developer_uid: NischayDnk
submission_id: chaiml-slerpv1-mistral3_60605_v2
model_name: chaiml-slerpv1-mistral3_60605_v2
model_group: ChaiML/slerpv1_mistral31
status: torndown
timestamp: 2025-04-16T18:21:35+00:00
num_battles: 6200
num_wins: 3599
celo_rating: 1342.67
family_friendly_score: 0.4666
family_friendly_standard_error: 0.007055273772150873
submission_type: basic
model_repo: ChaiML/slerpv1_mistral31_simpo_dpo_s2
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 768
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.38947647292503945, 'latency_mean': 2.5674828350543977, 'latency_p50': 2.57842755317688, 'latency_p90': 2.8489607334136964}, {'batch_size': 3, 'throughput': 0.8080828421240782, 'latency_mean': 3.7030728459358215, 'latency_p50': 3.7122915983200073, 'latency_p90': 4.11120834350586}, {'batch_size': 5, 'throughput': 1.0612009297095994, 'latency_mean': 4.684554582834243, 'latency_p50': 4.647297143936157, 'latency_p90': 5.2876975536346436}, {'batch_size': 6, 'throughput': 1.1483072858496015, 'latency_mean': 5.195571444034576, 'latency_p50': 5.244991183280945, 'latency_p90': 5.7970287799835205}, {'batch_size': 10, 'throughput': 1.3337987446880641, 'latency_mean': 7.415114554166794, 'latency_p50': 7.342108130455017, 'latency_p90': 8.395059013366698}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-slerpv1-mistral3_60605_v2
is_internal_developer: False
language_model: ChaiML/slerpv1_mistral31_simpo_dpo_s2
model_size: 24B
ranking_group: single
throughput_3p7s: 0.81
us_pacific_date: 2025-04-16
win_ratio: 0.5804838709677419
generation_params: {'temperature': 0.45, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['<|im_start|>', '\n', '<|im_end|>'], 'max_input_tokens': 768, '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-slerpv1-mistral3-60605-v2-mkmlizer
Waiting for job on chaiml-slerpv1-mistral3-60605-v2-mkmlizer to finish
chaiml-slerpv1-mistral3-60605-v2-mkmlizer: Downloaded to shared memory in 62.732s
chaiml-slerpv1-mistral3-60605-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpmf9tdfm1, device:0
chaiml-slerpv1-mistral3-60605-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-slerpv1-mistral3-60605-v2-mkmlizer: quantized model in 54.800s
chaiml-slerpv1-mistral3-60605-v2-mkmlizer: Processed model ChaiML/slerpv1_mistral31_simpo_dpo_s2 in 117.533s
chaiml-slerpv1-mistral3-60605-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-slerpv1-mistral3-60605-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-slerpv1-mistral3-60605-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-slerpv1-mistral3-60605-v2
chaiml-slerpv1-mistral3-60605-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-slerpv1-mistral3-60605-v2/special_tokens_map.json
chaiml-slerpv1-mistral3-60605-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-slerpv1-mistral3-60605-v2/config.json
chaiml-slerpv1-mistral3-60605-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-slerpv1-mistral3-60605-v2/tokenizer_config.json
chaiml-slerpv1-mistral3-60605-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-slerpv1-mistral3-60605-v2/tokenizer.json
chaiml-slerpv1-mistral3-60605-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-slerpv1-mistral3-60605-v2/flywheel_model.1.safetensors
chaiml-slerpv1-mistral3-60605-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-slerpv1-mistral3-60605-v2/flywheel_model.0.safetensors
chaiml-slerpv1-mistral3-60605-v2-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:06<18:35, 3.09s/it] Loading 0: 2%|▏ | 6/363 [00:06<05:01, 1.19it/s] Loading 0: 4%|▎ | 13/363 [00:06<01:48, 3.23it/s] Loading 0: 4%|▍ | 16/363 [00:06<01:21, 4.24it/s] Loading 0: 6%|▌ | 22/363 [00:06<00:51, 6.59it/s] Loading 0: 7%|▋ | 25/363 [00:07<00:43, 7.80it/s] Loading 0: 9%|▊ | 31/363 [00:07<00:28, 11.77it/s] Loading 0: 9%|▉ | 34/363 [00:07<00:25, 12.93it/s] Loading 0: 11%|█ | 40/363 [00:07<00:18, 17.89it/s] Loading 0: 12%|█▏ | 44/363 [00:07<00:16, 19.47it/s] Loading 0: 13%|█▎ | 49/363 [00:07<00:13, 23.25it/s] Loading 0: 15%|█▍ | 53/363 [00:08<00:13, 23.78it/s] Loading 0: 16%|█▌ | 58/363 [00:08<00:11, 27.24it/s] Loading 0: 17%|█▋ | 62/363 [00:08<00:14, 20.36it/s] Loading 0: 18%|█▊ | 67/363 [00:08<00:12, 24.11it/s] Loading 0: 20%|█▉ | 71/363 [00:08<00:12, 24.05it/s] Loading 0: 21%|██ | 76/363 [00:08<00:10, 27.23it/s] Loading 0: 22%|██▏ | 80/363 [00:09<00:10, 26.53it/s] Loading 0: 23%|██▎ | 85/363 [00:09<00:09, 29.48it/s] Loading 0: 25%|██▍ | 89/363 [00:09<00:09, 27.66it/s] Loading 0: 26%|██▌ | 94/363 [00:09<00:08, 30.31it/s] Loading 0: 27%|██▋ | 98/363 [00:09<00:12, 21.45it/s] Loading 0: 28%|██▊ | 103/363 [00:09<00:10, 25.04it/s] Loading 0: 29%|██▉ | 106/363 [00:10<00:10, 23.53it/s] Loading 0: 31%|███ | 112/363 [00:10<00:08, 28.17it/s] Loading 0: 32%|███▏ | 116/363 [00:10<00:09, 26.07it/s] Loading 0: 33%|███▎ | 121/363 [00:10<00:08, 28.29it/s] Loading 0: 34%|███▍ | 125/363 [00:10<00:08, 26.59it/s] Loading 0: 36%|███▌ | 130/363 [00:10<00:08, 29.03it/s] Loading 0: 37%|███▋ | 134/363 [00:11<00:08, 27.61it/s] Loading 0: 38%|███▊ | 139/363 [00:11<00:09, 22.87it/s] Loading 0: 39%|███▉ | 142/363 [00:11<00:10, 21.82it/s] Loading 0: 41%|████ | 148/363 [00:11<00:08, 26.61it/s] Loading 0: 42%|████▏ | 151/363 [00:11<00:08, 24.11it/s] Loading 0: 43%|████▎ | 155/363 [00:11<00:07, 26.92it/s] Loading 0: 44%|████▎ | 158/363 [00:12<00:07, 27.54it/s] Loading 0: 44%|████▍ | 161/363 [00:12<00:07, 26.51it/s] Loading 0: 46%|████▌ | 166/363 [00:12<00:06, 29.11it/s] Loading 0: 47%|████▋ | 169/363 [00:12<00:07, 24.71it/s] Loading 0: 48%|████▊ | 175/363 [00:12<00:06, 29.82it/s] Loading 0: 49%|████▉ | 179/363 [00:12<00:08, 20.59it/s] Loading 0: 51%|█████ | 184/363 [00:13<00:07, 23.93it/s] Loading 0: 51%|█████ | 185/363 [00:27<00:07, 23.93it/s] Loading 0: 51%|█████ | 186/363 [00:27<03:32, 1.20s/it] Loading 0: 53%|█████▎ | 191/363 [00:27<02:12, 1.30it/s] Loading 0: 54%|█████▎ | 195/363 [00:28<01:36, 1.75it/s] Loading 0: 56%|█████▌ | 202/363 [00:28<00:54, 2.96it/s] Loading 0: 57%|█████▋ | 206/363 [00:28<00:41, 3.82it/s] Loading 0: 58%|█████▊ | 211/363 [00:28<00:28, 5.31it/s] Loading 0: 59%|█████▉ | 215/363 [00:28<00:23, 6.21it/s] Loading 0: 61%|██████ | 220/363 [00:29<00:16, 8.45it/s] Loading 0: 61%|██████▏ | 223/363 [00:29<00:14, 9.55it/s] Loading 0: 63%|██████▎ | 229/363 [00:29<00:09, 13.44it/s] Loading 0: 64%|██████▍ | 232/363 [00:29<00:09, 14.22it/s] Loading 0: 66%|██████▌ | 238/363 [00:29<00:06, 19.05it/s] Loading 0: 67%|██████▋ | 242/363 [00:29<00:06, 19.93it/s] Loading 0: 68%|██████▊ | 247/363 [00:30<00:04, 23.22it/s] Loading 0: 69%|██████▉ | 251/363 [00:30<00:04, 23.54it/s] Loading 0: 71%|███████ | 256/363 [00:30<00:05, 20.86it/s] Loading 0: 71%|███████▏ | 259/363 [00:30<00:05, 20.12it/s] Loading 0: 73%|███████▎ | 265/363 [00:30<00:03, 25.16it/s] Loading 0: 74%|███████▍ | 268/363 [00:30<00:04, 23.49it/s] Loading 0: 75%|███████▌ | 274/363 [00:31<00:03, 28.59it/s] Loading 0: 77%|███████▋ | 278/363 [00:31<00:03, 27.23it/s] Loading 0: 78%|███████▊ | 283/363 [00:31<00:02, 29.26it/s] Loading 0: 79%|███████▉ | 287/363 [00:31<00:02, 27.15it/s] Loading 0: 80%|███████▉ | 290/363 [00:31<00:02, 27.68it/s] Loading 0: 81%|████████ | 293/363 [00:31<00:03, 19.68it/s] Loading 0: 82%|████████▏ | 296/363 [00:32<00:03, 20.66it/s] Loading 0: 83%|████████▎ | 301/363 [00:32<00:02, 24.78it/s] Loading 0: 84%|████████▎ | 304/363 [00:32<00:02, 22.77it/s] Loading 0: 85%|████████▌ | 310/363 [00:32<00:01, 27.97it/s] Loading 0: 86%|████████▌ | 313/363 [00:32<00:01, 25.19it/s] Loading 0: 88%|████████▊ | 319/363 [00:32<00:01, 29.81it/s] Loading 0: 89%|████████▉ | 323/363 [00:33<00:01, 27.34it/s] Loading 0: 90%|█████████ | 328/363 [00:33<00:01, 29.34it/s] Loading 0: 91%|█████████▏| 332/363 [00:33<00:01, 20.37it/s] Loading 0: 93%|█████████▎| 337/363 [00:33<00:01, 23.15it/s] Loading 0: 94%|█████████▎| 340/363 [00:33<00:01, 21.63it/s] Loading 0: 95%|█████████▌| 346/363 [00:33<00:00, 26.23it/s] Loading 0: 96%|█████████▌| 349/363 [00:34<00:00, 23.24it/s] Loading 0: 97%|█████████▋| 353/363 [00:34<00:00, 26.10it/s] Loading 0: 98%|█████████▊| 356/363 [00:34<00:00, 26.64it/s] Loading 0: 99%|█████████▉| 359/363 [00:34<00:00, 25.64it/s] Loading 0: 100%|█████████▉| 362/363 [00:34<00:00, 26.62it/s]
Job chaiml-slerpv1-mistral3-60605-v2-mkmlizer completed after 156.37s with status: succeeded
Stopping job with name chaiml-slerpv1-mistral3-60605-v2-mkmlizer
Pipeline stage MKMLizer completed in 156.85s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-slerpv1-mistral3-60605-v2
Waiting for inference service chaiml-slerpv1-mistral3-60605-v2 to be ready
Inference service chaiml-slerpv1-mistral3-60605-v2 ready after 180.6660373210907s
Pipeline stage MKMLDeployer completed in 181.30s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.0662574768066406s
Received healthy response to inference request in 2.4964373111724854s
Received healthy response to inference request in 2.460529088973999s
Received healthy response to inference request in 2.38955020904541s
Received healthy response to inference request in 2.720092535018921s
5 requests
0 failed requests
5th percentile: 2.403745985031128
10th percentile: 2.417941761016846
20th percentile: 2.446333312988281
30th percentile: 2.4677107334136963
40th percentile: 2.482074022293091
50th percentile: 2.4964373111724854
60th percentile: 2.5858994007110594
70th percentile: 2.675361490249634
80th percentile: 2.789325523376465
90th percentile: 2.9277915000915526
95th percentile: 2.9970244884490964
99th percentile: 3.052410879135132
mean time: 2.626573324203491
Pipeline stage StressChecker completed in 14.36s
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 0.74s
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 0.72s
Shutdown handler de-registered
chaiml-slerpv1-mistral3_60605_v2 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 2930.66s
Shutdown handler de-registered
chaiml-slerpv1-mistral3_60605_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-slerpv1-mistral3_60605_v2 status is now torndown due to DeploymentManager action