developer_uid: NischayDnk
submission_id: chaiml-mistral31-ff4kex_29911_v3
model_name: chaiml-mistral31-ff4kex_29911_v3
model_group: ChaiML/mistral31-ff4kexp
status: torndown
timestamp: 2025-04-12T19:24:32+00:00
num_battles: 9212
num_wins: 5065
celo_rating: 1322.76
family_friendly_score: 0.5234
family_friendly_standard_error: 0.007063319899310805
submission_type: basic
model_repo: ChaiML/mistral31-ff4kexp1-dpo-v2-data31preffull
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.3719148250777991, 'latency_mean': 2.6886880123615264, 'latency_p50': 2.6504586935043335, 'latency_p90': 2.990971875190735}, {'batch_size': 2, 'throughput': 0.5882810649712527, 'latency_mean': 3.3972314131259918, 'latency_p50': 3.38541841506958, 'latency_p90': 3.7753735542297364}, {'batch_size': 3, 'throughput': 0.7441768428275832, 'latency_mean': 4.0126429259777066, 'latency_p50': 3.9782599210739136, 'latency_p90': 4.502273082733154}, {'batch_size': 4, 'throughput': 0.8606722346277402, 'latency_mean': 4.630754321813583, 'latency_p50': 4.677448153495789, 'latency_p90': 5.0892149925231935}, {'batch_size': 5, 'throughput': 0.9576572271119541, 'latency_mean': 5.185813763141632, 'latency_p50': 5.173494577407837, 'latency_p90': 5.829618525505066}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-mistral31-ff4kex_29911_v3
is_internal_developer: False
language_model: ChaiML/mistral31-ff4kexp1-dpo-v2-data31preffull
model_size: 24B
ranking_group: single
throughput_3p7s: 0.67
us_pacific_date: 2025-04-12
win_ratio: 0.549826313504125
generation_params: {'temperature': 0.4, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 40, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['\n', '<|im_start|>', '<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '<|system|>Family Friendly{memory}\n', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\nYou:{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', '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-mistral31-ff4kex-29911-v3-mkmlizer
Waiting for job on chaiml-mistral31-ff4kex-29911-v3-mkmlizer to finish
Failed to get response for submission jellywibble-felix-black_21853_v1: HTTPConnectionPool(host='jellywibble-felix-black-21853-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-mistral31-ff4kex-29911-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral31-ff4kex-29911-v3-mkmlizer: ║ _____ __ __ ║
chaiml-mistral31-ff4kex-29911-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-mistral31-ff4kex-29911-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-mistral31-ff4kex-29911-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-mistral31-ff4kex-29911-v3-mkmlizer: ║ /___/ ║
chaiml-mistral31-ff4kex-29911-v3-mkmlizer: ║ ║
chaiml-mistral31-ff4kex-29911-v3-mkmlizer: ║ Version: 0.12.8 ║
chaiml-mistral31-ff4kex-29911-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-mistral31-ff4kex-29911-v3-mkmlizer: ║ https://mk1.ai ║
chaiml-mistral31-ff4kex-29911-v3-mkmlizer: ║ ║
chaiml-mistral31-ff4kex-29911-v3-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-mistral31-ff4kex-29911-v3-mkmlizer: ║ belonging to: ║
chaiml-mistral31-ff4kex-29911-v3-mkmlizer: ║ ║
chaiml-mistral31-ff4kex-29911-v3-mkmlizer: ║ Chai Research Corp. ║
chaiml-mistral31-ff4kex-29911-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-mistral31-ff4kex-29911-v3-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
chaiml-mistral31-ff4kex-29911-v3-mkmlizer: ║ ║
chaiml-mistral31-ff4kex-29911-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral31-ff4kex-29911-v3-mkmlizer: Downloaded to shared memory in 70.232s
chaiml-mistral31-ff4kex-29911-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpupgvizyr, device:0
chaiml-mistral31-ff4kex-29911-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission jellywibble-felix-black_21853_v1: HTTPConnectionPool(host='jellywibble-felix-black-21853-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-mistral31-ff4kex-29911-v3-mkmlizer: quantized model in 55.615s
chaiml-mistral31-ff4kex-29911-v3-mkmlizer: Processed model ChaiML/mistral31-ff4kexp1-dpo-v2-data31preffull in 125.847s
chaiml-mistral31-ff4kex-29911-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral31-ff4kex-29911-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral31-ff4kex-29911-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral31-ff4kex-29911-v3
chaiml-mistral31-ff4kex-29911-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral31-ff4kex-29911-v3/special_tokens_map.json
chaiml-mistral31-ff4kex-29911-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral31-ff4kex-29911-v3/config.json
chaiml-mistral31-ff4kex-29911-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral31-ff4kex-29911-v3/tokenizer_config.json
chaiml-mistral31-ff4kex-29911-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral31-ff4kex-29911-v3/tokenizer.json
chaiml-mistral31-ff4kex-29911-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral31-ff4kex-29911-v3/flywheel_model.0.safetensors
chaiml-mistral31-ff4kex-29911-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral31-ff4kex-29911-v3/flywheel_model.1.safetensors
chaiml-mistral31-ff4kex-29911-v3-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 4/363 [00:00<00:10, 34.79it/s] Loading 0: 2%|▏ | 8/363 [00:00<00:12, 28.05it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:11, 30.04it/s] Loading 0: 4%|▍ | 16/363 [00:00<00:13, 26.63it/s] Loading 0: 6%|▌ | 21/363 [00:00<00:11, 30.66it/s] Loading 0: 7%|▋ | 25/363 [00:00<00:12, 27.56it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:09, 34.85it/s] Loading 0: 10%|▉ | 35/363 [00:01<00:14, 22.77it/s] Loading 0: 10%|█ | 38/363 [00:01<00:14, 23.02it/s] Loading 0: 11%|█▏ | 41/363 [00:01<00:16, 19.00it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:12, 25.86it/s] Loading 0: 14%|█▍ | 52/363 [00:02<00:12, 24.12it/s] Loading 0: 16%|█▌ | 57/363 [00:02<00:11, 26.39it/s] Loading 0: 17%|█▋ | 60/363 [00:02<00:12, 23.63it/s] Loading 0: 18%|█▊ | 65/363 [00:02<00:11, 26.47it/s] Loading 0: 19%|█▉ | 69/363 [00:02<00:10, 29.24it/s] Loading 0: 20%|██ | 73/363 [00:03<00:15, 18.90it/s] Loading 0: 21%|██▏ | 78/363 [00:03<00:12, 23.40it/s] Loading 0: 23%|██▎ | 82/363 [00:03<00:12, 22.45it/s] Loading 0: 24%|██▎ | 86/363 [00:03<00:11, 24.09it/s] Loading 0: 25%|██▍ | 89/363 [00:03<00:11, 24.07it/s] Loading 0: 25%|██▌ | 92/363 [00:03<00:14, 18.85it/s] Loading 0: 27%|██▋ | 97/363 [00:03<00:10, 24.30it/s] Loading 0: 28%|██▊ | 100/363 [00:04<00:10, 24.77it/s] Loading 0: 28%|██▊ | 103/363 [00:04<00:10, 24.18it/s] Loading 0: 29%|██▉ | 107/363 [00:04<00:12, 20.34it/s] Loading 0: 31%|███ | 111/363 [00:04<00:10, 23.88it/s] Loading 0: 31%|███▏ | 114/363 [00:04<00:11, 21.58it/s] Loading 0: 33%|███▎ | 120/363 [00:04<00:09, 26.59it/s] Loading 0: 34%|███▍ | 123/363 [00:05<00:10, 23.73it/s] Loading 0: 36%|███▌ | 129/363 [00:05<00:08, 27.90it/s] Loading 0: 36%|███▋ | 132/363 [00:05<00:09, 24.45it/s] Loading 0: 37%|███▋ | 136/363 [00:05<00:08, 27.62it/s] Loading 0: 38%|███▊ | 139/363 [00:05<00:08, 27.60it/s] Loading 0: 39%|███▉ | 142/363 [00:05<00:08, 26.17it/s] Loading 0: 40%|████ | 146/363 [00:05<00:07, 29.49it/s] Loading 0: 41%|████▏ | 150/363 [00:06<00:09, 23.02it/s] Loading 0: 42%|████▏ | 153/363 [00:06<00:10, 19.21it/s] Loading 0: 43%|████▎ | 157/363 [00:06<00:09, 22.44it/s] Loading 0: 44%|████▍ | 160/363 [00:06<00:09, 22.47it/s] Loading 0: 45%|████▌ | 164/363 [00:06<00:07, 26.27it/s] Loading 0: 46%|████▌ | 167/363 [00:06<00:09, 20.43it/s] Loading 0: 48%|████▊ | 174/363 [00:07<00:06, 27.43it/s] Loading 0: 49%|████▉ | 178/363 [00:07<00:07, 25.81it/s] Loading 0: 50%|█████ | 182/363 [00:07<00:07, 25.54it/s] Loading 0: 51%|█████ | 186/363 [00:07<00:06, 28.42it/s] Loading 0: 52%|█████▏ | 190/363 [00:07<00:08, 20.40it/s] Loading 0: 53%|█████▎ | 193/363 [00:07<00:07, 21.65it/s] Loading 0: 54%|█████▍ | 196/363 [00:08<00:07, 22.03it/s] Loading 0: 55%|█████▌ | 200/363 [00:22<00:07, 22.03it/s] Loading 0: 55%|█████▌ | 201/363 [00:22<03:03, 1.13s/it] Loading 0: 56%|█████▌ | 203/363 [00:22<02:32, 1.05it/s] Loading 0: 57%|█████▋ | 208/363 [00:23<01:31, 1.69it/s] Loading 0: 58%|█████▊ | 211/363 [00:23<01:10, 2.16it/s] Loading 0: 59%|█████▉ | 214/363 [00:23<00:52, 2.83it/s] Loading 0: 60%|██████ | 218/363 [00:23<00:35, 4.04it/s] Loading 0: 61%|██████ | 221/363 [00:23<00:27, 5.12it/s] Loading 0: 62%|██████▏ | 224/363 [00:23<00:22, 6.07it/s] Loading 0: 63%|██████▎ | 229/363 [00:24<00:14, 8.97it/s] Loading 0: 64%|██████▍ | 232/363 [00:24<00:12, 10.62it/s] Loading 0: 65%|██████▌ | 237/363 [00:24<00:08, 14.23it/s] Loading 0: 66%|██████▌ | 240/363 [00:24<00:08, 14.93it/s] Loading 0: 68%|██████▊ | 246/363 [00:24<00:05, 20.02it/s] Loading 0: 69%|██████▊ | 249/363 [00:24<00:05, 19.30it/s] Loading 0: 70%|██████▉ | 253/363 [00:25<00:04, 22.84it/s] Loading 0: 71%|███████ | 256/363 [00:25<00:04, 23.79it/s] Loading 0: 71%|███████▏ | 259/363 [00:25<00:04, 23.37it/s] Loading 0: 73%|███████▎ | 264/363 [00:25<00:03, 28.67it/s] Loading 0: 74%|███████▍ | 268/363 [00:25<00:04, 20.73it/s] Loading 0: 75%|███████▍ | 271/363 [00:25<00:04, 19.62it/s] Loading 0: 75%|███████▌ | 274/363 [00:25<00:04, 21.14it/s] Loading 0: 76%|███████▋ | 277/363 [00:26<00:03, 21.54it/s] Loading 0: 77%|███████▋ | 280/363 [00:26<00:03, 22.79it/s] Loading 0: 78%|███████▊ | 283/363 [00:26<00:03, 24.03it/s] Loading 0: 79%|███████▉ | 286/363 [00:26<00:03, 23.79it/s] Loading 0: 80%|████████ | 291/363 [00:26<00:02, 26.87it/s] Loading 0: 81%|████████ | 294/363 [00:26<00:02, 23.06it/s] Loading 0: 82%|████████▏ | 299/363 [00:26<00:02, 25.51it/s] Loading 0: 84%|████████▎ | 304/363 [00:27<00:02, 22.27it/s] Loading 0: 85%|████████▍ | 307/363 [00:27<00:02, 20.86it/s] Loading 0: 85%|████████▌ | 310/363 [00:27<00:02, 22.15it/s] Loading 0: 86%|████████▌ | 313/363 [00:27<00:02, 22.16it/s] Loading 0: 87%|████████▋ | 316/363 [00:27<00:01, 23.77it/s] Loading 0: 88%|████████▊ | 319/363 [00:27<00:01, 24.96it/s] Loading 0: 89%|████████▊ | 322/363 [00:27<00:01, 24.48it/s] Loading 0: 90%|█████████ | 327/363 [00:28<00:01, 27.58it/s] Loading 0: 91%|█████████ | 330/363 [00:28<00:01, 23.81it/s] Loading 0: 92%|█████████▏| 335/363 [00:28<00:01, 26.65it/s] Loading 0: 93%|█████████▎| 338/363 [00:28<00:01, 24.89it/s] Loading 0: 94%|█████████▍| 341/363 [00:35<00:13, 1.59it/s] Loading 0: 96%|█████████▌| 347/363 [00:35<00:05, 2.69it/s] Loading 0: 96%|█████████▋| 350/363 [00:35<00:03, 3.37it/s] Loading 0: 98%|█████████▊| 355/363 [00:35<00:01, 5.01it/s] Loading 0: 99%|█████████▊| 358/363 [00:36<00:00, 6.01it/s]
Job chaiml-mistral31-ff4kex-29911-v3-mkmlizer completed after 166.38s with status: succeeded
Stopping job with name chaiml-mistral31-ff4kex-29911-v3-mkmlizer
Pipeline stage MKMLizer completed in 166.90s
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-mistral31-ff4kex-29911-v3
Waiting for inference service chaiml-mistral31-ff4kex-29911-v3 to be ready
Failed to get response for submission jellywibble-felix-black_21853_v1: HTTPConnectionPool(host='jellywibble-felix-black-21853-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-mistral31-ff4kex-29911-v3 ready after 110.39486813545227s
Pipeline stage MKMLDeployer completed in 111.16s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.359347105026245s
Received healthy response to inference request in 2.6281497478485107s
Received healthy response to inference request in 2.495756149291992s
Received healthy response to inference request in 2.4590702056884766s
Received healthy response to inference request in 2.7115366458892822s
5 requests
0 failed requests
5th percentile: 2.4664073944091798
10th percentile: 2.473744583129883
20th percentile: 2.488418960571289
30th percentile: 2.522234869003296
40th percentile: 2.5751923084259034
50th percentile: 2.6281497478485107
60th percentile: 2.6615045070648193
70th percentile: 2.694859266281128
80th percentile: 2.841098737716675
90th percentile: 3.10022292137146
95th percentile: 3.2297850131988524
99th percentile: 3.3334346866607665
mean time: 2.7307719707489015
Pipeline stage StressChecker completed in 14.97s
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 0.72s
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 0.91s
Shutdown handler de-registered
chaiml-mistral31-ff4kex_29911_v3 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-mistral31-ff4kex-29911-v3-profiler
Waiting for inference service chaiml-mistral31-ff4kex-29911-v3-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 3008.15s
Shutdown handler de-registered
chaiml-mistral31-ff4kex_29911_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral31-ff4kex_29911_v3 status is now torndown due to DeploymentManager action