chaiml-small-espresso-an_6112

developer_uid: azuruce

submission_id: chaiml-small-espresso-an_6112_v7

model_name: chaiml-small-espresso-an_6112_v7

model_group: ChaiML/small_espresso_an

status: inactive

timestamp: 2024-12-06T16:04:35+00:00

num_battles: 10419

num_wins: 5255

celo_rating: 1263.96

family_friendly_score: 0.5838

family_friendly_standard_error: 0.006971048127792549

submission_type: basic

model_repo: ChaiML/small_espresso_ant_llama_story_241205_albert_v1_sft-3e128a

model_architecture: MistralForCausalLM

model_num_parameters: 22247282688.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.3858724198336426, 'latency_mean': 2.59146915435791, 'latency_p50': 2.59769606590271, 'latency_p90': 2.8518298864364624}, {'batch_size': 3, 'throughput': 0.8184443656445841, 'latency_mean': 3.6645659863948823, 'latency_p50': 3.68444287776947, 'latency_p90': 4.095801877975464}, {'batch_size': 5, 'throughput': 1.0802279676232114, 'latency_mean': 4.600421317815781, 'latency_p50': 4.583832144737244, 'latency_p90': 5.159563446044921}, {'batch_size': 6, 'throughput': 1.1649849061924178, 'latency_mean': 5.1067952108383174, 'latency_p50': 5.079091310501099, 'latency_p90': 5.7683041334152225}, {'batch_size': 10, 'throughput': 1.3905050528970337, 'latency_mean': 7.122155205011368, 'latency_p50': 7.084546446800232, 'latency_p90': 7.996819734573364}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-small-espresso-an_6112_v7

is_internal_developer: True

language_model: ChaiML/small_espresso_ant_llama_story_241205_albert_v1_sft-3e128a

model_size: 22B

ranking_group: single

throughput_3p7s: 0.83

us_pacific_date: 2024-12-06

win_ratio: 0.5043670217871197

generation_params: {'temperature': 0.8, '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-small-espresso-an-6112-v7-mkmlizer
Waiting for job on chaiml-small-espresso-an-6112-v7-mkmlizer to finish
chaiml-small-espresso-an-6112-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-small-espresso-an-6112-v7-mkmlizer: ║     _____            __           __                                ║
chaiml-small-espresso-an-6112-v7-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-small-espresso-an-6112-v7-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-small-espresso-an-6112-v7-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-small-espresso-an-6112-v7-mkmlizer: ║       /___/                                                         ║
chaiml-small-espresso-an-6112-v7-mkmlizer: ║                                                                     ║
chaiml-small-espresso-an-6112-v7-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-small-espresso-an-6112-v7-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-small-espresso-an-6112-v7-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-small-espresso-an-6112-v7-mkmlizer: ║                                                                     ║
chaiml-small-espresso-an-6112-v7-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-small-espresso-an-6112-v7-mkmlizer: ║  belonging to:                                                      ║
chaiml-small-espresso-an-6112-v7-mkmlizer: ║                                                                     ║
chaiml-small-espresso-an-6112-v7-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-small-espresso-an-6112-v7-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-small-espresso-an-6112-v7-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-small-espresso-an-6112-v7-mkmlizer: ║                                                                     ║
chaiml-small-espresso-an-6112-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-small-espresso-an-6112-v7-mkmlizer: Downloaded to shared memory in 47.182s
chaiml-small-espresso-an-6112-v7-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpmrs_wuwe, device:0
chaiml-small-espresso-an-6112-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-small-espresso-an-6112-v7-mkmlizer: quantized model in 48.600s
chaiml-small-espresso-an-6112-v7-mkmlizer: Processed model ChaiML/small_espresso_ant_llama_story_241205_albert_v1_sft-3e128a in 95.782s
chaiml-small-espresso-an-6112-v7-mkmlizer: creating bucket guanaco-mkml-models
chaiml-small-espresso-an-6112-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-small-espresso-an-6112-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-small-espresso-an-6112-v7
chaiml-small-espresso-an-6112-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-small-espresso-an-6112-v7/special_tokens_map.json
chaiml-small-espresso-an-6112-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-small-espresso-an-6112-v7/config.json
chaiml-small-espresso-an-6112-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-small-espresso-an-6112-v7/tokenizer_config.json
chaiml-small-espresso-an-6112-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-small-espresso-an-6112-v7/tokenizer.json
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-small-espresso-an-6112-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-small-espresso-an-6112-v7/flywheel_model.1.safetensors
chaiml-small-espresso-an-6112-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-small-espresso-an-6112-v7/flywheel_model.0.safetensors
chaiml-small-espresso-an-6112-v7-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:19, 26.18it/s]
Loading 0:   2%|▏         | 10/507 [00:00<00:14, 35.16it/s]
Loading 0:   3%|▎         | 14/507 [00:00<00:17, 28.09it/s]
Loading 0:   4%|▎         | 19/507 [00:00<00:15, 31.83it/s]
Loading 0:   5%|▍         | 23/507 [00:00<00:18, 26.83it/s]
Loading 0:   6%|▌         | 28/507 [00:00<00:15, 31.06it/s]
Loading 0:   6%|▋         | 32/507 [00:01<00:16, 28.46it/s]
Loading 0:   7%|▋         | 37/507 [00:01<00:14, 31.83it/s]
Loading 0:   8%|▊         | 41/507 [00:01<00:16, 28.68it/s]
Loading 0:   9%|▉         | 46/507 [00:01<00:14, 32.83it/s]
Loading 0:  10%|▉         | 50/507 [00:01<00:15, 28.90it/s]
Loading 0:  11%|█         | 54/507 [00:02<00:22, 20.03it/s]
Loading 0:  11%|█         | 57/507 [00:02<00:22, 19.97it/s]
Loading 0:  12%|█▏        | 61/507 [00:02<00:19, 22.81it/s]
Loading 0:  13%|█▎        | 65/507 [00:02<00:19, 22.28it/s]
Loading 0:  14%|█▍        | 70/507 [00:02<00:16, 26.68it/s]
Loading 0:  15%|█▍        | 75/507 [00:02<00:14, 29.82it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:14, 30.05it/s]
Loading 0:  17%|█▋        | 85/507 [00:03<00:12, 33.60it/s]
Loading 0:  18%|█▊        | 89/507 [00:03<00:13, 30.53it/s]
Loading 0:  19%|█▊        | 94/507 [00:03<00:11, 34.64it/s]
Loading 0:  19%|█▉        | 98/507 [00:03<00:13, 30.87it/s]
Loading 0:  20%|██        | 103/507 [00:03<00:11, 34.18it/s]
Loading 0:  21%|██        | 107/507 [00:03<00:13, 30.15it/s]
Loading 0:  22%|██▏       | 112/507 [00:03<00:12, 32.27it/s]
Loading 0:  23%|██▎       | 116/507 [00:04<00:18, 21.43it/s]
Loading 0:  24%|██▍       | 122/507 [00:04<00:15, 24.48it/s]
Loading 0:  25%|██▌       | 127/507 [00:04<00:13, 28.72it/s]
Loading 0:  26%|██▌       | 131/507 [00:04<00:13, 27.06it/s]
Loading 0:  27%|██▋       | 136/507 [00:04<00:12, 30.48it/s]
Loading 0:  28%|██▊       | 140/507 [00:04<00:13, 28.02it/s]
Loading 0:  29%|██▊       | 145/507 [00:05<00:11, 32.43it/s]
Loading 0:  29%|██▉       | 149/507 [00:05<00:12, 29.07it/s]
Loading 0:  30%|███       | 154/507 [00:05<00:10, 33.05it/s]
Loading 0:  31%|███       | 158/507 [00:05<00:11, 30.80it/s]
Loading 0:  32%|███▏      | 164/507 [00:05<00:09, 35.61it/s]
Loading 0:  33%|███▎      | 169/507 [00:05<00:12, 28.16it/s]
Loading 0:  34%|███▍      | 173/507 [00:06<00:11, 29.24it/s]
Loading 0:  35%|███▍      | 177/507 [00:06<00:11, 28.36it/s]
Loading 0:  36%|███▌      | 181/507 [00:06<00:10, 30.55it/s]
Loading 0:  36%|███▋      | 185/507 [00:06<00:10, 29.62it/s]
Loading 0:  37%|███▋      | 190/507 [00:06<00:09, 34.28it/s]
Loading 0:  38%|███▊      | 194/507 [00:06<00:10, 31.09it/s]
Loading 0:  40%|███▉      | 201/507 [00:06<00:08, 37.84it/s]
Loading 0:  40%|████      | 205/507 [00:06<00:08, 36.69it/s]
Loading 0:  41%|████▏     | 210/507 [00:07<00:07, 38.93it/s]
Loading 0:  42%|████▏     | 215/507 [00:07<00:07, 38.86it/s]
Loading 0:  43%|████▎     | 219/507 [00:07<00:09, 31.36it/s]
Loading 0:  44%|████▍     | 224/507 [00:07<00:10, 26.29it/s]
Loading 0:  45%|████▌     | 230/507 [00:07<00:10, 27.56it/s]
Loading 0:  47%|████▋     | 237/507 [00:07<00:08, 33.70it/s]
Loading 0:  48%|████▊     | 241/507 [00:08<00:07, 33.34it/s]
Loading 0:  49%|████▊     | 246/507 [00:08<00:07, 35.29it/s]
Loading 0:  49%|████▉     | 250/507 [00:08<00:07, 34.25it/s]
Loading 0:  50%|█████     | 255/507 [00:08<00:06, 36.25it/s]
Loading 0:  51%|█████     | 259/507 [00:08<00:07, 34.81it/s]
Loading 0:  52%|█████▏    | 264/507 [00:08<00:06, 36.58it/s]
Loading 0:  53%|█████▎    | 268/507 [00:08<00:06, 34.99it/s]
Loading 0:  54%|█████▍    | 273/507 [00:08<00:06, 36.95it/s]
Loading 0:  55%|█████▍    | 277/507 [00:09<00:06, 35.14it/s]
Loading 0:  56%|█████▌    | 283/507 [00:09<00:06, 36.29it/s]
Loading 0:  57%|█████▋    | 287/507 [00:09<00:09, 24.03it/s]
Loading 0:  58%|█████▊    | 293/507 [00:09<00:07, 27.42it/s]
Loading 0:  59%|█████▉    | 299/507 [00:20<00:07, 27.42it/s]
Loading 0:  59%|█████▉    | 300/507 [00:25<02:54,  1.19it/s]
Loading 0:  60%|█████▉    | 302/507 [00:25<02:32,  1.35it/s]
Loading 0:  61%|██████    | 307/507 [00:25<01:43,  1.94it/s]
Loading 0:  61%|██████    | 310/507 [00:25<01:21,  2.42it/s]
Loading 0:  62%|██████▏   | 313/507 [00:25<01:02,  3.08it/s]
Loading 0:  63%|██████▎   | 318/507 [00:25<00:40,  4.62it/s]
Loading 0:  64%|██████▎   | 322/507 [00:25<00:30,  6.16it/s]
Loading 0:  64%|██████▍   | 327/507 [00:26<00:20,  8.69it/s]
Loading 0:  65%|██████▌   | 331/507 [00:26<00:16, 10.61it/s]
Loading 0:  66%|██████▌   | 335/507 [00:26<00:13, 12.86it/s]
Loading 0:  67%|██████▋   | 339/507 [00:26<00:10, 15.77it/s]
Loading 0:  68%|██████▊   | 343/507 [00:26<00:11, 13.75it/s]
Loading 0:  68%|██████▊   | 347/507 [00:27<00:10, 15.43it/s]
Loading 0:  69%|██████▉   | 352/507 [00:27<00:07, 20.01it/s]
Loading 0:  70%|███████   | 356/507 [00:27<00:07, 21.15it/s]
Loading 0:  71%|███████   | 361/507 [00:27<00:05, 25.48it/s]
Loading 0:  72%|███████▏  | 365/507 [00:27<00:05, 23.96it/s]
Loading 0:  73%|███████▎  | 370/507 [00:27<00:05, 27.31it/s]
Loading 0:  74%|███████▍  | 374/507 [00:27<00:05, 25.15it/s]
Loading 0:  75%|███████▍  | 379/507 [00:28<00:04, 28.50it/s]
Loading 0:  76%|███████▌  | 383/507 [00:28<00:04, 26.34it/s]
Loading 0:  77%|███████▋  | 388/507 [00:28<00:03, 30.03it/s]
Loading 0:  77%|███████▋  | 392/507 [00:28<00:04, 27.20it/s]
Loading 0:  78%|███████▊  | 395/507 [00:28<00:05, 19.05it/s]
Loading 0:  79%|███████▉  | 400/507 [00:28<00:04, 24.28it/s]
Loading 0:  80%|███████▉  | 404/507 [00:29<00:04, 25.58it/s]
Loading 0:  80%|████████  | 408/507 [00:29<00:03, 26.21it/s]
Loading 0:  81%|████████  | 411/507 [00:29<00:03, 24.87it/s]
Loading 0:  82%|████████▏ | 415/507 [00:29<00:03, 27.33it/s]
Loading 0:  83%|████████▎ | 419/507 [00:29<00:03, 26.27it/s]
Loading 0:  84%|████████▎ | 424/507 [00:29<00:02, 31.34it/s]
Loading 0:  84%|████████▍ | 428/507 [00:29<00:02, 29.48it/s]
Loading 0:  86%|████████▌ | 435/507 [00:30<00:01, 36.85it/s]
Loading 0:  87%|████████▋ | 439/507 [00:30<00:01, 35.58it/s]
Loading 0:  88%|████████▊ | 444/507 [00:30<00:01, 37.32it/s]
Loading 0:  88%|████████▊ | 448/507 [00:30<00:01, 35.33it/s]
Loading 0:  89%|████████▉ | 452/507 [00:30<00:01, 36.49it/s]
Loading 0:  90%|████████▉ | 456/507 [00:33<00:10,  4.96it/s]
Loading 0:  91%|█████████ | 459/507 [00:33<00:08,  5.94it/s]
Loading 0:  92%|█████████▏| 465/507 [00:33<00:04,  8.74it/s]
Loading 0:  93%|█████████▎| 470/507 [00:33<00:03, 11.48it/s]
Loading 0:  93%|█████████▎| 474/507 [00:33<00:02, 12.78it/s]
Loading 0:  94%|█████████▍| 479/507 [00:33<00:01, 16.49it/s]
Loading 0:  95%|█████████▌| 483/507 [00:34<00:01, 18.00it/s]
Loading 0:  96%|█████████▋| 488/507 [00:34<00:00, 22.22it/s]
Loading 0:  97%|█████████▋| 492/507 [00:34<00:00, 22.19it/s]
Loading 0:  98%|█████████▊| 497/507 [00:34<00:00, 26.87it/s]
Loading 0:  99%|█████████▉| 501/507 [00:34<00:00, 26.10it/s]
Loading 0: 100%|██████████| 507/507 [00:34<00:00, 32.95it/s]
                                                            
Job chaiml-small-espresso-an-6112-v7-mkmlizer completed after 141.58s with status: succeeded
Stopping job with name chaiml-small-espresso-an-6112-v7-mkmlizer
Pipeline stage MKMLizer completed in 143.36s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-small-espresso-an-6112-v7
Waiting for inference service chaiml-small-espresso-an-6112-v7 to be ready
Inference service chaiml-small-espresso-an-6112-v7 ready after 190.58644914627075s
Pipeline stage MKMLDeployer completed in 192.35s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.152416467666626s
Received healthy response to inference request in 2.6448569297790527s
Received healthy response to inference request in 2.287630558013916s
Received healthy response to inference request in 4.2483742237091064s
Received healthy response to inference request in 2.338613510131836s
5 requests
0 failed requests
5th percentile: 2.2978271484375
10th percentile: 2.308023738861084
20th percentile: 2.328416919708252
30th percentile: 2.399862194061279
40th percentile: 2.522359561920166
50th percentile: 2.6448569297790527
60th percentile: 2.847880744934082
70th percentile: 3.050904560089111
80th percentile: 3.371608018875122
90th percentile: 3.8099911212921143
95th percentile: 4.02918267250061
99th percentile: 4.204535913467407
mean time: 2.9343783378601076
Pipeline stage StressChecker completed in 15.99s
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 2.15s
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 1.99s
Shutdown handler de-registered
chaiml-small-espresso-an_6112_v7 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 3146.38s
Shutdown handler de-registered
chaiml-small-espresso-an_6112_v7 status is now inactive due to auto deactivation removed underperforming models