developer_uid: NischayDnk
submission_id: chaiml-sft-gemma2-28b-v_83370_v3
model_name: chaiml-sft-gemma2-28b-v_83370_v3
model_group: ChaiML/sft-gemma2-28b-v2
status: torndown
timestamp: 2025-04-03T01:36:06+00:00
num_battles: 52
num_wins: 26
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: ChaiML/sft-gemma2-28b-v2-exp1-del12ktop
model_architecture: Gemma2ForCausalLM
model_num_parameters: 28731935232.0
best_of: 1
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.30158569715473527, 'latency_mean': 3.315741262435913, 'latency_p50': 3.305116653442383, 'latency_p90': 3.662180948257446}, {'batch_size': 2, 'throughput': 0.4863080943447076, 'latency_mean': 4.106569969654084, 'latency_p50': 4.121461868286133, 'latency_p90': 4.536013507843018}, {'batch_size': 3, 'throughput': 0.643883796510925, 'latency_mean': 4.654750810861588, 'latency_p50': 4.648542881011963, 'latency_p90': 5.140126037597656}, {'batch_size': 4, 'throughput': 0.7589562215666449, 'latency_mean': 5.231993595361709, 'latency_p50': 5.216090798377991, 'latency_p90': 5.784636902809143}, {'batch_size': 5, 'throughput': 0.875088174547717, 'latency_mean': 5.692773996591568, 'latency_p50': 5.709685564041138, 'latency_p90': 6.4868278980255125}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-sft-gemma2-28b-v_83370_v3
ineligible_reason: num_battles<5000
is_internal_developer: False
language_model: ChaiML/sft-gemma2-28b-v2-exp1-del12ktop
model_size: 29B
ranking_group: single
throughput_3p7s: 0.4
us_pacific_date: 2025-04-02
win_ratio: 0.5
generation_params: {'temperature': 0.45, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 40, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 1, 'max_output_tokens': 64}
formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\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-sft-gemma2-28b-v-83370-v3-mkmlizer
Waiting for job on chaiml-sft-gemma2-28b-v-83370-v3-mkmlizer to finish
chaiml-sft-gemma2-28b-v-83370-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sft-gemma2-28b-v-83370-v3-mkmlizer: ║ _____ __ __ ║
chaiml-sft-gemma2-28b-v-83370-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-sft-gemma2-28b-v-83370-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-sft-gemma2-28b-v-83370-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-sft-gemma2-28b-v-83370-v3-mkmlizer: ║ /___/ ║
chaiml-sft-gemma2-28b-v-83370-v3-mkmlizer: ║ ║
chaiml-sft-gemma2-28b-v-83370-v3-mkmlizer: ║ Version: 0.12.8 ║
chaiml-sft-gemma2-28b-v-83370-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-sft-gemma2-28b-v-83370-v3-mkmlizer: ║ https://mk1.ai ║
chaiml-sft-gemma2-28b-v-83370-v3-mkmlizer: ║ ║
chaiml-sft-gemma2-28b-v-83370-v3-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-sft-gemma2-28b-v-83370-v3-mkmlizer: ║ belonging to: ║
chaiml-sft-gemma2-28b-v-83370-v3-mkmlizer: ║ ║
chaiml-sft-gemma2-28b-v-83370-v3-mkmlizer: ║ Chai Research Corp. ║
chaiml-sft-gemma2-28b-v-83370-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-sft-gemma2-28b-v-83370-v3-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
chaiml-sft-gemma2-28b-v-83370-v3-mkmlizer: ║ ║
chaiml-sft-gemma2-28b-v-83370-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-sft-gemma2-28b-v-83370-v3-mkmlizer: Downloaded to shared memory in 134.858s
chaiml-sft-gemma2-28b-v-83370-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpzphc51rl, device:0
chaiml-sft-gemma2-28b-v-83370-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-sft-gemma2-28b-v-83370-v3-mkmlizer: quantized model in 69.252s
chaiml-sft-gemma2-28b-v-83370-v3-mkmlizer: Processed model ChaiML/sft-gemma2-28b-v2-exp1-del12ktop in 204.111s
chaiml-sft-gemma2-28b-v-83370-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sft-gemma2-28b-v-83370-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sft-gemma2-28b-v-83370-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v-83370-v3
chaiml-sft-gemma2-28b-v-83370-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v-83370-v3/config.json
chaiml-sft-gemma2-28b-v-83370-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v-83370-v3/special_tokens_map.json
chaiml-sft-gemma2-28b-v-83370-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v-83370-v3/tokenizer_config.json
chaiml-sft-gemma2-28b-v-83370-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v-83370-v3/tokenizer.json
chaiml-sft-gemma2-28b-v-83370-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v-83370-v3/flywheel_model.2.safetensors
chaiml-sft-gemma2-28b-v-83370-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v-83370-v3/flywheel_model.0.safetensors
chaiml-sft-gemma2-28b-v-83370-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v-83370-v3/flywheel_model.1.safetensors
chaiml-sft-gemma2-28b-v-83370-v3-mkmlizer: Loading 0: 0%| | 0/508 [00:00<?, ?it/s] Loading 0: 1%| | 4/508 [00:00<00:13, 36.10it/s] Loading 0: 2%|▏ | 12/508 [00:00<00:11, 42.63it/s] Loading 0: 3%|▎ | 17/508 [00:00<00:15, 32.07it/s] Loading 0: 5%|▍ | 24/508 [00:00<00:11, 41.94it/s] Loading 0: 6%|▌ | 29/508 [00:00<00:17, 27.59it/s] Loading 0: 6%|▋ | 33/508 [00:01<00:16, 29.33it/s] Loading 0: 7%|▋ | 37/508 [00:01<00:15, 31.34it/s] Loading 0: 9%|▉ | 45/508 [00:01<00:11, 39.08it/s] Loading 0: 10%|▉ | 50/508 [00:01<00:12, 35.71it/s] Loading 0: 11%|█▏ | 58/508 [00:01<00:11, 40.79it/s] Loading 0: 12%|█▏ | 63/508 [00:01<00:10, 42.10it/s] Loading 0: 13%|█▎ | 68/508 [00:01<00:11, 39.91it/s] Loading 0: 14%|█▍ | 73/508 [00:02<00:15, 28.50it/s] Loading 0: 15%|█▌ | 78/508 [00:02<00:14, 30.32it/s] Loading 0: 16%|█▌ | 82/508 [00:02<00:14, 30.08it/s] Loading 0: 17%|█▋ | 87/508 [00:02<00:12, 34.08it/s] Loading 0: 19%|█▊ | 95/508 [00:02<00:09, 42.10it/s] Loading 0: 20%|█▉ | 100/508 [00:02<00:10, 37.30it/s] Loading 0: 21%|██▏ | 108/508 [00:02<00:09, 41.19it/s] Loading 0: 22%|██▏ | 113/508 [00:03<00:09, 42.64it/s] Loading 0: 23%|██▎ | 118/508 [00:03<00:12, 32.32it/s] Loading 0: 24%|██▍ | 124/508 [00:03<00:10, 37.05it/s] Loading 0: 25%|██▌ | 129/508 [00:03<00:09, 39.28it/s] Loading 0: 27%|██▋ | 135/508 [00:03<00:09, 38.94it/s] Loading 0: 28%|██▊ | 140/508 [00:03<00:09, 40.88it/s] Loading 0: 29%|██▊ | 146/508 [00:03<00:08, 40.85it/s] Loading 0: 30%|██▉ | 151/508 [00:04<00:08, 42.50it/s] Loading 0: 31%|███ | 157/508 [00:04<00:08, 42.26it/s] Loading 0: 32%|███▏ | 162/508 [00:04<00:08, 41.53it/s] Loading 0: 33%|███▎ | 168/508 [00:04<00:07, 43.91it/s] Loading 0: 34%|███▍ | 173/508 [00:04<00:11, 28.52it/s] Loading 0: 35%|███▌ | 179/508 [00:04<00:09, 34.05it/s] Loading 0: 36%|███▌ | 184/508 [00:05<00:08, 36.89it/s] Loading 0: 37%|███▋ | 190/508 [00:05<00:08, 37.50it/s] Loading 0: 38%|███▊ | 195/508 [00:19<04:19, 1.21it/s] Loading 0: 39%|███▉ | 199/508 [00:19<03:17, 1.57it/s] Loading 0: 40%|███▉ | 203/508 [00:20<02:31, 2.01it/s] Loading 0: 42%|████▏ | 211/508 [00:20<01:28, 3.37it/s] Loading 0: 42%|████▏ | 215/508 [00:20<01:08, 4.27it/s] Loading 0: 43%|████▎ | 219/508 [00:20<00:56, 5.12it/s] Loading 0: 44%|████▍ | 224/508 [00:20<00:40, 7.06it/s] Loading 0: 46%|████▌ | 232/508 [00:21<00:24, 11.09it/s] Loading 0: 47%|████▋ | 237/508 [00:21<00:21, 12.79it/s] Loading 0: 48%|████▊ | 245/508 [00:21<00:14, 17.92it/s] Loading 0: 49%|████▉ | 250/508 [00:21<00:12, 21.32it/s] Loading 0: 50%|█████ | 255/508 [00:21<00:10, 23.21it/s] Loading 0: 51%|█████ | 260/508 [00:21<00:09, 25.43it/s] Loading 0: 52%|█████▏ | 264/508 [00:22<00:10, 22.97it/s] Loading 0: 53%|█████▎ | 268/508 [00:22<00:09, 25.67it/s] Loading 0: 54%|█████▍ | 276/508 [00:22<00:07, 32.70it/s] Loading 0: 55%|█████▌ | 280/508 [00:22<00:07, 29.96it/s] Loading 0: 57%|█████▋ | 289/508 [00:22<00:05, 37.80it/s] Loading 0: 58%|█████▊ | 294/508 [00:22<00:05, 39.73it/s] Loading 0: 59%|█████▉ | 300/508 [00:22<00:05, 38.96it/s] Loading 0: 60%|██████ | 305/508 [00:23<00:04, 40.98it/s] Loading 0: 61%|██████ | 311/508 [00:23<00:04, 45.24it/s] Loading 0: 62%|██████▏ | 316/508 [00:23<00:06, 29.62it/s] Loading 0: 63%|██████▎ | 322/508 [00:23<00:05, 35.19it/s] Loading 0: 64%|██████▍ | 327/508 [00:23<00:04, 38.28it/s] Loading 0: 66%|██████▌ | 333/508 [00:23<00:04, 38.35it/s] Loading 0: 67%|██████▋ | 338/508 [00:23<00:04, 40.93it/s] Loading 0: 68%|██████▊ | 344/508 [00:24<00:04, 39.76it/s] Loading 0: 69%|██████▊ | 349/508 [00:24<00:03, 41.69it/s] Loading 0: 70%|██████▉ | 354/508 [00:24<00:03, 38.69it/s] Loading 0: 71%|███████ | 359/508 [00:24<00:04, 32.21it/s] Loading 0: 71%|███████▏ | 363/508 [00:24<00:04, 33.21it/s] Loading 0: 72%|███████▏ | 367/508 [00:24<00:04, 34.55it/s] Loading 0: 74%|███████▍ | 375/508 [00:24<00:03, 42.08it/s] Loading 0: 75%|███████▍ | 380/508 [00:25<00:03, 36.58it/s] Loading 0: 76%|███████▋ | 388/508 [00:25<00:02, 41.06it/s] Loading 0: 77%|███████▋ | 393/508 [00:25<00:02, 42.73it/s] Loading 0: 78%|███████▊ | 398/508 [00:25<00:02, 39.77it/s] Loading 0: 79%|███████▉ | 403/508 [00:25<00:02, 39.19it/s] Loading 0: 80%|████████ | 408/508 [00:25<00:03, 32.26it/s] Loading 0: 81%|████████ | 412/508 [00:26<00:03, 30.61it/s] Loading 0: 83%|████████▎ | 421/508 [00:26<00:02, 37.63it/s] Loading 0: 84%|████████▍ | 427/508 [00:26<00:01, 42.19it/s] Loading 0: 85%|████████▌ | 432/508 [00:26<00:01, 39.55it/s] Loading 0: 86%|████████▌ | 437/508 [00:26<00:01, 41.57it/s] Loading 0: 87%|████████▋ | 443/508 [00:26<00:01, 40.70it/s] Loading 0: 88%|████████▊ | 448/508 [00:26<00:01, 42.40it/s] Loading 0: 89%|████████▉ | 451/508 [00:41<00:01, 42.40it/s] Loading 0: 89%|████████▉ | 452/508 [00:41<00:49, 1.13it/s] Loading 0: 90%|████████▉ | 456/508 [00:41<00:34, 1.50it/s] Loading 0: 91%|█████████ | 461/508 [00:41<00:22, 2.08it/s] Loading 0: 92%|█████████▏| 466/508 [00:41<00:14, 2.96it/s] Loading 0: 93%|█████████▎| 474/508 [00:42<00:07, 4.85it/s] Loading 0: 94%|█████████▍| 479/508 [00:42<00:04, 6.22it/s] Loading 0: 96%|█████████▌| 487/508 [00:42<00:02, 9.37it/s] Loading 0: 97%|█████████▋| 492/508 [00:42<00:01, 11.77it/s] Loading 0: 98%|█████████▊| 497/508 [00:42<00:00, 14.10it/s] Loading 0: 99%|█████████▉| 502/508 [00:42<00:00, 15.31it/s] Loading 0: 100%|█████████▉| 506/508 [00:43<00:00, 17.79it/s]
Job chaiml-sft-gemma2-28b-v-83370-v3-mkmlizer completed after 237.09s with status: succeeded
Stopping job with name chaiml-sft-gemma2-28b-v-83370-v3-mkmlizer
Pipeline stage MKMLizer completed in 237.54s
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-sft-gemma2-28b-v-83370-v3
Waiting for inference service chaiml-sft-gemma2-28b-v-83370-v3 to be ready
Inference service chaiml-sft-gemma2-28b-v-83370-v3 ready after 110.67088723182678s
Pipeline stage MKMLDeployer completed in 111.10s
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 3.83738374710083s
Received healthy response to inference request in 2.863128662109375s
Received healthy response to inference request in 2.8687026500701904s
Received healthy response to inference request in 2.896085023880005s
5 requests
1 failed requests
5th percentile: 2.8642434597015383
10th percentile: 2.865358257293701
20th percentile: 2.867587852478027
30th percentile: 2.8741791248321533
40th percentile: 2.885132074356079
50th percentile: 2.896085023880005
60th percentile: 3.272604513168335
70th percentile: 3.6491240024566647
80th percentile: 7.096365451812748
90th percentile: 13.614328861236574
95th percentile: 16.873310565948483
99th percentile: 19.480495929718018
mean time: 6.51951847076416
%s, retrying in %s seconds...
Received healthy response to inference request in 2.9031221866607666s
Received healthy response to inference request in 2.840728759765625s
Received healthy response to inference request in 2.857860565185547s
Received healthy response to inference request in 2.8526499271392822s
Received healthy response to inference request in 2.8387386798858643s
5 requests
0 failed requests
5th percentile: 2.8391366958618165
10th percentile: 2.8395347118377687
20th percentile: 2.8403307437896728
30th percentile: 2.8431129932403563
40th percentile: 2.8478814601898192
50th percentile: 2.8526499271392822
60th percentile: 2.854734182357788
70th percentile: 2.856818437576294
80th percentile: 2.8669128894805906
90th percentile: 2.8850175380706786
95th percentile: 2.894069862365723
99th percentile: 2.9013117218017577
mean time: 2.858620023727417
Pipeline stage StressChecker completed in 49.40s
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 0.73s
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 0.70s
Shutdown handler de-registered
chaiml-sft-gemma2-28b-v_83370_v3 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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
chaiml-sft-gemma2-28b-v_83370_v3 status is now torndown due to DeploymentManager action