chaiml-small-anthropic-a_1700

submission_id: chaiml-small-anthropic-a_1700_v7

developer_uid: chai_backend_admin

best_of: 4

celo_rating: 1265.32

display_name: tempv1-3

family_friendly_score: 0.5862

family_friendly_standard_error: 0.006965192890365636

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}

generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, '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}

gpu_counts: {'NVIDIA RTX A6000': 1}

is_internal_developer: True

language_model: ChaiML/small_anthropic_addict_lexical_1120

latencies: [{'batch_size': 1, 'throughput': 0.38595656628309244, 'latency_mean': 2.5908868384361265, 'latency_p50': 2.5673632621765137, 'latency_p90': 2.8497071743011473}, {'batch_size': 3, 'throughput': 0.8192894441648745, 'latency_mean': 3.6543055212497713, 'latency_p50': 3.654271364212036, 'latency_p90': 4.006701326370239}, {'batch_size': 5, 'throughput': 1.0627652673595966, 'latency_mean': 4.673748799562454, 'latency_p50': 4.671144008636475, 'latency_p90': 5.274241471290589}, {'batch_size': 6, 'throughput': 1.1482721831365876, 'latency_mean': 5.186281419992447, 'latency_p50': 5.208114385604858, 'latency_p90': 5.841117310523987}, {'batch_size': 10, 'throughput': 1.375024005239819, 'latency_mean': 7.217440898418427, 'latency_p50': 7.203929543495178, 'latency_p90': 8.369555807113647}]

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: ChaiML/small_anthropic_a

model_name: tempv1-3

model_num_parameters: 22247282688.0

model_repo: ChaiML/small_anthropic_addict_lexical_1120

model_size: 22B

num_battles: 11251

num_wins: 5851

ranking_group: single

status: inactive

submission_type: basic

throughput_3p7s: 0.84

timestamp: 2024-11-19T12:45:15+00:00

us_pacific_date: 2024-11-19

win_ratio: 0.5200426628744111

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-anthropic-a-1700-v7-mkmlizer
Waiting for job on chaiml-small-anthropic-a-1700-v7-mkmlizer to finish
chaiml-small-anthropic-a-1700-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-small-anthropic-a-1700-v7-mkmlizer: ║     _____            __           __                                ║
chaiml-small-anthropic-a-1700-v7-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-small-anthropic-a-1700-v7-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-small-anthropic-a-1700-v7-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-small-anthropic-a-1700-v7-mkmlizer: ║       /___/                                                         ║
chaiml-small-anthropic-a-1700-v7-mkmlizer: ║                                                                     ║
chaiml-small-anthropic-a-1700-v7-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-small-anthropic-a-1700-v7-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-small-anthropic-a-1700-v7-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-small-anthropic-a-1700-v7-mkmlizer: ║                                                                     ║
chaiml-small-anthropic-a-1700-v7-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-small-anthropic-a-1700-v7-mkmlizer: ║  belonging to:                                                      ║
chaiml-small-anthropic-a-1700-v7-mkmlizer: ║                                                                     ║
chaiml-small-anthropic-a-1700-v7-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-small-anthropic-a-1700-v7-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-small-anthropic-a-1700-v7-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-small-anthropic-a-1700-v7-mkmlizer: ║                                                                     ║
chaiml-small-anthropic-a-1700-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-small-anthropic-a-1700-v7-mkmlizer: Downloaded to shared memory in 88.622s
chaiml-small-anthropic-a-1700-v7-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpkikjejlh, device:0
chaiml-small-anthropic-a-1700-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
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
chaiml-small-anthropic-a-1700-v7-mkmlizer: quantized model in 46.922s
chaiml-small-anthropic-a-1700-v7-mkmlizer: Processed model ChaiML/small_anthropic_addict_lexical_1120 in 135.545s
chaiml-small-anthropic-a-1700-v7-mkmlizer: creating bucket guanaco-mkml-models
chaiml-small-anthropic-a-1700-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-small-anthropic-a-1700-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-small-anthropic-a-1700-v7
chaiml-small-anthropic-a-1700-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-small-anthropic-a-1700-v7/config.json
chaiml-small-anthropic-a-1700-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-small-anthropic-a-1700-v7/special_tokens_map.json
chaiml-small-anthropic-a-1700-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-small-anthropic-a-1700-v7/tokenizer_config.json
chaiml-small-anthropic-a-1700-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-small-anthropic-a-1700-v7/tokenizer.json
chaiml-small-anthropic-a-1700-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-small-anthropic-a-1700-v7/flywheel_model.1.safetensors
chaiml-small-anthropic-a-1700-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-small-anthropic-a-1700-v7/flywheel_model.0.safetensors
chaiml-small-anthropic-a-1700-v7-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:21, 23.36it/s]
Loading 0:   2%|▏         | 10/507 [00:00<00:15, 32.39it/s]
Loading 0:   3%|▎         | 14/507 [00:00<00:17, 28.00it/s]
Loading 0:   4%|▎         | 19/507 [00:00<00:14, 32.86it/s]
Loading 0:   5%|▍         | 23/507 [00:00<00:16, 29.25it/s]
Loading 0:   6%|▌         | 28/507 [00:00<00:14, 32.59it/s]
Loading 0:   6%|▋         | 32/507 [00:01<00:16, 29.20it/s]
Loading 0:   7%|▋         | 37/507 [00:01<00:14, 33.33it/s]
Loading 0:   8%|▊         | 41/507 [00:01<00:15, 30.30it/s]
Loading 0:   9%|▉         | 46/507 [00:01<00:13, 34.48it/s]
Loading 0:  10%|▉         | 50/507 [00:01<00:14, 30.61it/s]
Loading 0:  11%|█         | 54/507 [00:01<00:21, 21.54it/s]
Loading 0:  11%|█         | 57/507 [00:02<00:20, 21.80it/s]
Loading 0:  12%|█▏        | 61/507 [00:02<00:17, 24.89it/s]
Loading 0:  13%|█▎        | 65/507 [00:02<00:18, 24.40it/s]
Loading 0:  14%|█▍        | 70/507 [00:02<00:14, 29.18it/s]
Loading 0:  15%|█▍        | 75/507 [00:02<00:13, 32.02it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:13, 30.70it/s]
Loading 0:  17%|█▋        | 85/507 [00:02<00:12, 33.85it/s]
Loading 0:  18%|█▊        | 89/507 [00:03<00:13, 29.95it/s]
Loading 0:  19%|█▊        | 94/507 [00:03<00:12, 33.67it/s]
Loading 0:  19%|█▉        | 98/507 [00:03<00:13, 29.47it/s]
Loading 0:  20%|██        | 103/507 [00:03<00:12, 33.25it/s]
Loading 0:  21%|██        | 107/507 [00:03<00:14, 27.66it/s]
Loading 0:  22%|██▏       | 112/507 [00:03<00:12, 31.27it/s]
Loading 0:  23%|██▎       | 116/507 [00:04<00:18, 21.14it/s]
Loading 0:  24%|██▍       | 122/507 [00:04<00:15, 24.35it/s]
Loading 0:  25%|██▌       | 127/507 [00:04<00:13, 28.54it/s]
Loading 0:  26%|██▌       | 131/507 [00:04<00:13, 27.10it/s]
Loading 0:  27%|██▋       | 136/507 [00:04<00:11, 31.02it/s]
Loading 0:  28%|██▊       | 140/507 [00:04<00:12, 28.35it/s]
Loading 0:  29%|██▊       | 145/507 [00:05<00:11, 32.08it/s]
Loading 0:  29%|██▉       | 149/507 [00:05<00:12, 29.31it/s]
Loading 0:  30%|███       | 154/507 [00:05<00:10, 32.88it/s]
Loading 0:  31%|███       | 158/507 [00:05<00:11, 29.99it/s]
Loading 0:  32%|███▏      | 163/507 [00:05<00:10, 34.28it/s]
Loading 0:  33%|███▎      | 168/507 [00:05<00:09, 35.38it/s]
Loading 0:  34%|███▍      | 172/507 [00:06<00:14, 23.38it/s]
Loading 0:  35%|███▍      | 176/507 [00:06<00:13, 23.68it/s]
Loading 0:  36%|███▌      | 181/507 [00:06<00:11, 27.96it/s]
Loading 0:  36%|███▋      | 185/507 [00:06<00:11, 27.02it/s]
Loading 0:  37%|███▋      | 190/507 [00:06<00:10, 31.38it/s]
Loading 0:  38%|███▊      | 194/507 [00:06<00:10, 29.01it/s]
Loading 0:  39%|███▉      | 199/507 [00:06<00:09, 33.13it/s]
Loading 0:  40%|████      | 203/507 [00:06<00:09, 30.57it/s]
Loading 0:  41%|████▏     | 210/507 [00:07<00:07, 37.40it/s]
Loading 0:  42%|████▏     | 214/507 [00:07<00:08, 35.30it/s]
Loading 0:  43%|████▎     | 218/507 [00:07<00:08, 34.34it/s]
Loading 0:  44%|████▍     | 222/507 [00:07<00:08, 33.03it/s]
Loading 0:  45%|████▍     | 226/507 [00:07<00:11, 23.63it/s]
Loading 0:  45%|████▌     | 230/507 [00:07<00:11, 23.86it/s]
Loading 0:  46%|████▋     | 235/507 [00:08<00:09, 28.59it/s]
Loading 0:  47%|████▋     | 239/507 [00:08<00:09, 26.81it/s]
Loading 0:  48%|████▊     | 244/507 [00:08<00:08, 31.05it/s]
Loading 0:  49%|████▉     | 248/507 [00:08<00:09, 28.77it/s]
Loading 0:  50%|████▉     | 253/507 [00:08<00:07, 32.84it/s]
Loading 0:  51%|█████     | 257/507 [00:08<00:08, 29.79it/s]
Loading 0:  52%|█████▏    | 262/507 [00:08<00:07, 33.44it/s]
Loading 0:  52%|█████▏    | 266/507 [00:09<00:07, 30.40it/s]
Loading 0:  53%|█████▎    | 271/507 [00:09<00:06, 34.45it/s]
Loading 0:  54%|█████▍    | 275/507 [00:09<00:07, 31.26it/s]
Loading 0:  55%|█████▌    | 280/507 [00:09<00:06, 35.50it/s]
Loading 0:  56%|█████▌    | 284/507 [00:09<00:08, 25.76it/s]
Loading 0:  57%|█████▋    | 288/507 [00:09<00:08, 25.49it/s]
Loading 0:  58%|█████▊    | 293/507 [00:10<00:08, 26.14it/s]
Loading 0:  59%|█████▉    | 298/507 [00:10<00:06, 30.25it/s]
Loading 0:  59%|█████▉    | 299/507 [00:24<00:06, 30.25it/s]
Loading 0:  59%|█████▉    | 300/507 [00:24<04:00,  1.16s/it]
Loading 0:  60%|█████▉    | 302/507 [00:24<03:18,  1.03it/s]
Loading 0:  61%|██████    | 307/507 [00:25<02:00,  1.66it/s]
Loading 0:  61%|██████    | 310/507 [00:25<01:30,  2.18it/s]
Loading 0:  62%|██████▏   | 313/507 [00:25<01:07,  2.88it/s]
Loading 0:  62%|██████▏   | 316/507 [00:25<00:49,  3.83it/s]
Loading 0:  63%|██████▎   | 320/507 [00:25<00:34,  5.38it/s]
Loading 0:  64%|██████▍   | 325/507 [00:25<00:22,  8.14it/s]
Loading 0:  65%|██████▍   | 329/507 [00:25<00:17, 10.19it/s]
Loading 0:  66%|██████▌   | 334/507 [00:25<00:12, 14.00it/s]
Loading 0:  67%|██████▋   | 339/507 [00:26<00:09, 17.70it/s]
Loading 0:  68%|██████▊   | 343/507 [00:26<00:10, 15.66it/s]
Loading 0:  68%|██████▊   | 347/507 [00:26<00:09, 17.28it/s]
Loading 0:  69%|██████▉   | 352/507 [00:26<00:07, 21.93it/s]
Loading 0:  70%|███████   | 356/507 [00:26<00:06, 22.03it/s]
Loading 0:  71%|███████   | 361/507 [00:27<00:05, 26.74it/s]
Loading 0:  72%|███████▏  | 365/507 [00:27<00:05, 26.22it/s]
Loading 0:  73%|███████▎  | 370/507 [00:27<00:04, 30.83it/s]
Loading 0:  74%|███████▍  | 374/507 [00:27<00:04, 29.08it/s]
Loading 0:  75%|███████▌  | 381/507 [00:27<00:03, 36.30it/s]
Loading 0:  76%|███████▌  | 386/507 [00:27<00:03, 36.06it/s]
Loading 0:  77%|███████▋  | 390/507 [00:27<00:03, 30.02it/s]
Loading 0:  78%|███████▊  | 395/507 [00:28<00:04, 25.14it/s]
Loading 0:  79%|███████▉  | 401/507 [00:28<00:03, 26.69it/s]
Loading 0:  80%|████████  | 406/507 [00:28<00:03, 30.60it/s]
Loading 0:  81%|████████  | 410/507 [00:28<00:03, 27.13it/s]
Loading 0:  82%|████████▏ | 415/507 [00:28<00:03, 28.47it/s]
Loading 0:  83%|████████▎ | 419/507 [00:28<00:03, 27.33it/s]
Loading 0:  84%|████████▎ | 424/507 [00:29<00:02, 31.60it/s]
Loading 0:  84%|████████▍ | 428/507 [00:29<00:02, 29.81it/s]
Loading 0:  85%|████████▌ | 433/507 [00:29<00:02, 33.93it/s]
Loading 0:  86%|████████▌ | 437/507 [00:29<00:02, 30.34it/s]
Loading 0:  87%|████████▋ | 442/507 [00:29<00:01, 34.61it/s]
Loading 0:  88%|████████▊ | 446/507 [00:29<00:01, 31.80it/s]
Loading 0:  89%|████████▉ | 453/507 [00:29<00:01, 40.02it/s]
Loading 0:  90%|█████████ | 458/507 [00:32<00:08,  6.11it/s]
Loading 0:  91%|█████████ | 462/507 [00:32<00:05,  7.67it/s]
Loading 0:  92%|█████████▏| 466/507 [00:32<00:04,  9.26it/s]
Loading 0:  93%|█████████▎| 470/507 [00:32<00:03, 11.68it/s]
Loading 0:  93%|█████████▎| 474/507 [00:32<00:02, 13.51it/s]
Loading 0:  94%|█████████▍| 479/507 [00:33<00:01, 17.58it/s]
Loading 0:  95%|█████████▌| 483/507 [00:33<00:01, 19.10it/s]
Loading 0:  96%|█████████▋| 488/507 [00:33<00:00, 23.48it/s]
Loading 0:  97%|█████████▋| 492/507 [00:33<00:00, 22.80it/s]
Loading 0:  98%|█████████▊| 497/507 [00:33<00:00, 26.77it/s]
Loading 0:  99%|█████████▉| 501/507 [00:33<00:00, 24.64it/s]
Loading 0: 100%|█████████▉| 506/507 [00:34<00:00, 27.68it/s]
                                                            
Job chaiml-small-anthropic-a-1700-v7-mkmlizer completed after 167.21s with status: succeeded
Stopping job with name chaiml-small-anthropic-a-1700-v7-mkmlizer
Pipeline stage MKMLizer completed in 167.75s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.21s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-small-anthropic-a-1700-v7
Waiting for inference service chaiml-small-anthropic-a-1700-v7 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Retrying (%r) after connection broken by '%r': %s
Inference service chaiml-small-anthropic-a-1700-v7 ready after 211.9407036304474s
Pipeline stage MKMLDeployer completed in 212.66s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 3.181757688522339s
Received healthy response to inference request in 2.385462760925293s
Received healthy response to inference request in 2.406390905380249s
Received healthy response to inference request in 2.471597194671631s
5 requests
1 failed requests
5th percentile: 2.3896483898162844
10th percentile: 2.3938340187072753
20th percentile: 2.4022052764892576
30th percentile: 2.4194321632385254
40th percentile: 2.445514678955078
50th percentile: 2.471597194671631
60th percentile: 2.755661392211914
70th percentile: 3.039725589752197
80th percentile: 6.576347064971927
90th percentile: 13.365525817871095
95th percentile: 16.760115194320676
99th percentile: 19.475786695480345
mean time: 6.119982624053955
%s, retrying in %s seconds...
Received healthy response to inference request in 3.286787986755371s
Received healthy response to inference request in 2.7067201137542725s
Received healthy response to inference request in 2.5895209312438965s
Received healthy response to inference request in 2.22261381149292s
Received healthy response to inference request in 2.835716485977173s
5 requests
0 failed requests
5th percentile: 2.2959952354431152
10th percentile: 2.3693766593933105
20th percentile: 2.516139507293701
30th percentile: 2.612960767745972
40th percentile: 2.659840440750122
50th percentile: 2.7067201137542725
60th percentile: 2.7583186626434326
70th percentile: 2.8099172115325928
80th percentile: 2.9259307861328128
90th percentile: 3.1063593864440917
95th percentile: 3.196573686599731
99th percentile: 3.268745126724243
mean time: 2.7282718658447265
Pipeline stage StressChecker completed in 47.83s
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 5.36s
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 2.65s
Shutdown handler de-registered
chaiml-small-anthropic-a_1700_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 3222.76s
Shutdown handler de-registered
chaiml-small-anthropic-a_1700_v7 status is now inactive due to auto deactivation removed underperforming models