developer_uid: zonemercy
submission_id: chaiml-405b-mini1-12b0-s_7586_v1
model_name: tempv1-2
model_group: ChaiML/405b-mini1-12b0-s
status: torndown
timestamp: 2025-01-03T23:29:18+00:00
num_battles: 14230
num_wins: 7187
celo_rating: 1258.21
family_friendly_score: 0.6036
family_friendly_standard_error: 0.006917615774238983
submission_type: basic
model_repo: ChaiML/405b-mini1-12b0-sftl1e5r7
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 768
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.6531496477019149, 'latency_mean': 1.5309809708595277, 'latency_p50': 1.5311447381973267, 'latency_p90': 1.6893661260604858}, {'batch_size': 3, 'throughput': 1.2413376233405322, 'latency_mean': 2.4099945604801176, 'latency_p50': 2.411918520927429, 'latency_p90': 2.6479427099227903}, {'batch_size': 5, 'throughput': 1.5629489362100213, 'latency_mean': 3.1771916055679323, 'latency_p50': 3.202130079269409, 'latency_p90': 3.6059359073638917}, {'batch_size': 6, 'throughput': 1.6545954484751084, 'latency_mean': 3.6008147239685058, 'latency_p50': 3.607530117034912, 'latency_p90': 4.098263454437256}, {'batch_size': 8, 'throughput': 1.733176201760972, 'latency_mean': 4.586587369441986, 'latency_p50': 4.59389865398407, 'latency_p90': 5.137818932533264}, {'batch_size': 10, 'throughput': 1.7814683108772855, 'latency_mean': 5.578905491828919, 'latency_p50': 5.639461159706116, 'latency_p90': 6.249260950088501}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: tempv1-2
is_internal_developer: True
language_model: ChaiML/405b-mini1-12b0-sftl1e5r7
model_size: 13B
ranking_group: single
throughput_3p7s: 1.68
us_pacific_date: 2025-01-03
win_ratio: 0.5050597329585383
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': ['<|im_end|>', '####', '</s>', 'User:', 'Bot:', '<|eot_id|>', '\n', 'You:'], 'max_input_tokens': 768, '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': '####\n{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-405b-mini1-12b0-s-7586-v1-mkmlizer
Waiting for job on chaiml-405b-mini1-12b0-s-7586-v1-mkmlizer to finish
Failed to get response for submission function_lijit_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 127.0.0.1:50382->127.0.0.1:8080: read: connection reset by peer\n')
chaiml-405b-mini1-12b0-s-7586-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-405b-mini1-12b0-s-7586-v1-mkmlizer: ║ _____ __ __ ║
chaiml-405b-mini1-12b0-s-7586-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-405b-mini1-12b0-s-7586-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-405b-mini1-12b0-s-7586-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-405b-mini1-12b0-s-7586-v1-mkmlizer: ║ /___/ ║
chaiml-405b-mini1-12b0-s-7586-v1-mkmlizer: ║ ║
chaiml-405b-mini1-12b0-s-7586-v1-mkmlizer: ║ Version: 0.11.12 ║
chaiml-405b-mini1-12b0-s-7586-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-405b-mini1-12b0-s-7586-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-405b-mini1-12b0-s-7586-v1-mkmlizer: ║ ║
chaiml-405b-mini1-12b0-s-7586-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-405b-mini1-12b0-s-7586-v1-mkmlizer: ║ belonging to: ║
chaiml-405b-mini1-12b0-s-7586-v1-mkmlizer: ║ ║
chaiml-405b-mini1-12b0-s-7586-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-405b-mini1-12b0-s-7586-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-405b-mini1-12b0-s-7586-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
chaiml-405b-mini1-12b0-s-7586-v1-mkmlizer: ║ ║
chaiml-405b-mini1-12b0-s-7586-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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-405b-mini1-12b0-s-7586-v1-mkmlizer: Downloaded to shared memory in 50.365s
chaiml-405b-mini1-12b0-s-7586-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp0uad82r6, device:0
chaiml-405b-mini1-12b0-s-7586-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-405b-mini1-12b0-s-7586-v1-mkmlizer: quantized model in 37.250s
chaiml-405b-mini1-12b0-s-7586-v1-mkmlizer: Processed model ChaiML/405b-mini1-12b0-sftl1e5r7 in 87.616s
chaiml-405b-mini1-12b0-s-7586-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-405b-mini1-12b0-s-7586-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-405b-mini1-12b0-s-7586-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-405b-mini1-12b0-s-7586-v1
chaiml-405b-mini1-12b0-s-7586-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-405b-mini1-12b0-s-7586-v1/config.json
chaiml-405b-mini1-12b0-s-7586-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-405b-mini1-12b0-s-7586-v1/special_tokens_map.json
chaiml-405b-mini1-12b0-s-7586-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-405b-mini1-12b0-s-7586-v1/tokenizer_config.json
chaiml-405b-mini1-12b0-s-7586-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-405b-mini1-12b0-s-7586-v1/tokenizer.json
chaiml-405b-mini1-12b0-s-7586-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-405b-mini1-12b0-s-7586-v1/flywheel_model.0.safetensors
chaiml-405b-mini1-12b0-s-7586-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:12, 29.18it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:07, 48.79it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 47.35it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:07, 46.69it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 53.17it/s] Loading 0: 10%|█ | 37/363 [00:00<00:06, 48.60it/s] Loading 0: 12%|█▏ | 43/363 [00:00<00:06, 46.42it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 48.57it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 46.74it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 37.01it/s] Loading 0: 18%|█▊ | 66/363 [00:01<00:08, 36.18it/s] Loading 0: 20%|█▉ | 71/363 [00:01<00:07, 39.06it/s] Loading 0: 21%|██ | 76/363 [00:01<00:07, 39.02it/s] Loading 0: 22%|██▏ | 81/363 [00:01<00:06, 41.29it/s] Loading 0: 24%|██▎ | 86/363 [00:01<00:06, 42.79it/s] Loading 0: 25%|██▌ | 91/363 [00:02<00:07, 36.02it/s] Loading 0: 27%|██▋ | 98/363 [00:02<00:06, 42.43it/s] Loading 0: 28%|██▊ | 103/363 [00:02<00:06, 41.16it/s] Loading 0: 30%|██▉ | 108/363 [00:02<00:06, 42.14it/s] Loading 0: 31%|███ | 113/363 [00:02<00:07, 35.05it/s] Loading 0: 33%|███▎ | 118/363 [00:02<00:06, 35.11it/s] Loading 0: 34%|███▍ | 125/363 [00:03<00:05, 41.84it/s] Loading 0: 36%|███▌ | 130/363 [00:03<00:05, 41.01it/s] Loading 0: 37%|███▋ | 135/363 [00:03<00:05, 41.02it/s] Loading 0: 39%|███▊ | 140/363 [00:03<00:05, 41.46it/s] Loading 0: 40%|███▉ | 145/363 [00:03<00:08, 26.29it/s] Loading 0: 41%|████ | 149/363 [00:03<00:08, 26.34it/s] Loading 0: 43%|████▎ | 156/363 [00:04<00:06, 33.24it/s] Loading 0: 44%|████▍ | 160/363 [00:04<00:06, 32.64it/s] Loading 0: 45%|████▌ | 165/363 [00:04<00:05, 34.85it/s] Loading 0: 47%|████▋ | 169/363 [00:04<00:05, 33.73it/s] Loading 0: 48%|████▊ | 174/363 [00:04<00:05, 36.87it/s] Loading 0: 49%|████▉ | 178/363 [00:04<00:05, 35.76it/s] Loading 0: 50%|█████ | 183/363 [00:04<00:04, 37.36it/s] Loading 0: 52%|█████▏ | 187/363 [00:04<00:04, 35.51it/s] Loading 0: 53%|█████▎ | 192/363 [00:04<00:04, 37.80it/s] Loading 0: 54%|█████▍ | 196/363 [00:05<00:04, 35.89it/s] Loading 0: 55%|█████▌ | 201/363 [00:05<00:04, 37.79it/s] Loading 0: 56%|█████▋ | 205/363 [00:05<00:04, 36.02it/s] Loading 0: 58%|█████▊ | 210/363 [00:05<00:03, 38.61it/s] Loading 0: 59%|█████▉ | 214/363 [00:05<00:04, 36.36it/s] Loading 0: 60%|██████ | 218/363 [00:05<00:04, 35.57it/s] Loading 0: 61%|██████▏ | 223/363 [00:05<00:05, 26.89it/s] Loading 0: 63%|██████▎ | 227/363 [00:06<00:04, 28.24it/s] Loading 0: 64%|██████▎ | 231/363 [00:06<00:04, 27.81it/s] Loading 0: 65%|██████▌ | 237/363 [00:06<00:03, 33.95it/s] Loading 0: 66%|██████▋ | 241/363 [00:06<00:03, 33.23it/s] Loading 0: 68%|██████▊ | 246/363 [00:06<00:03, 35.62it/s] Loading 0: 69%|██████▉ | 250/363 [00:06<00:03, 34.42it/s] Loading 0: 70%|███████ | 255/363 [00:06<00:02, 36.16it/s] Loading 0: 71%|███████▏ | 259/363 [00:06<00:03, 33.66it/s] Loading 0: 72%|███████▏ | 263/363 [00:07<00:02, 35.20it/s] Loading 0: 74%|███████▎ | 267/363 [00:07<00:02, 32.72it/s] Loading 0: 75%|███████▌ | 273/363 [00:07<00:02, 37.27it/s] Loading 0: 76%|███████▋ | 277/363 [00:07<00:02, 35.52it/s] Loading 0: 78%|███████▊ | 282/363 [00:07<00:02, 37.60it/s] Loading 0: 79%|███████▉ | 286/363 [00:07<00:02, 35.71it/s] Loading 0: 80%|████████ | 291/363 [00:07<00:01, 37.56it/s] Loading 0: 81%|████████▏ | 295/363 [00:07<00:01, 35.31it/s] Loading 0: 82%|████████▏ | 299/363 [00:08<00:01, 34.70it/s] Loading 0: 84%|████████▎ | 304/363 [00:14<00:27, 2.11it/s] Loading 0: 85%|████████▍ | 307/363 [00:15<00:21, 2.64it/s] Loading 0: 86%|████████▌ | 312/363 [00:15<00:13, 3.90it/s] Loading 0: 88%|████████▊ | 320/363 [00:15<00:06, 6.70it/s] Loading 0: 90%|████████▉ | 326/363 [00:15<00:04, 9.17it/s] Loading 0: 91%|█████████ | 331/363 [00:15<00:02, 11.75it/s] Loading 0: 93%|█████████▎| 338/363 [00:15<00:01, 16.63it/s] Loading 0: 94%|█████████▍| 343/363 [00:15<00:00, 20.18it/s] Loading 0: 96%|█████████▌| 348/363 [00:15<00:00, 21.52it/s] Loading 0: 98%|█████████▊| 356/363 [00:16<00:00, 29.29it/s] Loading 0: 100%|█████████▉| 362/363 [00:16<00:00, 32.36it/s]
Job chaiml-405b-mini1-12b0-s-7586-v1-mkmlizer completed after 115.05s with status: succeeded
Stopping job with name chaiml-405b-mini1-12b0-s-7586-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.56s
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-405b-mini1-12b0-s-7586-v1
Waiting for inference service chaiml-405b-mini1-12b0-s-7586-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-405b-mini1-12b0-s-7586-v1 ready after 331.13123869895935s
Pipeline stage MKMLDeployer completed in 331.69s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0665411949157715s
Received healthy response to inference request in 1.5492887496948242s
Received healthy response to inference request in 1.5079960823059082s
Received healthy response to inference request in 1.4007289409637451s
Received healthy response to inference request in 6.70767068862915s
5 requests
0 failed requests
5th percentile: 1.4221823692321778
10th percentile: 1.4436357975006104
20th percentile: 1.4865426540374755
30th percentile: 1.5162546157836914
40th percentile: 1.532771682739258
50th percentile: 1.5492887496948242
60th percentile: 1.756189727783203
70th percentile: 1.9630907058715819
80th percentile: 2.994767093658448
90th percentile: 4.851218891143799
95th percentile: 5.779444789886474
99th percentile: 6.522025508880615
mean time: 2.64644513130188
Pipeline stage StressChecker completed in 14.86s
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 0.68s
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 0.64s
Shutdown handler de-registered
chaiml-405b-mini1-12b0-s_7586_v1 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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-405b-mini1-12b0-s-7586-v1-profiler
Waiting for inference service chaiml-405b-mini1-12b0-s-7586-v1-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 2585.83s
Shutdown handler de-registered
chaiml-405b-mini1-12b0-s_7586_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-405b-mini1-12b0-s_7586_v1 status is now torndown due to DeploymentManager action
chaiml-405b-mini1-12b0-s_7586_v1 status is now torndown due to DeploymentManager action
chaiml-405b-mini1-12b0-s_7586_v1 status is now torndown due to DeploymentManager action