaiml-espresso-ant-llam_1666_v3

model_name: chaiml-espresso-ant-llam_1666_v3

model_group: ChaiML/espresso_ant_llam

status: inactive

timestamp: 2024-12-05T07:07:43+00:00

num_battles: 11650

num_wins: 6022

celo_rating: 1273.35

family_friendly_score: 0.5842

family_friendly_standard_error: 0.006970084074098389

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: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.3831167936697748, 'latency_mean': 2.610112638473511, 'latency_p50': 2.5818307399749756, 'latency_p90': 2.8993101596832274}, {'batch_size': 2, 'throughput': 0.6009484451229241, 'latency_mean': 3.3169574975967406, 'latency_p50': 3.317296862602234, 'latency_p90': 3.653500485420227}, {'batch_size': 3, 'throughput': 0.7687752124849093, 'latency_mean': 3.89379278421402, 'latency_p50': 3.8988348245620728, 'latency_p90': 4.296667122840882}, {'batch_size': 4, 'throughput': 0.8819221592774587, 'latency_mean': 4.507758861780166, 'latency_p50': 4.501532316207886, 'latency_p90': 4.992909216880799}, {'batch_size': 5, 'throughput': 0.9764977928302645, 'latency_mean': 5.0957891917228695, 'latency_p50': 5.071410179138184, 'latency_p90': 5.737205219268799}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-espresso-ant-llam_1666_v3

is_internal_developer: True

language_model: ChaiML/espresso_ant_llama_241204_albert_v2_sft_2epoch_128alpha

model_size: 22B

ranking_group: single

throughput_3p7s: 0.72

us_pacific_date: 2024-12-04

win_ratio: 0.5169098712446352

generation_params: {'temperature': 0.9, '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-espresso-ant-llam-1666-v3-mkmlizer
Waiting for job on chaiml-espresso-ant-llam-1666-v3-mkmlizer to finish
chaiml-espresso-ant-llam-1666-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-espresso-ant-llam-1666-v3-mkmlizer: ║     _____            __           __                                ║
chaiml-espresso-ant-llam-1666-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-espresso-ant-llam-1666-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-espresso-ant-llam-1666-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-espresso-ant-llam-1666-v3-mkmlizer: ║       /___/                                                         ║
chaiml-espresso-ant-llam-1666-v3-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-1666-v3-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-espresso-ant-llam-1666-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-espresso-ant-llam-1666-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-espresso-ant-llam-1666-v3-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-1666-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-espresso-ant-llam-1666-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-espresso-ant-llam-1666-v3-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-1666-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-espresso-ant-llam-1666-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-espresso-ant-llam-1666-v3-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-espresso-ant-llam-1666-v3-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-1666-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-espresso-ant-llam-1666-v3-mkmlizer: Downloaded to shared memory in 48.327s
chaiml-espresso-ant-llam-1666-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpnr4v2zfm, device:0
chaiml-espresso-ant-llam-1666-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-espresso-ant-llam-1666-v3-mkmlizer: quantized model in 43.106s
chaiml-espresso-ant-llam-1666-v3-mkmlizer: Processed model ChaiML/espresso_ant_llama_241204_albert_v2_sft_2epoch_128alpha in 91.433s
chaiml-espresso-ant-llam-1666-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-espresso-ant-llam-1666-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-espresso-ant-llam-1666-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v3
chaiml-espresso-ant-llam-1666-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v3/config.json
chaiml-espresso-ant-llam-1666-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v3/special_tokens_map.json
chaiml-espresso-ant-llam-1666-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v3/tokenizer_config.json
chaiml-espresso-ant-llam-1666-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v3/tokenizer.json
chaiml-espresso-ant-llam-1666-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v3/flywheel_model.1.safetensors
chaiml-espresso-ant-llam-1666-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v3/flywheel_model.0.safetensors
chaiml-espresso-ant-llam-1666-v3-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:19, 25.62it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:11, 42.47it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:12, 38.60it/s]
Loading 0:   4%|▍         | 22/507 [00:00<00:12, 40.32it/s]
Loading 0:   5%|▌         | 27/507 [00:00<00:11, 42.53it/s]
Loading 0:   6%|▋         | 32/507 [00:00<00:13, 35.04it/s]
Loading 0:   8%|▊         | 39/507 [00:00<00:10, 42.95it/s]
Loading 0:   9%|▊         | 44/507 [00:01<00:10, 42.55it/s]
Loading 0:  10%|▉         | 49/507 [00:01<00:12, 37.69it/s]
Loading 0:  11%|█         | 54/507 [00:01<00:15, 28.97it/s]
Loading 0:  11%|█▏        | 58/507 [00:01<00:15, 29.68it/s]
Loading 0:  12%|█▏        | 63/507 [00:01<00:13, 33.28it/s]
Loading 0:  13%|█▎        | 67/507 [00:01<00:13, 33.68it/s]
Loading 0:  14%|█▍        | 73/507 [00:02<00:11, 36.42it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:11, 37.77it/s]
Loading 0:  17%|█▋        | 87/507 [00:02<00:09, 43.09it/s]
Loading 0:  18%|█▊        | 92/507 [00:02<00:09, 41.82it/s]
Loading 0:  19%|█▉        | 97/507 [00:02<00:10, 40.91it/s]
Loading 0:  20%|██        | 102/507 [00:02<00:09, 42.35it/s]
Loading 0:  21%|██        | 107/507 [00:02<00:11, 36.18it/s]
Loading 0:  22%|██▏       | 113/507 [00:03<00:12, 30.82it/s]
Loading 0:  23%|██▎       | 117/507 [00:03<00:13, 29.73it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:12, 29.91it/s]
Loading 0:  25%|██▌       | 129/507 [00:03<00:10, 36.85it/s]
Loading 0:  26%|██▌       | 133/507 [00:03<00:10, 36.79it/s]
Loading 0:  27%|██▋       | 139/507 [00:03<00:09, 39.83it/s]
Loading 0:  28%|██▊       | 144/507 [00:03<00:08, 41.42it/s]
Loading 0:  29%|██▉       | 149/507 [00:04<00:09, 36.19it/s]
Loading 0:  31%|███       | 156/507 [00:04<00:08, 42.81it/s]
Loading 0:  32%|███▏      | 161/507 [00:04<00:08, 42.12it/s]
Loading 0:  33%|███▎      | 166/507 [00:04<00:07, 43.84it/s]
Loading 0:  34%|███▎      | 171/507 [00:04<00:12, 27.23it/s]
Loading 0:  35%|███▍      | 176/507 [00:04<00:11, 28.00it/s]
Loading 0:  36%|███▌      | 183/507 [00:05<00:09, 34.19it/s]
Loading 0:  37%|███▋      | 188/507 [00:05<00:09, 34.41it/s]
Loading 0:  38%|███▊      | 192/507 [00:05<00:08, 35.30it/s]
Loading 0:  39%|███▊      | 196/507 [00:05<00:09, 34.15it/s]
Loading 0:  40%|███▉      | 201/507 [00:05<00:08, 36.50it/s]
Loading 0:  40%|████      | 205/507 [00:05<00:08, 35.38it/s]
Loading 0:  41%|████▏     | 210/507 [00:05<00:07, 38.79it/s]
Loading 0:  42%|████▏     | 215/507 [00:05<00:07, 39.62it/s]
Loading 0:  43%|████▎     | 220/507 [00:06<00:08, 35.26it/s]
Loading 0:  44%|████▍     | 224/507 [00:06<00:10, 27.04it/s]
Loading 0:  45%|████▌     | 230/507 [00:06<00:09, 28.42it/s]
Loading 0:  47%|████▋     | 237/507 [00:06<00:07, 34.03it/s]
Loading 0:  48%|████▊     | 241/507 [00:06<00:08, 33.21it/s]
Loading 0:  49%|████▊     | 246/507 [00:06<00:07, 36.03it/s]
Loading 0:  49%|████▉     | 250/507 [00:07<00:07, 36.02it/s]
Loading 0:  50%|█████     | 255/507 [00:07<00:06, 38.61it/s]
Loading 0:  51%|█████▏    | 260/507 [00:07<00:06, 36.83it/s]
Loading 0:  52%|█████▏    | 264/507 [00:07<00:06, 36.63it/s]
Loading 0:  53%|█████▎    | 268/507 [00:07<00:07, 34.01it/s]
Loading 0:  54%|█████▍    | 273/507 [00:07<00:06, 35.71it/s]
Loading 0:  55%|█████▍    | 277/507 [00:07<00:06, 33.87it/s]
Loading 0:  56%|█████▌    | 283/507 [00:07<00:06, 36.10it/s]
Loading 0:  57%|█████▋    | 287/507 [00:08<00:09, 23.89it/s]
Loading 0:  58%|█████▊    | 293/507 [00:08<00:07, 26.90it/s]
Loading 0:  59%|█████▉    | 299/507 [00:23<00:07, 26.90it/s]
Loading 0:  59%|█████▉    | 300/507 [00:23<02:46,  1.24it/s]
Loading 0:  60%|█████▉    | 302/507 [00:23<02:25,  1.41it/s]
Loading 0:  61%|██████    | 307/507 [00:23<01:38,  2.04it/s]
Loading 0:  61%|██████    | 310/507 [00:23<01:17,  2.53it/s]
Loading 0:  62%|██████▏   | 315/507 [00:23<00:51,  3.72it/s]
Loading 0:  63%|██████▎   | 319/507 [00:23<00:37,  4.97it/s]
Loading 0:  64%|██████▍   | 325/507 [00:23<00:24,  7.41it/s]
Loading 0:  65%|██████▍   | 329/507 [00:24<00:19,  9.24it/s]
Loading 0:  66%|██████▌   | 335/507 [00:24<00:13, 13.21it/s]
Loading 0:  67%|██████▋   | 340/507 [00:24<00:11, 14.81it/s]
Loading 0:  68%|██████▊   | 344/507 [00:24<00:09, 16.97it/s]
Loading 0:  69%|██████▊   | 348/507 [00:24<00:08, 18.95it/s]
Loading 0:  70%|██████▉   | 354/507 [00:24<00:06, 24.82it/s]
Loading 0:  71%|███████   | 358/507 [00:24<00:05, 26.48it/s]
Loading 0:  72%|███████▏  | 363/507 [00:25<00:04, 30.77it/s]
Loading 0:  72%|███████▏  | 367/507 [00:25<00:04, 31.27it/s]
Loading 0:  73%|███████▎  | 372/507 [00:25<00:03, 35.46it/s]
Loading 0:  74%|███████▍  | 377/507 [00:25<00:03, 37.40it/s]
Loading 0:  75%|███████▌  | 382/507 [00:25<00:03, 38.80it/s]
Loading 0:  77%|███████▋  | 388/507 [00:25<00:03, 39.47it/s]
Loading 0:  78%|███████▊  | 393/507 [00:25<00:02, 38.72it/s]
Loading 0:  79%|███████▊  | 398/507 [00:25<00:03, 30.68it/s]
Loading 0:  79%|███████▉  | 402/507 [00:26<00:03, 29.12it/s]
Loading 0:  80%|████████  | 408/507 [00:26<00:02, 33.69it/s]
Loading 0:  81%|████████▏ | 412/507 [00:26<00:02, 33.96it/s]
Loading 0:  82%|████████▏ | 417/507 [00:26<00:02, 36.83it/s]
Loading 0:  83%|████████▎ | 421/507 [00:26<00:02, 36.71it/s]
Loading 0:  84%|████████▍ | 427/507 [00:26<00:02, 39.78it/s]
Loading 0:  85%|████████▌ | 432/507 [00:26<00:01, 41.53it/s]
Loading 0:  86%|████████▌ | 437/507 [00:27<00:01, 36.03it/s]
Loading 0:  88%|████████▊ | 445/507 [00:27<00:01, 43.67it/s]
Loading 0:  89%|████████▉ | 450/507 [00:27<00:01, 44.96it/s]
Loading 0:  90%|████████▉ | 455/507 [00:29<00:07,  7.10it/s]
Loading 0:  91%|█████████ | 459/507 [00:29<00:05,  8.59it/s]
Loading 0:  92%|█████████▏| 465/507 [00:29<00:03, 11.49it/s]
Loading 0:  93%|█████████▎| 472/507 [00:29<00:02, 16.12it/s]
Loading 0:  94%|█████████▍| 476/507 [00:30<00:01, 18.44it/s]
Loading 0:  95%|█████████▍| 481/507 [00:30<00:01, 22.46it/s]
Loading 0:  96%|█████████▌| 486/507 [00:30<00:00, 25.75it/s]
Loading 0:  97%|█████████▋| 491/507 [00:30<00:00, 28.59it/s]
Loading 0:  98%|█████████▊| 496/507 [00:30<00:00, 32.13it/s]
Loading 0:  99%|█████████▉| 501/507 [00:30<00:00, 29.80it/s]
                                                            
Job chaiml-espresso-ant-llam-1666-v3-mkmlizer completed after 121.53s with status: succeeded
Stopping job with name chaiml-espresso-ant-llam-1666-v3-mkmlizer
Connection pool is full, discarding connection: %s. Connection pool size: %s
Pipeline stage MKMLizer completed in 122.99s
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-espresso-ant-llam-1666-v3
Waiting for inference service chaiml-espresso-ant-llam-1666-v3 to be ready
Inference service chaiml-espresso-ant-llam-1666-v3 ready after 173.94551301002502s
Pipeline stage MKMLDeployer completed in 175.89s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.48439359664917s
Received healthy response to inference request in 2.374969005584717s
Received healthy response to inference request in 2.7592430114746094s
Received healthy response to inference request in 2.4887053966522217s
Received healthy response to inference request in 2.319918632507324s
5 requests
0 failed requests
5th percentile: 2.3309287071228026
10th percentile: 2.341938781738281
20th percentile: 2.3639589309692384
30th percentile: 2.3977162837982178
40th percentile: 2.4432108402252197
50th percentile: 2.4887053966522217
60th percentile: 2.596920442581177
70th percentile: 2.7051354885101317
80th percentile: 2.9042731285095216
90th percentile: 3.1943333625793455
95th percentile: 3.3393634796142577
99th percentile: 3.4553875732421875
mean time: 2.6854459285736083
Pipeline stage StressChecker completed in 14.78s
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 2.18s
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 2.02s
Shutdown handler de-registered
chaiml-espresso-ant-llam_1666_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 0.13s
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-espresso-ant-llam-1666-v3-profiler
Waiting for inference service chaiml-espresso-ant-llam-1666-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 3233.02s
Shutdown handler de-registered
chaiml-espresso-ant-llam_1666_v3 status is now inactive due to auto deactivation removed underperforming models