developer_uid: NischayDnk
submission_id: chaiml-sft-gemma2-28b-v2-_453_v4
model_name: chaiml-sft-gemma2-28b-v2-_453_v4
model_group: ChaiML/sft-gemma2-28b-v2
status: torndown
timestamp: 2025-04-01T16:02:33+00:00
num_battles: 14
num_wins: 5
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: ChaiML/sft-gemma2-28b-v2-exp1-del5ktop
model_architecture: Gemma2ForCausalLM
model_num_parameters: 28731935232.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.2747920181238682, 'latency_mean': 3.639025937318802, 'latency_p50': 3.6737970113754272, 'latency_p90': 4.014996743202209}, {'batch_size': 2, 'throughput': 0.4194489956420483, 'latency_mean': 4.748703742027283, 'latency_p50': 4.78442108631134, 'latency_p90': 5.261774468421936}, {'batch_size': 3, 'throughput': 0.5329673889182414, 'latency_mean': 5.605153743028641, 'latency_p50': 5.590205430984497, 'latency_p90': 6.175395393371582}, {'batch_size': 5, 'throughput': 0.6726938959016515, 'latency_mean': 7.400698266029358, 'latency_p50': 7.3747031688690186, 'latency_p90': 8.17700445652008}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-sft-gemma2-28b-v2-_453_v4
ineligible_reason: num_battles<5000
is_internal_developer: False
language_model: ChaiML/sft-gemma2-28b-v2-exp1-del5ktop
model_size: 29B
ranking_group: single
throughput_3p7s: 0.29
us_pacific_date: 2025-04-01
win_ratio: 0.35714285714285715
generation_params: {'temperature': 0.4, 'top_p': 0.925, 'min_p': 0.05, 'top_k': 60, 'presence_penalty': 0.05, 'frequency_penalty': 0.05, 'stopping_words': ['<|im_end|>', '###', 'Me:', '\n', 'You:'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{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-sft-gemma2-28b-v2-453-v4-mkmlizer
Waiting for job on chaiml-sft-gemma2-28b-v2-453-v4-mkmlizer to finish
chaiml-sft-gemma2-28b-v2-453-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sft-gemma2-28b-v2-453-v4-mkmlizer: ║ _____ __ __ ║
chaiml-sft-gemma2-28b-v2-453-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-sft-gemma2-28b-v2-453-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-sft-gemma2-28b-v2-453-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-sft-gemma2-28b-v2-453-v4-mkmlizer: ║ /___/ ║
chaiml-sft-gemma2-28b-v2-453-v4-mkmlizer: ║ ║
chaiml-sft-gemma2-28b-v2-453-v4-mkmlizer: ║ Version: 0.12.8 ║
chaiml-sft-gemma2-28b-v2-453-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-sft-gemma2-28b-v2-453-v4-mkmlizer: ║ https://mk1.ai ║
chaiml-sft-gemma2-28b-v2-453-v4-mkmlizer: ║ ║
chaiml-sft-gemma2-28b-v2-453-v4-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-sft-gemma2-28b-v2-453-v4-mkmlizer: ║ belonging to: ║
chaiml-sft-gemma2-28b-v2-453-v4-mkmlizer: ║ ║
chaiml-sft-gemma2-28b-v2-453-v4-mkmlizer: ║ Chai Research Corp. ║
chaiml-sft-gemma2-28b-v2-453-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-sft-gemma2-28b-v2-453-v4-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
chaiml-sft-gemma2-28b-v2-453-v4-mkmlizer: ║ ║
chaiml-sft-gemma2-28b-v2-453-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission chaiml-sft-gemma2-28b-v2-_453_v3: HTTPConnectionPool(host='chaiml-sft-gemma2-28b-v2-453-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-sft-gemma2-28b-v2-_453_v3: HTTPConnectionPool(host='chaiml-sft-gemma2-28b-v2-453-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-sft-gemma2-28b-v2-453-v4-mkmlizer: Downloaded to shared memory in 77.296s
chaiml-sft-gemma2-28b-v2-453-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpd00057zu, device:0
chaiml-sft-gemma2-28b-v2-453-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-sft-gemma2-28b-v2-453-v4-mkmlizer: quantized model in 67.998s
chaiml-sft-gemma2-28b-v2-453-v4-mkmlizer: Processed model ChaiML/sft-gemma2-28b-v2-exp1-del5ktop in 145.295s
chaiml-sft-gemma2-28b-v2-453-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sft-gemma2-28b-v2-453-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sft-gemma2-28b-v2-453-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v2-453-v4
chaiml-sft-gemma2-28b-v2-453-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v2-453-v4/config.json
chaiml-sft-gemma2-28b-v2-453-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v2-453-v4/special_tokens_map.json
chaiml-sft-gemma2-28b-v2-453-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v2-453-v4/tokenizer_config.json
chaiml-sft-gemma2-28b-v2-453-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v2-453-v4/tokenizer.model
chaiml-sft-gemma2-28b-v2-453-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v2-453-v4/tokenizer.json
chaiml-sft-gemma2-28b-v2-453-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v2-453-v4/flywheel_model.2.safetensors
Failed to get response for submission chaiml-sft-gemma2-28b-v2-_453_v3: HTTPConnectionPool(host='chaiml-sft-gemma2-28b-v2-453-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-sft-gemma2-28b-v2-_453_v3: HTTPConnectionPool(host='chaiml-sft-gemma2-28b-v2-453-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-sft-gemma2-28b-v2-453-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v2-453-v4/flywheel_model.0.safetensors
chaiml-sft-gemma2-28b-v2-453-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v2-453-v4/flywheel_model.1.safetensors
chaiml-sft-gemma2-28b-v2-453-v4-mkmlizer: Loading 0: 0%| | 0/508 [00:00<?, ?it/s] Loading 0: 1%| | 4/508 [00:00<00:12, 39.53it/s] Loading 0: 2%|▏ | 12/508 [00:00<00:10, 46.01it/s] Loading 0: 3%|▎ | 17/508 [00:00<00:14, 34.36it/s] Loading 0: 5%|▌ | 27/508 [00:00<00:10, 43.95it/s] Loading 0: 6%|▋ | 32/508 [00:00<00:16, 28.16it/s] Loading 0: 7%|▋ | 38/508 [00:01<00:15, 31.06it/s] Loading 0: 9%|▉ | 47/508 [00:01<00:11, 38.52it/s] Loading 0: 10%|█ | 52/508 [00:01<00:11, 40.39it/s] Loading 0: 11%|█▏ | 58/508 [00:01<00:11, 40.42it/s] Loading 0: 12%|█▏ | 63/508 [00:01<00:10, 42.02it/s] Loading 0: 13%|█▎ | 68/508 [00:01<00:11, 39.18it/s] Loading 0: 14%|█▍ | 73/508 [00:02<00:15, 27.30it/s] Loading 0: 15%|█▌ | 78/508 [00:02<00:14, 29.52it/s] Loading 0: 16%|█▌ | 82/508 [00:02<00:14, 29.70it/s] Loading 0: 17%|█▋ | 87/508 [00:02<00:12, 33.79it/s] Loading 0: 19%|█▊ | 95/508 [00:02<00:10, 40.81it/s] Loading 0: 20%|█▉ | 100/508 [00:02<00:11, 36.80it/s] Loading 0: 21%|██▏ | 108/508 [00:02<00:09, 41.97it/s] Loading 0: 22%|██▏ | 113/508 [00:03<00:09, 43.34it/s] Loading 0: 23%|██▎ | 118/508 [00:03<00:12, 32.14it/s] Loading 0: 24%|██▍ | 124/508 [00:03<00:10, 37.16it/s] Loading 0: 25%|██▌ | 129/508 [00:03<00:09, 39.65it/s] Loading 0: 27%|██▋ | 135/508 [00:03<00:09, 39.72it/s] Loading 0: 28%|██▊ | 140/508 [00:03<00:08, 41.62it/s] Loading 0: 29%|██▊ | 146/508 [00:03<00:08, 42.12it/s] Loading 0: 30%|██▉ | 151/508 [00:04<00:08, 43.63it/s] Loading 0: 31%|███ | 157/508 [00:04<00:08, 42.72it/s] Loading 0: 32%|███▏ | 162/508 [00:04<00:07, 43.31it/s] Loading 0: 33%|███▎ | 168/508 [00:04<00:07, 45.35it/s] Loading 0: 34%|███▍ | 173/508 [00:04<00:11, 27.93it/s] Loading 0: 35%|███▌ | 179/508 [00:04<00:09, 33.57it/s] Loading 0: 36%|███▌ | 184/508 [00:04<00:08, 36.81it/s] Loading 0: 37%|███▋ | 190/508 [00:05<00:08, 37.47it/s] Loading 0: 38%|███▊ | 195/508 [00:19<04:14, 1.23it/s] Loading 0: 39%|███▉ | 199/508 [00:19<03:13, 1.60it/s] Loading 0: 40%|████ | 204/508 [00:19<02:19, 2.17it/s] Loading 0: 42%|████▏ | 211/508 [00:20<01:27, 3.39it/s] Loading 0: 43%|████▎ | 216/508 [00:20<01:05, 4.42it/s] Loading 0: 43%|████▎ | 220/508 [00:20<00:51, 5.59it/s] Loading 0: 44%|████▍ | 225/508 [00:20<00:37, 7.46it/s] Loading 0: 46%|████▌ | 234/508 [00:20<00:22, 11.97it/s] Loading 0: 47%|████▋ | 238/508 [00:20<00:19, 14.07it/s] Loading 0: 48%|████▊ | 245/508 [00:21<00:13, 18.85it/s] Loading 0: 49%|████▉ | 250/508 [00:21<00:11, 22.46it/s] Loading 0: 50%|█████ | 255/508 [00:21<00:10, 24.53it/s] Loading 0: 51%|█████ | 260/508 [00:21<00:08, 27.69it/s] Loading 0: 52%|█████▏ | 265/508 [00:21<00:09, 26.03it/s] Loading 0: 53%|█████▎ | 269/508 [00:21<00:09, 26.03it/s] Loading 0: 55%|█████▍ | 278/508 [00:21<00:06, 34.05it/s] Loading 0: 56%|█████▌ | 282/508 [00:22<00:06, 35.05it/s] Loading 0: 57%|█████▋ | 289/508 [00:22<00:05, 38.68it/s] Loading 0: 58%|█████▊ | 294/508 [00:22<00:05, 40.82it/s] Loading 0: 59%|█████▉ | 300/508 [00:22<00:05, 41.22it/s] Loading 0: 60%|██████ | 305/508 [00:22<00:04, 42.86it/s] Loading 0: 61%|██████▏ | 312/508 [00:22<00:03, 49.59it/s] Loading 0: 63%|██████▎ | 318/508 [00:22<00:06, 30.54it/s] Loading 0: 64%|██████▎ | 323/508 [00:23<00:05, 34.01it/s] Loading 0: 65%|██████▌ | 331/508 [00:23<00:04, 40.36it/s] Loading 0: 66%|██████▌ | 336/508 [00:23<00:04, 36.75it/s] Loading 0: 68%|██████▊ | 344/508 [00:23<00:03, 42.00it/s] Loading 0: 69%|██████▊ | 349/508 [00:23<00:03, 43.29it/s] Loading 0: 70%|██████▉ | 354/508 [00:23<00:04, 38.32it/s] Loading 0: 71%|███████ | 359/508 [00:24<00:04, 30.96it/s] Loading 0: 71%|███████▏ | 363/508 [00:24<00:04, 32.23it/s] Loading 0: 72%|███████▏ | 368/508 [00:24<00:04, 32.58it/s] Loading 0: 74%|███████▍ | 377/508 [00:24<00:03, 39.80it/s] Loading 0: 75%|███████▌ | 382/508 [00:24<00:03, 41.84it/s] Loading 0: 76%|███████▋ | 388/508 [00:24<00:02, 41.70it/s] Loading 0: 77%|███████▋ | 393/508 [00:24<00:02, 43.28it/s] Loading 0: 78%|███████▊ | 398/508 [00:24<00:02, 39.44it/s] Loading 0: 79%|███████▉ | 403/508 [00:25<00:02, 38.61it/s] Loading 0: 80%|████████ | 407/508 [00:25<00:03, 30.73it/s] Loading 0: 81%|████████ | 412/508 [00:25<00:03, 31.63it/s] Loading 0: 83%|████████▎ | 421/508 [00:25<00:02, 37.51it/s] Loading 0: 84%|████████▎ | 425/508 [00:25<00:02, 37.57it/s] Loading 0: 85%|████████▌ | 432/508 [00:25<00:01, 38.58it/s] Loading 0: 86%|████████▌ | 436/508 [00:26<00:01, 38.22it/s] Loading 0: 87%|████████▋ | 443/508 [00:26<00:01, 39.71it/s] Loading 0: 88%|████████▊ | 447/508 [00:26<00:01, 39.40it/s] Loading 0: 89%|████████▉ | 451/508 [00:40<00:01, 39.40it/s] Loading 0: 89%|████████▉ | 452/508 [00:40<00:47, 1.17it/s] Loading 0: 90%|████████▉ | 456/508 [00:40<00:33, 1.54it/s] Loading 0: 91%|█████████ | 460/508 [00:41<00:24, 1.98it/s] Loading 0: 92%|█████████▏| 466/508 [00:41<00:13, 3.04it/s] Loading 0: 93%|█████████▎| 474/508 [00:41<00:06, 4.93it/s] Loading 0: 94%|█████████▍| 479/508 [00:41<00:04, 6.30it/s] Loading 0: 96%|█████████▌| 487/508 [00:41<00:02, 9.46it/s] Loading 0: 97%|█████████▋| 492/508 [00:42<00:01, 11.87it/s] Loading 0: 98%|█████████▊| 497/508 [00:42<00:00, 14.28it/s] Loading 0: 99%|█████████▉| 502/508 [00:42<00:00, 15.32it/s] Loading 0: 100%|█████████▉| 506/508 [00:42<00:00, 17.85it/s]
Job chaiml-sft-gemma2-28b-v2-453-v4-mkmlizer completed after 186.16s with status: succeeded
Stopping job with name chaiml-sft-gemma2-28b-v2-453-v4-mkmlizer
Pipeline stage MKMLizer completed in 186.64s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.36s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-sft-gemma2-28b-v2-453-v4
Waiting for inference service chaiml-sft-gemma2-28b-v2-453-v4 to be ready
Inference service chaiml-sft-gemma2-28b-v2-453-v4 ready after 120.52935719490051s
Pipeline stage MKMLDeployer completed in 121.11s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.073578834533691s
Received healthy response to inference request in 3.3226096630096436s
Received healthy response to inference request in 3.5434460639953613s
Received healthy response to inference request in 3.503762722015381s
Received healthy response to inference request in 3.3031604290008545s
5 requests
0 failed requests
5th percentile: 3.307050275802612
10th percentile: 3.31094012260437
20th percentile: 3.318719816207886
30th percentile: 3.358840274810791
40th percentile: 3.431301498413086
50th percentile: 3.503762722015381
60th percentile: 3.519636058807373
70th percentile: 3.535509395599365
80th percentile: 3.6494726181030273
90th percentile: 3.8615257263183596
95th percentile: 3.9675522804260255
99th percentile: 4.052373523712158
mean time: 3.5493115425109862
Pipeline stage StressChecker completed in 19.23s
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 0.85s
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-sft-gemma2-28b-v2-_453_v4 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-v2-_453_v4 status is now torndown due to DeploymentManager action