chaiml-gemma-exp3-dpo-s_66157

developer_uid: NischayDnk

submission_id: chaiml-gemma-exp3-dpo-s_66157_v1

model_name: chaiml-gemma-exp3-dpo-s_66157_v1

model_group: ChaiML/gemma-exp3-dpo-sf

status: torndown

timestamp: 2025-04-02T18:29:07+00:00

num_battles: 6

num_wins: 3

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/gemma-exp3-dpo-sftv2-v10filter

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': 0.2741872519360896, 'latency_mean': 3.6470451378822326, 'latency_p50': 3.641234040260315, 'latency_p90': 4.036689805984497}, {'batch_size': 2, 'throughput': 0.41556417109916155, 'latency_mean': 4.795376657247544, 'latency_p50': 4.819035053253174, 'latency_p90': 5.262291336059571}, {'batch_size': 3, 'throughput': 0.5210660641979439, 'latency_mean': 5.735058627128601, 'latency_p50': 5.751712918281555, 'latency_p90': 6.350434279441833}, {'batch_size': 5, 'throughput': 0.6609185053498965, 'latency_mean': 7.527917665243149, 'latency_p50': 7.5459885597229, 'latency_p90': 8.38565764427185}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-gemma-exp3-dpo-s_66157_v1

ineligible_reason: num_battles<5000

is_internal_developer: False

language_model: ChaiML/gemma-exp3-dpo-sftv2-v10filter

model_size: 29B

ranking_group: single

throughput_3p7s: 0.28

us_pacific_date: 2025-04-02

win_ratio: 0.5

generation_params: {'temperature': 0.45, 'top_p': 0.95, 'min_p': 0.05, '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': '[INST]<|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-gemma-exp3-dpo-s-66157-v1-mkmlizer
Waiting for job on chaiml-gemma-exp3-dpo-s-66157-v1-mkmlizer to finish
chaiml-gemma-exp3-dpo-s-66157-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gemma-exp3-dpo-s-66157-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-gemma-exp3-dpo-s-66157-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-gemma-exp3-dpo-s-66157-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-gemma-exp3-dpo-s-66157-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-gemma-exp3-dpo-s-66157-v1-mkmlizer: ║       /___/                                                         ║
chaiml-gemma-exp3-dpo-s-66157-v1-mkmlizer: ║                                                                     ║
chaiml-gemma-exp3-dpo-s-66157-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-gemma-exp3-dpo-s-66157-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-gemma-exp3-dpo-s-66157-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gemma-exp3-dpo-s-66157-v1-mkmlizer: ║                                                                     ║
chaiml-gemma-exp3-dpo-s-66157-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gemma-exp3-dpo-s-66157-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gemma-exp3-dpo-s-66157-v1-mkmlizer: ║                                                                     ║
chaiml-gemma-exp3-dpo-s-66157-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gemma-exp3-dpo-s-66157-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gemma-exp3-dpo-s-66157-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-gemma-exp3-dpo-s-66157-v1-mkmlizer: ║                                                                     ║
chaiml-gemma-exp3-dpo-s-66157-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gemma-exp3-dpo-s-66157-v1-mkmlizer: Downloaded to shared memory in 96.663s
chaiml-gemma-exp3-dpo-s-66157-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpj1h7k515, device:0
chaiml-gemma-exp3-dpo-s-66157-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission chaiml-sft-gemma2-28b-v_83370_v2: HTTPConnectionPool(host='chaiml-sft-gemma2-28b-v-83370-v2-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-v_83370_v1: HTTPConnectionPool(host='chaiml-sft-gemma2-28b-v-83370-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-gemma-exp3-dpo-s-66157-v1-mkmlizer: quantized model in 70.547s
chaiml-gemma-exp3-dpo-s-66157-v1-mkmlizer: Processed model ChaiML/gemma-exp3-dpo-sftv2-v10filter in 167.211s
chaiml-gemma-exp3-dpo-s-66157-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gemma-exp3-dpo-s-66157-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gemma-exp3-dpo-s-66157-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gemma-exp3-dpo-s-66157-v1
chaiml-gemma-exp3-dpo-s-66157-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gemma-exp3-dpo-s-66157-v1/config.json
chaiml-gemma-exp3-dpo-s-66157-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gemma-exp3-dpo-s-66157-v1/special_tokens_map.json
chaiml-gemma-exp3-dpo-s-66157-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gemma-exp3-dpo-s-66157-v1/tokenizer_config.json
chaiml-gemma-exp3-dpo-s-66157-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/chaiml-gemma-exp3-dpo-s-66157-v1/tokenizer.model
chaiml-gemma-exp3-dpo-s-66157-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gemma-exp3-dpo-s-66157-v1/tokenizer.json
chaiml-gemma-exp3-dpo-s-66157-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-gemma-exp3-dpo-s-66157-v1/flywheel_model.2.safetensors
chaiml-gemma-exp3-dpo-s-66157-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gemma-exp3-dpo-s-66157-v1/flywheel_model.0.safetensors
chaiml-gemma-exp3-dpo-s-66157-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gemma-exp3-dpo-s-66157-v1/flywheel_model.1.safetensors
chaiml-gemma-exp3-dpo-s-66157-v1-mkmlizer: 
Loading 0:   0%|          | 0/508 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/508 [00:00<00:13, 38.21it/s]
Loading 0:   2%|▏         | 12/508 [00:00<00:11, 44.10it/s]
Loading 0:   3%|▎         | 17/508 [00:00<00:14, 33.35it/s]
Loading 0:   5%|▍         | 25/508 [00:00<00:10, 45.78it/s]
Loading 0:   6%|▌         | 31/508 [00:00<00:17, 27.02it/s]
Loading 0:   7%|▋         | 37/508 [00:01<00:14, 32.42it/s]
Loading 0:   9%|▉         | 45/508 [00:01<00:12, 37.99it/s]
Loading 0:  10%|▉         | 50/508 [00:01<00:12, 35.51it/s]
Loading 0:  11%|█▏        | 58/508 [00:01<00:11, 40.05it/s]
Loading 0:  12%|█▏        | 63/508 [00:01<00:10, 41.72it/s]
Loading 0:  13%|█▎        | 68/508 [00:01<00:11, 37.15it/s]
Loading 0:  14%|█▍        | 73/508 [00:02<00:15, 27.41it/s]
Loading 0:  15%|█▌        | 78/508 [00:02<00:14, 28.71it/s]
Loading 0:  16%|█▌        | 82/508 [00:02<00:14, 28.60it/s]
Loading 0:  17%|█▋        | 87/508 [00:02<00:12, 32.55it/s]
Loading 0:  19%|█▊        | 95/508 [00:02<00:10, 39.41it/s]
Loading 0:  20%|█▉        | 100/508 [00:02<00:11, 35.71it/s]
Loading 0:  21%|██▏       | 108/508 [00:03<00:10, 39.63it/s]
Loading 0:  22%|██▏       | 113/508 [00:03<00:09, 40.93it/s]
Loading 0:  23%|██▎       | 118/508 [00:03<00:12, 31.69it/s]
Loading 0:  24%|██▍       | 124/508 [00:03<00:10, 36.57it/s]
Loading 0:  25%|██▌       | 129/508 [00:03<00:09, 39.06it/s]
Loading 0:  27%|██▋       | 135/508 [00:03<00:09, 38.05it/s]
Loading 0:  28%|██▊       | 140/508 [00:03<00:09, 39.97it/s]
Loading 0:  29%|██▊       | 146/508 [00:04<00:09, 39.10it/s]
Loading 0:  30%|██▉       | 151/508 [00:04<00:08, 40.83it/s]
Loading 0:  31%|███       | 157/508 [00:04<00:08, 39.89it/s]
Loading 0:  32%|███▏      | 162/508 [00:04<00:08, 41.49it/s]
Loading 0:  33%|███▎      | 168/508 [00:04<00:07, 44.63it/s]
Loading 0:  34%|███▍      | 173/508 [00:04<00:11, 29.23it/s]
Loading 0:  35%|███▌      | 179/508 [00:04<00:09, 34.61it/s]
Loading 0:  36%|███▌      | 184/508 [00:05<00:08, 37.20it/s]
Loading 0:  37%|███▋      | 190/508 [00:05<00:08, 37.45it/s]
Loading 0:  38%|███▊      | 191/508 [00:20<00:08, 37.45it/s]
Loading 0:  38%|███▊      | 192/508 [00:20<05:18,  1.01s/it]
Loading 0:  39%|███▉      | 199/508 [00:20<03:09,  1.63it/s]
Loading 0:  40%|████      | 204/508 [00:20<02:18,  2.19it/s]
Loading 0:  42%|████▏     | 211/508 [00:20<01:28,  3.36it/s]
Loading 0:  43%|████▎     | 216/508 [00:20<01:06,  4.36it/s]
Loading 0:  43%|████▎     | 220/508 [00:21<00:52,  5.49it/s]
Loading 0:  44%|████▍     | 224/508 [00:21<00:40,  6.98it/s]
Loading 0:  46%|████▌     | 232/508 [00:21<00:25, 11.01it/s]
Loading 0:  46%|████▋     | 236/508 [00:21<00:21, 12.41it/s]
Loading 0:  48%|████▊     | 243/508 [00:21<00:14, 17.73it/s]
Loading 0:  49%|████▉     | 248/508 [00:21<00:13, 19.63it/s]
Loading 0:  50%|█████     | 255/508 [00:21<00:10, 23.85it/s]
Loading 0:  51%|█████     | 260/508 [00:22<00:09, 26.00it/s]
Loading 0:  52%|█████▏    | 264/508 [00:22<00:10, 23.25it/s]
Loading 0:  53%|█████▎    | 268/508 [00:22<00:09, 25.87it/s]
Loading 0:  54%|█████▍    | 276/508 [00:22<00:06, 33.44it/s]
Loading 0:  55%|█████▌    | 281/508 [00:22<00:07, 31.99it/s]
Loading 0:  57%|█████▋    | 289/508 [00:22<00:05, 36.71it/s]
Loading 0:  58%|█████▊    | 294/508 [00:23<00:05, 38.94it/s]
Loading 0:  59%|█████▉    | 300/508 [00:23<00:05, 37.68it/s]
Loading 0:  60%|██████    | 305/508 [00:23<00:05, 39.62it/s]
Loading 0:  61%|██████    | 310/508 [00:23<00:04, 41.78it/s]
Loading 0:  62%|██████▏   | 315/508 [00:23<00:06, 29.03it/s]
Loading 0:  63%|██████▎   | 319/508 [00:23<00:06, 30.59it/s]
Loading 0:  64%|██████▎   | 323/508 [00:23<00:05, 32.23it/s]
Loading 0:  65%|██████▌   | 331/508 [00:24<00:04, 38.58it/s]
Loading 0:  66%|██████▌   | 336/508 [00:24<00:04, 34.66it/s]
Loading 0:  67%|██████▋   | 342/508 [00:24<00:04, 40.07it/s]
Loading 0:  68%|██████▊   | 347/508 [00:24<00:04, 35.11it/s]
Loading 0:  69%|██████▉   | 353/508 [00:24<00:03, 39.93it/s]
Loading 0:  70%|███████   | 358/508 [00:24<00:04, 36.74it/s]
Loading 0:  71%|███████▏  | 362/508 [00:25<00:05, 27.30it/s]
Loading 0:  72%|███████▏  | 367/508 [00:25<00:04, 31.35it/s]
Loading 0:  74%|███████▍  | 375/508 [00:25<00:03, 38.12it/s]
Loading 0:  75%|███████▍  | 380/508 [00:25<00:03, 34.34it/s]
Loading 0:  76%|███████▋  | 388/508 [00:25<00:03, 38.69it/s]
Loading 0:  77%|███████▋  | 393/508 [00:25<00:02, 40.32it/s]
Loading 0:  78%|███████▊  | 398/508 [00:25<00:03, 36.66it/s]
Loading 0:  79%|███████▉  | 403/508 [00:26<00:02, 37.00it/s]
Loading 0:  80%|████████  | 407/508 [00:26<00:03, 29.58it/s]
Loading 0:  81%|████████  | 412/508 [00:26<00:03, 30.60it/s]
Loading 0:  83%|████████▎ | 421/508 [00:26<00:02, 37.76it/s]
Loading 0:  84%|████████▎ | 425/508 [00:26<00:02, 37.80it/s]
Loading 0:  85%|████████▌ | 432/508 [00:26<00:01, 40.31it/s]
Loading 0:  86%|████████▌ | 437/508 [00:27<00:01, 42.09it/s]
Loading 0:  87%|████████▋ | 443/508 [00:27<00:01, 41.60it/s]
Loading 0:  88%|████████▊ | 448/508 [00:27<00:01, 43.23it/s]
Loading 0:  89%|████████▉ | 451/508 [00:42<00:01, 43.23it/s]
Loading 0:  89%|████████▉ | 452/508 [00:42<00:50,  1.11it/s]
Loading 0:  90%|████████▉ | 456/508 [00:42<00:35,  1.46it/s]
Loading 0:  91%|█████████ | 461/508 [00:42<00:23,  2.04it/s]
Loading 0:  92%|█████████▏| 467/508 [00:42<00:13,  3.04it/s]
Loading 0:  94%|█████████▎| 476/508 [00:43<00:06,  5.10it/s]
Loading 0:  95%|█████████▍| 481/508 [00:43<00:04,  6.59it/s]
Loading 0:  96%|█████████▌| 487/508 [00:43<00:02,  8.80it/s]
Loading 0:  97%|█████████▋| 492/508 [00:43<00:01, 11.22it/s]
Loading 0:  98%|█████████▊| 497/508 [00:43<00:00, 13.56it/s]
Loading 0:  99%|█████████▉| 502/508 [00:43<00:00, 15.11it/s]
Loading 0: 100%|█████████▉| 506/508 [00:43<00:00, 17.57it/s]
                                                            
Job chaiml-gemma-exp3-dpo-s-66157-v1-mkmlizer completed after 197.34s with status: succeeded
Stopping job with name chaiml-gemma-exp3-dpo-s-66157-v1-mkmlizer
Pipeline stage MKMLizer completed in 197.78s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gemma-exp3-dpo-s-66157-v1
Waiting for inference service chaiml-gemma-exp3-dpo-s-66157-v1 to be ready
Failed to get response for submission chaiml-sft-gemma2-28b-v_83370_v2: HTTPConnectionPool(host='chaiml-sft-gemma2-28b-v-83370-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission rirv938-mistral-24b-dpo_17398_v1: HTTPConnectionPool(host='rirv938-mistral-24b-dpo-17398-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Max retries exceeded with url: /v1/models/GPT-J-6B-lit-v2:predict (Caused by ConnectTimeoutError(<urllib3.connection.HTTPConnection object at 0x7b114841b810>, 'Connection to rirv938-mistral-24b-dpo-17398-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com timed out. (connect timeout=12.0)'))
Inference service chaiml-gemma-exp3-dpo-s-66157-v1 ready after 110.42342066764832s
Pipeline stage MKMLDeployer completed in 110.99s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.19955039024353s
Received healthy response to inference request in 3.4571571350097656s
Received healthy response to inference request in 3.714331865310669s
Received healthy response to inference request in 3.638387441635132s
Received healthy response to inference request in 3.754769802093506s
5 requests
0 failed requests
5th percentile: 3.493403196334839
10th percentile: 3.529649257659912
20th percentile: 3.6021413803100586
30th percentile: 3.6535763263702394
40th percentile: 3.683954095840454
50th percentile: 3.714331865310669
60th percentile: 3.7305070400238036
70th percentile: 3.7466822147369383
80th percentile: 3.8437259197235107
90th percentile: 4.0216381549835205
95th percentile: 4.110594272613525
99th percentile: 4.181759166717529
mean time: 3.7528393268585205
%s, retrying in %s seconds...
Received healthy response to inference request in 3.4440062046051025s
Received healthy response to inference request in 3.1995646953582764s
Received healthy response to inference request in 3.4312896728515625s
Received healthy response to inference request in 3.19868803024292s
Received healthy response to inference request in 4.193392276763916s
5 requests
0 failed requests
5th percentile: 3.1988633632659913
10th percentile: 3.1990386962890627
20th percentile: 3.199389362335205
30th percentile: 3.2459096908569336
40th percentile: 3.338599681854248
50th percentile: 3.4312896728515625
60th percentile: 3.4363762855529787
70th percentile: 3.4414628982543944
80th percentile: 3.5938834190368656
90th percentile: 3.893637847900391
95th percentile: 4.043515062332153
99th percentile: 4.163416833877563
mean time: 3.4933881759643555
Pipeline stage StressChecker completed in 38.49s
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 0.64s
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 0.64s
Shutdown handler de-registered
chaiml-gemma-exp3-dpo-s_66157_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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-gemma-exp3-dpo-s-66157-v1-profiler
Waiting for inference service chaiml-gemma-exp3-dpo-s-66157-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
%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-gemma-exp3-dpo-s_66157_v1 status is now torndown due to DeploymentManager action