chaiml-espresso-ant-lla_1666

developer_uid: azuruce

submission_id: chaiml-espresso-ant-lla_1666_v14

model_name: chaiml-espresso-ant-lla_1666_v14

model_group: ChaiML/espresso_ant_llam

status: inactive

timestamp: 2024-12-05T16:29:51+00:00

num_battles: 17914

num_wins: 8894

celo_rating: 1261.21

family_friendly_score: 0.5826

family_friendly_standard_error: 0.006973911958148023

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': 0.38445835101611975, 'latency_mean': 2.6009899842739106, 'latency_p50': 2.597294569015503, 'latency_p90': 2.872824716567993}, {'batch_size': 3, 'throughput': 0.8079120835389505, 'latency_mean': 3.7038720381259918, 'latency_p50': 3.690438747406006, 'latency_p90': 4.043907618522644}, {'batch_size': 5, 'throughput': 1.0792055339151305, 'latency_mean': 4.612319989204407, 'latency_p50': 4.62248957157135, 'latency_p90': 5.10529408454895}, {'batch_size': 6, 'throughput': 1.1563742098916634, 'latency_mean': 5.1560853683948515, 'latency_p50': 5.150220155715942, 'latency_p90': 5.730830335617066}, {'batch_size': 10, 'throughput': 1.3607068436917882, 'latency_mean': 7.273992900848389, 'latency_p50': 7.2380690574646, 'latency_p90': 8.191890406608582}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-espresso-ant-lla_1666_v14

is_internal_developer: True

language_model: ChaiML/espresso_ant_llama_241204_albert_v2_sft_2epoch_128alpha

model_size: 22B

ranking_group: single

throughput_3p7s: 0.81

us_pacific_date: 2024-12-05

win_ratio: 0.49648319749916264

generation_params: {'temperature': 0.82, '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-v14-mkmlizer
Waiting for job on chaiml-espresso-ant-lla-1666-v14-mkmlizer to finish
chaiml-espresso-ant-lla-1666-v14-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-espresso-ant-lla-1666-v14-mkmlizer: ║     _____            __           __                                ║
chaiml-espresso-ant-lla-1666-v14-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-espresso-ant-lla-1666-v14-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-espresso-ant-lla-1666-v14-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-espresso-ant-lla-1666-v14-mkmlizer: ║       /___/                                                         ║
chaiml-espresso-ant-lla-1666-v14-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-lla-1666-v14-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-espresso-ant-lla-1666-v14-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-espresso-ant-lla-1666-v14-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-espresso-ant-lla-1666-v14-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-lla-1666-v14-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-espresso-ant-lla-1666-v14-mkmlizer: ║  belonging to:                                                      ║
chaiml-espresso-ant-lla-1666-v14-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-lla-1666-v14-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-espresso-ant-lla-1666-v14-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-espresso-ant-lla-1666-v14-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-espresso-ant-lla-1666-v14-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-lla-1666-v14-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-espresso-ant-lla-1666-v14-mkmlizer: Downloaded to shared memory in 47.647s
chaiml-espresso-ant-lla-1666-v14-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpln3mspur, device:0
chaiml-espresso-ant-lla-1666-v14-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-espresso-ant-lla-1666-v14-mkmlizer: quantized model in 43.062s
chaiml-espresso-ant-lla-1666-v14-mkmlizer: Processed model ChaiML/espresso_ant_llama_241204_albert_v2_sft_2epoch_128alpha in 90.709s
chaiml-espresso-ant-lla-1666-v14-mkmlizer: creating bucket guanaco-mkml-models
chaiml-espresso-ant-lla-1666-v14-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-espresso-ant-lla-1666-v14-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-espresso-ant-lla-1666-v14
chaiml-espresso-ant-lla-1666-v14-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-espresso-ant-lla-1666-v14/config.json
chaiml-espresso-ant-lla-1666-v14-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-espresso-ant-lla-1666-v14/special_tokens_map.json
chaiml-espresso-ant-lla-1666-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-espresso-ant-lla-1666-v14/tokenizer_config.json
chaiml-espresso-ant-lla-1666-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-espresso-ant-lla-1666-v14/tokenizer.json
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
chaiml-espresso-ant-lla-1666-v14-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-lla-1666-v14/flywheel_model.1.safetensors
chaiml-espresso-ant-lla-1666-v14-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-lla-1666-v14/flywheel_model.0.safetensors
chaiml-espresso-ant-lla-1666-v14-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:20, 23.97it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:12, 40.88it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:12, 39.80it/s]
Loading 0:   4%|▍         | 22/507 [00:00<00:11, 40.79it/s]
Loading 0:   5%|▌         | 27/507 [00:00<00:11, 42.72it/s]
Loading 0:   6%|▋         | 32/507 [00:00<00:13, 36.02it/s]
Loading 0:   8%|▊         | 39/507 [00:00<00:10, 43.79it/s]
Loading 0:   9%|▊         | 44/507 [00:01<00:10, 43.30it/s]
Loading 0:  10%|▉         | 49/507 [00:01<00:12, 36.93it/s]
Loading 0:  10%|█         | 53/507 [00:01<00:16, 27.57it/s]
Loading 0:  11%|█         | 57/507 [00:01<00:16, 27.39it/s]
Loading 0:  12%|█▏        | 63/507 [00:01<00:13, 32.55it/s]
Loading 0:  13%|█▎        | 67/507 [00:01<00:13, 32.89it/s]
Loading 0:  14%|█▍        | 73/507 [00:02<00:12, 35.47it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:11, 36.80it/s]
Loading 0:  17%|█▋        | 87/507 [00:02<00:10, 41.51it/s]
Loading 0:  18%|█▊        | 92/507 [00:02<00:10, 40.62it/s]
Loading 0:  19%|█▉        | 97/507 [00:02<00:10, 40.10it/s]
Loading 0:  20%|██        | 102/507 [00:02<00:09, 40.73it/s]
Loading 0:  21%|██        | 107/507 [00:02<00:11, 34.90it/s]
Loading 0:  22%|██▏       | 113/507 [00:03<00:12, 31.07it/s]
Loading 0:  23%|██▎       | 117/507 [00:03<00:13, 28.94it/s]
Loading 0:  24%|██▍       | 121/507 [00:03<00:12, 30.82it/s]
Loading 0:  25%|██▍       | 125/507 [00:03<00:11, 32.55it/s]
Loading 0:  25%|██▌       | 129/507 [00:03<00:11, 34.30it/s]
Loading 0:  26%|██▌       | 133/507 [00:03<00:10, 34.09it/s]
Loading 0:  27%|██▋       | 138/507 [00:03<00:09, 37.74it/s]
Loading 0:  28%|██▊       | 142/507 [00:03<00:09, 36.84it/s]
Loading 0:  29%|██▉       | 147/507 [00:04<00:09, 39.40it/s]
Loading 0:  30%|██▉       | 152/507 [00:04<00:09, 39.01it/s]
Loading 0:  31%|███       | 157/507 [00:04<00:08, 40.13it/s]
Loading 0:  32%|███▏      | 162/507 [00:04<00:08, 42.38it/s]
Loading 0:  33%|███▎      | 167/507 [00:04<00:07, 44.08it/s]
Loading 0:  34%|███▍      | 172/507 [00:04<00:12, 27.55it/s]
Loading 0:  35%|███▍      | 176/507 [00:05<00:12, 26.52it/s]
Loading 0:  36%|███▌      | 181/507 [00:05<00:10, 30.57it/s]
Loading 0:  36%|███▋      | 185/507 [00:05<00:10, 29.31it/s]
Loading 0:  38%|███▊      | 192/507 [00:05<00:08, 37.13it/s]
Loading 0:  39%|███▉      | 197/507 [00:05<00:08, 37.40it/s]
Loading 0:  40%|███▉      | 202/507 [00:05<00:07, 38.59it/s]
Loading 0:  41%|████      | 207/507 [00:05<00:07, 41.24it/s]
Loading 0:  42%|████▏     | 212/507 [00:05<00:08, 35.65it/s]
Loading 0:  43%|████▎     | 218/507 [00:06<00:07, 40.13it/s]
Loading 0:  44%|████▍     | 223/507 [00:06<00:07, 37.37it/s]
Loading 0:  45%|████▍     | 227/507 [00:06<00:08, 31.32it/s]
Loading 0:  46%|████▌     | 231/507 [00:06<00:09, 29.73it/s]
Loading 0:  47%|████▋     | 237/507 [00:06<00:07, 34.99it/s]
Loading 0:  48%|████▊     | 241/507 [00:06<00:07, 35.17it/s]
Loading 0:  49%|████▊     | 246/507 [00:06<00:06, 37.47it/s]
Loading 0:  49%|████▉     | 250/507 [00:07<00:06, 36.73it/s]
Loading 0:  50%|█████     | 255/507 [00:07<00:06, 39.23it/s]
Loading 0:  51%|█████▏    | 260/507 [00:07<00:06, 39.30it/s]
Loading 0:  52%|█████▏    | 265/507 [00:07<00:06, 39.16it/s]
Loading 0:  53%|█████▎    | 269/507 [00:07<00:06, 38.45it/s]
Loading 0:  54%|█████▍    | 274/507 [00:07<00:05, 39.42it/s]
Loading 0:  55%|█████▍    | 278/507 [00:07<00:06, 37.65it/s]
Loading 0:  56%|█████▌    | 283/507 [00:07<00:05, 38.21it/s]
Loading 0:  57%|█████▋    | 287/507 [00:08<00:08, 24.96it/s]
Loading 0:  58%|█████▊    | 293/507 [00:08<00:07, 28.32it/s]
Loading 0:  59%|█████▉    | 299/507 [00:22<00:07, 28.32it/s]
Loading 0:  59%|█████▉    | 300/507 [00:22<02:46,  1.25it/s]
Loading 0:  60%|█████▉    | 302/507 [00:22<02:24,  1.42it/s]
Loading 0:  61%|██████    | 307/507 [00:23<01:37,  2.05it/s]
Loading 0:  61%|██████    | 310/507 [00:23<01:17,  2.55it/s]
Loading 0:  62%|██████▏   | 314/507 [00:23<00:55,  3.50it/s]
Loading 0:  63%|██████▎   | 319/507 [00:23<00:36,  5.10it/s]
Loading 0:  64%|██████▎   | 323/507 [00:23<00:27,  6.74it/s]
Loading 0:  65%|██████▍   | 328/507 [00:23<00:19,  9.38it/s]
Loading 0:  65%|██████▌   | 332/507 [00:23<00:14, 11.90it/s]
Loading 0:  66%|██████▋   | 337/507 [00:23<00:10, 15.86it/s]
Loading 0:  67%|██████▋   | 342/507 [00:24<00:10, 15.38it/s]
Loading 0:  68%|██████▊   | 347/507 [00:24<00:08, 18.56it/s]
Loading 0:  70%|██████▉   | 354/507 [00:24<00:05, 25.55it/s]
Loading 0:  71%|███████   | 359/507 [00:24<00:05, 28.41it/s]
Loading 0:  72%|███████▏  | 364/507 [00:24<00:04, 31.38it/s]
Loading 0:  73%|███████▎  | 369/507 [00:24<00:03, 34.60it/s]
Loading 0:  74%|███████▍  | 374/507 [00:25<00:04, 32.25it/s]
Loading 0:  75%|███████▌  | 382/507 [00:25<00:03, 40.24it/s]
Loading 0:  77%|███████▋  | 388/507 [00:25<00:02, 40.20it/s]
Loading 0:  78%|███████▊  | 393/507 [00:25<00:02, 38.69it/s]
Loading 0:  79%|███████▊  | 398/507 [00:25<00:03, 32.55it/s]
Loading 0:  79%|███████▉  | 402/507 [00:25<00:03, 30.71it/s]
Loading 0:  80%|████████  | 408/507 [00:25<00:02, 35.33it/s]
Loading 0:  81%|████████▏ | 412/507 [00:26<00:02, 34.98it/s]
Loading 0:  82%|████████▏ | 417/507 [00:26<00:02, 37.71it/s]
Loading 0:  83%|████████▎ | 421/507 [00:26<00:02, 35.21it/s]
Loading 0:  84%|████████▍ | 426/507 [00:26<00:02, 37.46it/s]
Loading 0:  85%|████████▍ | 430/507 [00:26<00:02, 37.02it/s]
Loading 0:  86%|████████▌ | 435/507 [00:26<00:01, 40.08it/s]
Loading 0:  87%|████████▋ | 440/507 [00:26<00:01, 40.96it/s]
Loading 0:  88%|████████▊ | 445/507 [00:26<00:01, 41.67it/s]
Loading 0:  89%|████████▉ | 450/507 [00:26<00:01, 43.83it/s]
Loading 0:  90%|████████▉ | 455/507 [00:29<00:07,  6.52it/s]
Loading 0:  91%|█████████ | 459/507 [00:29<00:05,  8.10it/s]
Loading 0:  92%|█████████▏| 465/507 [00:29<00:03, 11.26it/s]
Loading 0:  93%|█████████▎| 472/507 [00:29<00:02, 16.15it/s]
Loading 0:  94%|█████████▍| 477/507 [00:29<00:01, 19.24it/s]
Loading 0:  95%|█████████▌| 482/507 [00:29<00:01, 22.64it/s]
Loading 0:  96%|█████████▌| 487/507 [00:30<00:00, 26.54it/s]
Loading 0:  97%|█████████▋| 492/507 [00:30<00:00, 26.40it/s]
Loading 0:  98%|█████████▊| 499/507 [00:30<00:00, 33.36it/s]
Loading 0:  99%|█████████▉| 504/507 [00:30<00:00, 34.82it/s]
                                                            
Job chaiml-espresso-ant-lla-1666-v14-mkmlizer completed after 131.71s with status: succeeded
Stopping job with name chaiml-espresso-ant-lla-1666-v14-mkmlizer
Pipeline stage MKMLizer completed in 132.98s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-espresso-ant-lla-1666-v14
Waiting for inference service chaiml-espresso-ant-lla-1666-v14 to be ready
Inference service chaiml-espresso-ant-lla-1666-v14 ready after 174.8276002407074s
Pipeline stage MKMLDeployer completed in 176.62s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.0051252841949463s
Received healthy response to inference request in 2.260692834854126s
Received healthy response to inference request in 2.3239989280700684s
Received healthy response to inference request in 2.3576858043670654s
Received healthy response to inference request in 2.3763234615325928s
5 requests
0 failed requests
5th percentile: 2.2733540534973145
10th percentile: 2.286015272140503
20th percentile: 2.31133770942688
30th percentile: 2.3307363033294677
40th percentile: 2.344211053848267
50th percentile: 2.3576858043670654
60th percentile: 2.3651408672332765
70th percentile: 2.372595930099487
80th percentile: 2.5020838260650637
90th percentile: 2.753604555130005
95th percentile: 2.8793649196624753
99th percentile: 2.9799732112884523
mean time: 2.46476526260376
Pipeline stage StressChecker completed in 13.56s
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 2.20s
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 2.09s
Shutdown handler de-registered
chaiml-espresso-ant-lla_1666_v14 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 3247.56s
Shutdown handler de-registered
chaiml-espresso-ant-lla_1666_v14 status is now inactive due to auto deactivation removed underperforming models