zzyabc-mixtral-8x7b-v0-1

developer_uid: ZZYABC

submission_id: zzyabc-mixtral-8x7b-v0-1_v1

model_name: zzyabc-mixtral-8x7b-v0-1_v1

model_group: ZZYABC/Mixtral-8x7B-v0.1

status: torndown

timestamp: 2024-12-20T06:46:54+00:00

num_battles: 11789

num_wins: 5044

celo_rating: 1206.31

family_friendly_score: 0.5776

family_friendly_standard_error: 0.006985388178190243

submission_type: basic

model_repo: ZZYABC/Mixtral-8x7B-v0.1

model_architecture: MistralForCausalLM

model_num_parameters: 7241732096.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.915788648159766, 'latency_mean': 1.0918687891960144, 'latency_p50': 1.088066577911377, 'latency_p90': 1.2074611902236938}, {'batch_size': 4, 'throughput': 1.97946330138688, 'latency_mean': 2.007485046386719, 'latency_p50': 2.019639253616333, 'latency_p90': 2.231565499305725}, {'batch_size': 5, 'throughput': 2.118110004816634, 'latency_mean': 2.3461118137836454, 'latency_p50': 2.3616552352905273, 'latency_p90': 2.6496890068054197}, {'batch_size': 8, 'throughput': 2.381146726878706, 'latency_mean': 3.3461591100692747, 'latency_p50': 3.2915923595428467, 'latency_p90': 3.772598695755005}, {'batch_size': 10, 'throughput': 2.432305991561084, 'latency_mean': 4.0817652559280395, 'latency_p50': 4.0701717138290405, 'latency_p90': 4.5735667705535885}, {'batch_size': 12, 'throughput': 2.47039318926741, 'latency_mean': 4.820778442621231, 'latency_p50': 4.815141916275024, 'latency_p90': 5.399766492843628}, {'batch_size': 15, 'throughput': 2.4813943448122546, 'latency_mean': 5.971005077362061, 'latency_p50': 6.031225919723511, 'latency_p90': 6.642153906822204}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: zzyabc-mixtral-8x7b-v0-1_v1

is_internal_developer: False

language_model: ZZYABC/Mixtral-8x7B-v0.1

model_size: 7B

ranking_group: single

throughput_3p7s: 2.42

us_pacific_date: 2024-12-19

win_ratio: 0.427856476376283

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', '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 zzyabc-mixtral-8x7b-v0-1-v1-mkmlizer
Waiting for job on zzyabc-mixtral-8x7b-v0-1-v1-mkmlizer to finish
zzyabc-mixtral-8x7b-v0-1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zzyabc-mixtral-8x7b-v0-1-v1-mkmlizer: ║     _____            __           __                                ║
zzyabc-mixtral-8x7b-v0-1-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
zzyabc-mixtral-8x7b-v0-1-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
zzyabc-mixtral-8x7b-v0-1-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
zzyabc-mixtral-8x7b-v0-1-v1-mkmlizer: ║       /___/                                                         ║
zzyabc-mixtral-8x7b-v0-1-v1-mkmlizer: ║                                                                     ║
zzyabc-mixtral-8x7b-v0-1-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
zzyabc-mixtral-8x7b-v0-1-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
zzyabc-mixtral-8x7b-v0-1-v1-mkmlizer: ║  https://mk1.ai                                                     ║
zzyabc-mixtral-8x7b-v0-1-v1-mkmlizer: ║                                                                     ║
zzyabc-mixtral-8x7b-v0-1-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
zzyabc-mixtral-8x7b-v0-1-v1-mkmlizer: ║  belonging to:                                                      ║
zzyabc-mixtral-8x7b-v0-1-v1-mkmlizer: ║                                                                     ║
zzyabc-mixtral-8x7b-v0-1-v1-mkmlizer: ║  Chai Research Corp.                                                ║
zzyabc-mixtral-8x7b-v0-1-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
zzyabc-mixtral-8x7b-v0-1-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
zzyabc-mixtral-8x7b-v0-1-v1-mkmlizer: ║                                                                     ║
zzyabc-mixtral-8x7b-v0-1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
zzyabc-mixtral-8x7b-v0-1-v1-mkmlizer: Downloaded to shared memory in 28.926s
zzyabc-mixtral-8x7b-v0-1-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp0crhhq7e, device:0
zzyabc-mixtral-8x7b-v0-1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
zzyabc-mixtral-8x7b-v0-1-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/mk1/flywheel/functional/loader.py:55: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
zzyabc-mixtral-8x7b-v0-1-v1-mkmlizer:   tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
zzyabc-mixtral-8x7b-v0-1-v1-mkmlizer: quantized model in 17.777s
zzyabc-mixtral-8x7b-v0-1-v1-mkmlizer: Processed model ZZYABC/Mixtral-8x7B-v0.1 in 46.703s
zzyabc-mixtral-8x7b-v0-1-v1-mkmlizer: creating bucket guanaco-mkml-models
zzyabc-mixtral-8x7b-v0-1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zzyabc-mixtral-8x7b-v0-1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zzyabc-mixtral-8x7b-v0-1-v1
zzyabc-mixtral-8x7b-v0-1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zzyabc-mixtral-8x7b-v0-1-v1/config.json
zzyabc-mixtral-8x7b-v0-1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zzyabc-mixtral-8x7b-v0-1-v1/special_tokens_map.json
zzyabc-mixtral-8x7b-v0-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zzyabc-mixtral-8x7b-v0-1-v1/tokenizer_config.json
zzyabc-mixtral-8x7b-v0-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/zzyabc-mixtral-8x7b-v0-1-v1/tokenizer.model
zzyabc-mixtral-8x7b-v0-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zzyabc-mixtral-8x7b-v0-1-v1/tokenizer.json
zzyabc-mixtral-8x7b-v0-1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zzyabc-mixtral-8x7b-v0-1-v1/flywheel_model.0.safetensors
zzyabc-mixtral-8x7b-v0-1-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 50.77it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:04, 67.19it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 75.57it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:02, 89.73it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:02, 81.77it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:03, 74.03it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:03, 74.23it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:02, 73.95it/s]
Loading 0:  29%|██▉       | 85/291 [00:01<00:02, 72.08it/s]
Loading 0:  32%|███▏      | 94/291 [00:01<00:02, 71.25it/s]
Loading 0:  35%|███▌      | 102/291 [00:02<00:09, 20.45it/s]
Loading 0:  37%|███▋      | 108/291 [00:02<00:07, 23.30it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:06, 27.67it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:04, 35.77it/s]
Loading 0:  46%|████▌     | 133/291 [00:02<00:03, 43.90it/s]
Loading 0:  49%|████▉     | 142/291 [00:02<00:02, 50.81it/s]
Loading 0:  52%|█████▏    | 151/291 [00:03<00:02, 55.81it/s]
Loading 0:  55%|█████▍    | 160/291 [00:03<00:02, 61.34it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:01, 66.95it/s]
Loading 0:  61%|██████    | 178/291 [00:03<00:01, 70.65it/s]
Loading 0:  64%|██████▍   | 187/291 [00:03<00:01, 71.30it/s]
Loading 0:  67%|██████▋   | 196/291 [00:03<00:01, 73.40it/s]
Loading 0:  70%|███████   | 204/291 [00:04<00:03, 21.84it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:03, 26.22it/s]
Loading 0:  76%|███████▌  | 220/291 [00:04<00:02, 33.36it/s]
Loading 0:  79%|███████▊  | 229/291 [00:05<00:01, 40.56it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:01, 46.48it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 53.44it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 59.28it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 65.44it/s]
Loading 0:  94%|█████████▍| 274/291 [00:05<00:00, 69.48it/s]
Loading 0:  97%|█████████▋| 283/291 [00:05<00:00, 66.29it/s]
Loading 0: 100%|██████████| 291/291 [00:07<00:00, 17.27it/s]
                                                            
Job zzyabc-mixtral-8x7b-v0-1-v1-mkmlizer completed after 73.72s with status: succeeded
Stopping job with name zzyabc-mixtral-8x7b-v0-1-v1-mkmlizer
Pipeline stage MKMLizer completed in 74.22s
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 zzyabc-mixtral-8x7b-v0-1-v1
Waiting for inference service zzyabc-mixtral-8x7b-v0-1-v1 to be ready
Failed to get response for submission function_gidef_2024-11-26: ('http://chaiml-llama-8b-multihea-7878-v5-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:59944->127.0.0.1:8080: read: connection reset by peer\n')
Inference service zzyabc-mixtral-8x7b-v0-1-v1 ready after 251.28440022468567s
Pipeline stage MKMLDeployer completed in 251.83s
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 1.2928276062011719s
Received healthy response to inference request in 1.412585735321045s
Received healthy response to inference request in 0.9114160537719727s
Received healthy response to inference request in 0.6560516357421875s
5 requests
1 failed requests
5th percentile: 0.7071245193481446
10th percentile: 0.7581974029541015
20th percentile: 0.8603431701660156
30th percentile: 0.9876983642578125
40th percentile: 1.140262985229492
50th percentile: 1.2928276062011719
60th percentile: 1.340730857849121
70th percentile: 1.3886341094970702
80th percentile: 5.1523401260376005
90th percentile: 12.631848907470705
95th percentile: 16.371603298187253
99th percentile: 19.363406810760498
mean time: 4.876847743988037
%s, retrying in %s seconds...
Received healthy response to inference request in 1.3650727272033691s
Received healthy response to inference request in 1.517604112625122s
Received healthy response to inference request in 1.6685361862182617s
Received healthy response to inference request in 0.7048740386962891s
Received healthy response to inference request in 0.8570334911346436s
5 requests
0 failed requests
5th percentile: 0.73530592918396
10th percentile: 0.7657378196716309
20th percentile: 0.8266016006469726
30th percentile: 0.9586413383483886
40th percentile: 1.161857032775879
50th percentile: 1.3650727272033691
60th percentile: 1.4260852813720704
70th percentile: 1.4870978355407714
80th percentile: 1.54779052734375
90th percentile: 1.6081633567810059
95th percentile: 1.6383497714996338
99th percentile: 1.662498903274536
mean time: 1.2226241111755372
Pipeline stage StressChecker completed in 33.32s
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 2.44s
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 2.41s
Shutdown handler de-registered
zzyabc-mixtral-8x7b-v0-1_v1 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 2075.01s
Shutdown handler de-registered
zzyabc-mixtral-8x7b-v0-1_v1 status is now inactive due to auto deactivation removed underperforming models
zzyabc-mixtral-8x7b-v0-1_v1 status is now torndown due to DeploymentManager action
zzyabc-mixtral-8x7b-v0-1_v1 status is now torndown due to DeploymentManager action
zzyabc-mixtral-8x7b-v0-1_v1 status is now torndown due to DeploymentManager action