developer_uid: bogoconic1
submission_id: chaiml-gy-exp98-sft-gy-d_6572_v1
model_name: chaiml-gy-exp98-sft-gy-d_6572_v1
model_group: ChaiML/gy-exp98-sft-gy-d
status: torndown
timestamp: 2025-07-06T14:56:37+00:00
num_battles: 7388
num_wins: 3804
celo_rating: 1300.98
family_friendly_score: 0.5206
family_friendly_standard_error: 0.007065063906292709
submission_type: basic
model_repo: ChaiML/gy-exp98-sft-gy-datamix-v1-bo8-pygmalion-ep2
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': 0.522337123729504, 'latency_mean': 1.9143465483188629, 'latency_p50': 1.9032942056655884, 'latency_p90': 2.120074820518494}, {'batch_size': 3, 'throughput': 1.0503326353806213, 'latency_mean': 2.8412083804607393, 'latency_p50': 2.852174997329712, 'latency_p90': 3.1476155042648317}, {'batch_size': 5, 'throughput': 1.3398634301824603, 'latency_mean': 3.6990792965888977, 'latency_p50': 3.6999210119247437, 'latency_p90': 4.117687082290649}, {'batch_size': 6, 'throughput': 1.4443779113004662, 'latency_mean': 4.133062101602555, 'latency_p50': 4.126416802406311, 'latency_p90': 4.668544816970825}, {'batch_size': 8, 'throughput': 1.5813069198362908, 'latency_mean': 5.012512220144272, 'latency_p50': 5.01148796081543, 'latency_p90': 5.665263915061951}, {'batch_size': 10, 'throughput': 1.6709247293506784, 'latency_mean': 5.938244755268097, 'latency_p50': 5.884405612945557, 'latency_p90': 6.794668388366699}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-gy-exp98-sft-gy-d_6572_v1
is_internal_developer: False
language_model: ChaiML/gy-exp98-sft-gy-datamix-v1-bo8-pygmalion-ep2
model_size: 24B
ranking_group: single
throughput_3p7s: 1.35
us_pacific_date: 2025-07-06
win_ratio: 0.5148890092041147
generation_params: {'temperature': 0.6, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n<START>\n", 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': True}
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-gy-exp98-sft-gy-d-6572-v1-mkmlizer
Waiting for job on chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer to finish
chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer: ║ ║
chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer: ║ ║
chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer: ║ Version: 0.29.15 ║
chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer: ║ ║
chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer: ║ belonging to: ║
chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer: ║ ║
chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer: ║ ║
chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer: Downloaded to shared memory in 116.720s
chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer: Checking if ChaiML/gy-exp98-sft-gy-datamix-v1-bo8-pygmalion-ep2 already exists in ChaiML
chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmptozxak0w, device:0
chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer: quantized model in 92.750s
chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer: Processed model ChaiML/gy-exp98-sft-gy-datamix-v1-bo8-pygmalion-ep2 in 209.471s
chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp98-sft-gy-d-6572-v1/nvidia
chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp98-sft-gy-d-6572-v1/nvidia/special_tokens_map.json
chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp98-sft-gy-d-6572-v1/nvidia/config.json
chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp98-sft-gy-d-6572-v1/nvidia/tokenizer_config.json
chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp98-sft-gy-d-6572-v1/nvidia/tokenizer.json
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp98-sft-gy-d-6572-v1/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp98-sft-gy-d-6572-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 4/363 [00:00<00:14, 24.60it/s] Loading 0: 2%|▏ | 7/363 [00:00<00:18, 18.99it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:17, 20.03it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:17, 20.45it/s] Loading 0: 4%|▍ | 16/363 [00:00<00:19, 17.58it/s] Loading 0: 5%|▌ | 19/363 [00:01<00:19, 17.69it/s] Loading 0: 6%|▌ | 22/363 [00:01<00:17, 19.07it/s] Loading 0: 7%|▋ | 24/363 [00:01<00:19, 17.10it/s] Loading 0: 8%|▊ | 28/363 [00:01<00:16, 19.86it/s] Loading 0: 9%|▉ | 32/363 [00:01<00:15, 22.00it/s] Loading 0: 10%|▉ | 35/363 [00:02<00:25, 12.75it/s] Loading 0: 10%|█ | 37/363 [00:02<00:28, 11.56it/s] Loading 0: 11%|█ | 39/363 [00:02<00:25, 12.72it/s] Loading 0: 11%|█▏ | 41/363 [00:02<00:29, 10.83it/s] Loading 0: 13%|█▎ | 46/363 [00:02<00:20, 15.48it/s] Loading 0: 13%|█▎ | 49/363 [00:03<00:20, 15.63it/s] Loading 0: 14%|█▍ | 51/363 [00:03<00:22, 13.88it/s] Loading 0: 15%|█▌ | 55/363 [00:03<00:17, 17.37it/s] Loading 0: 16%|█▌ | 58/363 [00:03<00:17, 17.36it/s] Loading 0: 17%|█▋ | 60/363 [00:03<00:19, 15.39it/s] Loading 0: 18%|█▊ | 64/363 [00:03<00:17, 16.98it/s] Loading 0: 18%|█▊ | 67/363 [00:04<00:15, 19.32it/s] Loading 0: 19%|█▉ | 70/363 [00:04<00:23, 12.58it/s] Loading 0: 20%|█▉ | 72/363 [00:04<00:23, 12.50it/s] Loading 0: 20%|██ | 74/363 [00:04<00:24, 11.80it/s] Loading 0: 21%|██▏ | 78/363 [00:05<00:19, 14.96it/s] Loading 0: 22%|██▏ | 80/363 [00:05<00:23, 12.17it/s] Loading 0: 23%|██▎ | 84/363 [00:05<00:18, 15.49it/s] Loading 0: 24%|██▍ | 87/363 [00:05<00:20, 13.77it/s] Loading 0: 25%|██▌ | 91/363 [00:05<00:16, 16.63it/s] Loading 0: 26%|██▌ | 93/363 [00:06<00:17, 15.15it/s] Loading 0: 27%|██▋ | 97/363 [00:06<00:14, 18.15it/s] Loading 0: 28%|██▊ | 100/363 [00:06<00:14, 17.93it/s] Loading 0: 28%|██▊ | 102/363 [00:06<00:16, 15.42it/s] Loading 0: 29%|██▉ | 106/363 [00:06<00:13, 19.36it/s] Loading 0: 30%|███ | 109/363 [00:06<00:17, 14.71it/s] Loading 0: 31%|███ | 112/363 [00:07<00:15, 15.72it/s] Loading 0: 31%|███▏ | 114/363 [00:07<00:17, 14.58it/s] Loading 0: 33%|███▎ | 118/363 [00:07<00:13, 18.69it/s] Loading 0: 33%|███▎ | 121/363 [00:07<00:13, 18.18it/s] Loading 0: 34%|███▍ | 124/363 [00:07<00:13, 18.03it/s] Loading 0: 35%|███▍ | 127/363 [00:07<00:12, 19.39it/s] Loading 0: 36%|███▌ | 130/363 [00:08<00:12, 19.15it/s] Loading 0: 37%|███▋ | 133/363 [00:08<00:12, 17.70it/s] Loading 0: 37%|███▋ | 136/363 [00:08<00:12, 18.74it/s] Loading 0: 38%|███▊ | 139/363 [00:08<00:12, 17.97it/s] Loading 0: 39%|███▉ | 141/363 [00:08<00:14, 15.83it/s] Loading 0: 40%|███▉ | 145/363 [00:08<00:11, 18.66it/s] Loading 0: 41%|████ | 149/363 [00:09<00:09, 22.29it/s] Loading 0: 42%|████▏ | 152/363 [00:09<00:14, 14.12it/s] Loading 0: 42%|████▏ | 154/363 [00:09<00:15, 13.45it/s] Loading 0: 43%|████▎ | 157/363 [00:09<00:14, 14.41it/s] Loading 0: 44%|████▍ | 159/363 [00:10<00:15, 12.99it/s] Loading 0: 45%|████▍ | 163/363 [00:10<00:11, 16.76it/s] Loading 0: 45%|████▌ | 165/363 [00:10<00:11, 16.98it/s] Loading 0: 46%|████▌ | 167/363 [00:10<00:14, 13.71it/s] Loading 0: 47%|████▋ | 172/363 [00:10<00:09, 19.29it/s] Loading 0: 48%|████▊ | 175/363 [00:10<00:09, 18.91it/s] Loading 0: 49%|████▉ | 178/363 [00:10<00:09, 18.85it/s] Loading 0: 50%|████▉ | 181/363 [00:11<00:08, 20.26it/s] Loading 0: 51%|█████ | 184/363 [00:11<00:08, 22.02it/s] Loading 0: 52%|█████▏ | 187/363 [00:11<00:12, 14.24it/s] Loading 0: 52%|█████▏ | 189/363 [00:11<00:14, 12.35it/s] Loading 0: 53%|█████▎ | 193/363 [00:11<00:11, 15.25it/s] Loading 0: 54%|█████▎ | 195/363 [00:12<00:11, 14.24it/s] Loading 0: 55%|█████▍ | 199/363 [00:12<00:09, 17.14it/s] Loading 0: 55%|█████▌ | 200/363 [00:30<00:09, 17.14it/s] Loading 0: 55%|█████▌ | 201/363 [00:40<08:14, 3.05s/it] Loading 0: 56%|█████▌ | 202/363 [00:40<07:08, 2.66s/it] Loading 0: 56%|█████▌ | 204/363 [00:40<05:12, 1.97s/it] Loading 0: 57%|█████▋ | 208/363 [00:40<02:53, 1.12s/it] Loading 0: 58%|█████▊ | 210/363 [00:41<02:13, 1.15it/s] Loading 0: 58%|█████▊ | 212/363 [00:41<01:43, 1.46it/s] Loading 0: 60%|█████▉ | 217/363 [00:41<00:54, 2.69it/s] Loading 0: 61%|██████ | 220/363 [00:41<00:41, 3.48it/s] Loading 0: 61%|██████▏ | 223/363 [00:41<00:30, 4.66it/s] Loading 0: 62%|██████▏ | 226/363 [00:42<00:25, 5.46it/s] Loading 0: 63%|██████▎ | 229/363 [00:42<00:19, 7.00it/s] Loading 0: 64%|██████▎ | 231/363 [00:42<00:17, 7.64it/s] Loading 0: 65%|██████▍ | 235/363 [00:42<00:11, 10.78it/s] Loading 0: 66%|██████▌ | 238/363 [00:42<00:10, 12.06it/s] Loading 0: 66%|██████▌ | 240/363 [00:43<00:10, 11.19it/s] Loading 0: 67%|██████▋ | 244/363 [00:43<00:07, 14.93it/s] Loading 0: 68%|██████▊ | 247/363 [00:43<00:07, 15.23it/s] Loading 0: 69%|██████▊ | 249/363 [00:43<00:08, 14.15it/s] Loading 0: 70%|██████▉ | 253/363 [00:43<00:06, 17.40it/s] Loading 0: 71%|███████ | 256/363 [00:43<00:06, 17.63it/s] Loading 0: 71%|███████ | 258/363 [00:44<00:06, 15.28it/s] Loading 0: 72%|███████▏ | 262/363 [00:44<00:05, 18.94it/s] Loading 0: 73%|███████▎ | 266/363 [00:44<00:04, 21.91it/s] Loading 0: 74%|███████▍ | 269/363 [00:44<00:07, 13.19it/s] Loading 0: 75%|███████▍ | 271/363 [00:44<00:07, 12.22it/s] Loading 0: 75%|███████▌ | 273/363 [00:45<00:06, 13.33it/s] Loading 0: 76%|███████▌ | 275/363 [00:45<00:08, 10.86it/s] Loading 0: 77%|███████▋ | 280/363 [00:45<00:05, 15.39it/s] Loading 0: 78%|███████▊ | 283/363 [00:45<00:04, 16.00it/s] Loading 0: 79%|███████▊ | 285/363 [00:45<00:05, 15.26it/s] Loading 0: 80%|███████▉ | 289/363 [00:45<00:03, 18.55it/s] Loading 0: 80%|████████ | 292/363 [00:46<00:03, 19.09it/s] Loading 0: 81%|████████▏ | 295/363 [00:46<00:03, 17.85it/s] Loading 0: 82%|████████▏ | 298/363 [00:46<00:03, 19.18it/s] Loading 0: 83%|████████▎ | 301/363 [00:46<00:03, 20.33it/s] Loading 0: 84%|████████▎ | 304/363 [00:47<00:04, 12.77it/s] Loading 0: 84%|████████▍ | 306/363 [00:47<00:05, 10.75it/s] Loading 0: 85%|████████▌ | 310/363 [00:47<00:03, 13.26it/s] Loading 0: 86%|████████▌ | 312/363 [00:47<00:04, 11.85it/s] Loading 0: 87%|████████▋ | 316/363 [00:47<00:03, 14.91it/s] Loading 0: 88%|████████▊ | 319/363 [00:48<00:02, 15.40it/s] Loading 0: 88%|████████▊ | 321/363 [00:48<00:03, 13.78it/s] Loading 0: 90%|████████▉ | 325/363 [00:48<00:02, 16.70it/s] Loading 0: 90%|█████████ | 327/363 [00:48<00:02, 16.83it/s] Loading 0: 91%|█████████ | 329/363 [00:48<00:02, 11.96it/s] Loading 0: 92%|█████████▏| 334/363 [00:49<00:01, 17.07it/s] Loading 0: 93%|█████████▎| 337/363 [00:49<00:01, 14.03it/s] Loading 0: 94%|█████████▎| 340/363 [00:49<00:01, 15.74it/s] Loading 0: 94%|█████████▍| 342/363 [00:50<00:02, 7.91it/s] Loading 0: 95%|█████████▌| 346/363 [00:50<00:01, 10.54it/s] Loading 0: 96%|█████████▌| 348/363 [00:50<00:01, 9.04it/s] Loading 0: 97%|█████████▋| 353/363 [00:50<00:00, 12.72it/s] Loading 0: 98%|█████████▊| 356/363 [00:51<00:00, 13.54it/s] Loading 0: 99%|█████████▊| 358/363 [00:51<00:00, 12.16it/s] Loading 0: 100%|█████████▉| 362/363 [00:51<00:00, 14.76it/s]
Job chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer completed after 269.85s with status: succeeded
Stopping job with name chaiml-gy-exp98-sft-gy-d-6572-v1-mkmlizer
Pipeline stage MKMLizer completed in 270.62s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-exp98-sft-gy-d-6572-v1
Waiting for inference service chaiml-gy-exp98-sft-gy-d-6572-v1 to be ready
Inference service chaiml-gy-exp98-sft-gy-d-6572-v1 ready after 211.0123610496521s
Pipeline stage MKMLDeployer completed in 211.46s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.6150565147399902s
Received healthy response to inference request in 2.4522390365600586s
Received healthy response to inference request in 2.2624499797821045s
Received healthy response to inference request in 2.2604470252990723s
Received healthy response to inference request in 2.256894826889038s
5 requests
0 failed requests
5th percentile: 2.257605266571045
10th percentile: 2.2583157062530517
20th percentile: 2.2597365856170653
30th percentile: 2.2608476161956785
40th percentile: 2.2616487979888915
50th percentile: 2.2624499797821045
60th percentile: 2.338365602493286
70th percentile: 2.414281225204468
80th percentile: 2.684802532196045
90th percentile: 3.1499295234680176
95th percentile: 3.382493019104004
99th percentile: 3.568543815612793
mean time: 2.5694174766540527
Pipeline stage StressChecker completed in 14.09s
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 0.65s
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 0.67s
Shutdown handler de-registered
chaiml-gy-exp98-sft-gy-d_6572_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 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-gy-exp98-sft-gy-d-6572-v1-profiler
Waiting for inference service chaiml-gy-exp98-sft-gy-d-6572-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 3781.72s
Shutdown handler de-registered
chaiml-gy-exp98-sft-gy-d_6572_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp98-sft-gy-d_6572_v1 status is now torndown due to DeploymentManager action