developer_uid: NischayDnk
submission_id: chaiml-exp71-dpo-ftexp1_51186_v1
model_name: chaiml-exp71-dpo-ftexp1_51186_v1
model_group: ChaiML/exp71-dpo-ftexp13
status: torndown
timestamp: 2025-03-13T04:22:48+00:00
num_battles: 8271
num_wins: 4383
celo_rating: 1281.37
family_friendly_score: 0.5916
family_friendly_standard_error: 0.006951394680206268
submission_type: basic
model_repo: ChaiML/exp71-dpo-ftexp13sft-24B-ssdelnofiltered15K-s035
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': 0.36835432097179316, 'latency_mean': 2.7147163450717926, 'latency_p50': 2.7282334566116333, 'latency_p90': 3.01403648853302}, {'batch_size': 2, 'throughput': 0.5787233082928176, 'latency_mean': 3.442835559844971, 'latency_p50': 3.4463776350021362, 'latency_p90': 3.7838124752044675}, {'batch_size': 3, 'throughput': 0.7334697589048135, 'latency_mean': 4.088828419446945, 'latency_p50': 4.093745708465576, 'latency_p90': 4.468846797943115}, {'batch_size': 4, 'throughput': 0.8475014750159797, 'latency_mean': 4.702283269166946, 'latency_p50': 4.714130759239197, 'latency_p90': 5.163427424430847}, {'batch_size': 5, 'throughput': 0.9534910328053707, 'latency_mean': 5.231549957990646, 'latency_p50': 5.1981284618377686, 'latency_p90': 5.859228491783142}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-exp71-dpo-ftexp1_51186_v1
is_internal_developer: False
language_model: ChaiML/exp71-dpo-ftexp13sft-24B-ssdelnofiltered15K-s035
model_size: 24B
ranking_group: single
throughput_3p7s: 0.65
us_pacific_date: 2025-03-12
win_ratio: 0.529923830250272
generation_params: {'temperature': 0.45, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['You:', '###', '\n', '</s>'], '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}:[/INST]', '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-exp71-dpo-ftexp1-51186-v1-mkmlizer
Waiting for job on chaiml-exp71-dpo-ftexp1-51186-v1-mkmlizer to finish
chaiml-exp71-dpo-ftexp1-51186-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp71-dpo-ftexp1-51186-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-exp71-dpo-ftexp1-51186-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-exp71-dpo-ftexp1-51186-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-exp71-dpo-ftexp1-51186-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-exp71-dpo-ftexp1-51186-v1-mkmlizer: ║       /___/                                                         ║
chaiml-exp71-dpo-ftexp1-51186-v1-mkmlizer: ║                                                                     ║
chaiml-exp71-dpo-ftexp1-51186-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-exp71-dpo-ftexp1-51186-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-exp71-dpo-ftexp1-51186-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-exp71-dpo-ftexp1-51186-v1-mkmlizer: ║                                                                     ║
chaiml-exp71-dpo-ftexp1-51186-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-exp71-dpo-ftexp1-51186-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-exp71-dpo-ftexp1-51186-v1-mkmlizer: ║                                                                     ║
chaiml-exp71-dpo-ftexp1-51186-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-exp71-dpo-ftexp1-51186-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-exp71-dpo-ftexp1-51186-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-exp71-dpo-ftexp1-51186-v1-mkmlizer: ║                                                                     ║
chaiml-exp71-dpo-ftexp1-51186-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission jellywibble-enzo-mafia-enemy_v12: HTTPConnectionPool(host='jellywibble-enzo-mafia-enemy-v12-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission jellywibble-enzo-mafia-enemy_v12: HTTPConnectionPool(host='jellywibble-enzo-mafia-enemy-v12-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-exp71-dpo-ftexp1-51186-v1-mkmlizer: Downloaded to shared memory in 80.110s
chaiml-exp71-dpo-ftexp1-51186-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpw7kjgegq, device:0
chaiml-exp71-dpo-ftexp1-51186-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-exp71-dpo-ftexp1-51186-v1-mkmlizer: quantized model in 55.729s
chaiml-exp71-dpo-ftexp1-51186-v1-mkmlizer: Processed model ChaiML/exp71-dpo-ftexp13sft-24B-ssdelnofiltered15K-s035 in 135.840s
chaiml-exp71-dpo-ftexp1-51186-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-exp71-dpo-ftexp1-51186-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp71-dpo-ftexp1-51186-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp71-dpo-ftexp1-51186-v1
chaiml-exp71-dpo-ftexp1-51186-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp71-dpo-ftexp1-51186-v1/config.json
chaiml-exp71-dpo-ftexp1-51186-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp71-dpo-ftexp1-51186-v1/special_tokens_map.json
chaiml-exp71-dpo-ftexp1-51186-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp71-dpo-ftexp1-51186-v1/tokenizer_config.json
chaiml-exp71-dpo-ftexp1-51186-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-exp71-dpo-ftexp1-51186-v1/tokenizer.json
chaiml-exp71-dpo-ftexp1-51186-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-exp71-dpo-ftexp1-51186-v1/flywheel_model.1.safetensors
chaiml-exp71-dpo-ftexp1-51186-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp71-dpo-ftexp1-51186-v1/flywheel_model.0.safetensors
chaiml-exp71-dpo-ftexp1-51186-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 36.05it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:12, 28.40it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 29.85it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:13, 26.42it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:11, 29.75it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:12, 27.11it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:09, 34.74it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:14, 22.17it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:14, 22.48it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:17, 18.40it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:14, 22.40it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:13, 23.24it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:13, 23.16it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:11, 26.56it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:13, 23.15it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:11, 25.88it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 23.22it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:14, 19.74it/s]
Loading 0:  21%|██▏       | 78/363 [00:03<00:11, 24.97it/s]
Loading 0:  22%|██▏       | 81/363 [00:03<00:12, 22.04it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 24.34it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:11, 23.86it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:14, 19.26it/s]
Loading 0:  27%|██▋       | 97/363 [00:04<00:10, 24.52it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:10, 24.89it/s]
Loading 0:  28%|██▊       | 103/363 [00:04<00:10, 23.89it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:12, 21.29it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:10, 24.58it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:11, 22.55it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 28.37it/s]
Loading 0:  34%|███▍      | 124/363 [00:05<00:08, 27.17it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:07, 30.08it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:08, 28.72it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 30.75it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 28.40it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:06, 33.83it/s]
Loading 0:  42%|████▏     | 153/363 [00:06<00:09, 21.25it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:08, 23.73it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 23.20it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:08, 24.15it/s]
Loading 0:  46%|████▌     | 166/363 [00:06<00:08, 24.18it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:08, 23.36it/s]
Loading 0:  48%|████▊     | 174/363 [00:07<00:07, 25.80it/s]
Loading 0:  49%|████▉     | 177/363 [00:07<00:08, 22.68it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:06, 26.33it/s]
Loading 0:  51%|█████     | 186/363 [00:07<00:06, 27.94it/s]
Loading 0:  52%|█████▏    | 189/363 [00:07<00:09, 17.84it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:08, 20.82it/s]
Loading 0:  54%|█████▍    | 196/363 [00:08<00:07, 21.27it/s]
Loading 0:  55%|█████▌    | 200/363 [00:08<00:06, 25.05it/s]
Loading 0:  55%|█████▌    | 200/363 [00:23<00:06, 25.05it/s]
Loading 0:  55%|█████▌    | 201/363 [00:23<04:15,  1.58s/it]
Loading 0:  56%|█████▌    | 203/363 [00:23<03:18,  1.24s/it]
Loading 0:  57%|█████▋    | 208/363 [00:23<01:47,  1.44it/s]
Loading 0:  58%|█████▊    | 211/363 [00:23<01:19,  1.91it/s]
Loading 0:  59%|█████▉    | 214/363 [00:23<00:57,  2.59it/s]
Loading 0:  60%|██████    | 218/363 [00:23<00:38,  3.79it/s]
Loading 0:  61%|██████    | 221/363 [00:24<00:28,  4.91it/s]
Loading 0:  62%|██████▏   | 224/363 [00:24<00:23,  5.97it/s]
Loading 0:  63%|██████▎   | 228/363 [00:24<00:15,  8.45it/s]
Loading 0:  64%|██████▎   | 231/363 [00:24<00:13,  9.85it/s]
Loading 0:  65%|██████▌   | 237/363 [00:24<00:08, 14.65it/s]
Loading 0:  66%|██████▌   | 240/363 [00:24<00:08, 14.85it/s]
Loading 0:  68%|██████▊   | 246/363 [00:25<00:05, 19.78it/s]
Loading 0:  69%|██████▊   | 249/363 [00:25<00:06, 18.85it/s]
Loading 0:  70%|██████▉   | 253/363 [00:25<00:04, 22.11it/s]
Loading 0:  71%|███████   | 256/363 [00:25<00:04, 22.87it/s]
Loading 0:  71%|███████▏  | 259/363 [00:25<00:04, 22.55it/s]
Loading 0:  72%|███████▏  | 262/363 [00:25<00:04, 24.13it/s]
Loading 0:  74%|███████▎  | 267/363 [00:25<00:04, 21.86it/s]
Loading 0:  74%|███████▍  | 270/363 [00:26<00:04, 18.71it/s]
Loading 0:  75%|███████▌  | 274/363 [00:26<00:04, 21.58it/s]
Loading 0:  76%|███████▋  | 277/363 [00:26<00:03, 21.79it/s]
Loading 0:  77%|███████▋  | 280/363 [00:26<00:03, 23.29it/s]
Loading 0:  78%|███████▊  | 283/363 [00:26<00:03, 24.02it/s]
Loading 0:  79%|███████▉  | 286/363 [00:26<00:03, 22.86it/s]
Loading 0:  80%|███████▉  | 289/363 [00:26<00:03, 24.03it/s]
Loading 0:  80%|████████  | 292/363 [00:27<00:02, 24.14it/s]
Loading 0:  81%|████████▏ | 295/363 [00:27<00:03, 22.40it/s]
Loading 0:  82%|████████▏ | 298/363 [00:27<00:02, 23.97it/s]
Loading 0:  83%|████████▎ | 303/363 [00:27<00:02, 26.46it/s]
Loading 0:  84%|████████▍ | 306/363 [00:27<00:03, 17.11it/s]
Loading 0:  85%|████████▌ | 310/363 [00:27<00:02, 20.46it/s]
Loading 0:  86%|████████▌ | 313/363 [00:28<00:02, 21.13it/s]
Loading 0:  88%|████████▊ | 318/363 [00:28<00:01, 24.41it/s]
Loading 0:  88%|████████▊ | 321/363 [00:28<00:01, 22.25it/s]
Loading 0:  90%|█████████ | 327/363 [00:28<00:01, 27.45it/s]
Loading 0:  91%|█████████ | 330/363 [00:28<00:01, 24.35it/s]
Loading 0:  92%|█████████▏| 334/363 [00:28<00:01, 27.41it/s]
Loading 0:  93%|█████████▎| 337/363 [00:28<00:01, 23.50it/s]
Loading 0:  94%|█████████▍| 341/363 [00:35<00:12,  1.74it/s]
Loading 0:  96%|█████████▌| 347/363 [00:35<00:05,  2.84it/s]
Loading 0:  96%|█████████▋| 350/363 [00:36<00:03,  3.55it/s]
Loading 0:  98%|█████████▊| 355/363 [00:36<00:01,  5.23it/s]
Loading 0:  99%|█████████▉| 359/363 [00:36<00:00,  6.75it/s]
                                                            

Job chaiml-exp71-dpo-ftexp1-51186-v1-mkmlizer completed after 165.43s with status: succeeded
Stopping job with name chaiml-exp71-dpo-ftexp1-51186-v1-mkmlizer
Pipeline stage MKMLizer completed in 165.93s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-exp71-dpo-ftexp1-51186-v1
Waiting for inference service chaiml-exp71-dpo-ftexp1-51186-v1 to be ready
Failed to get response for submission jellywibble-enzo-mafia-enemy_v12: HTTPConnectionPool(host='jellywibble-enzo-mafia-enemy-v12-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-exp71-dpo-ftexp1-51186-v1 ready after 100.38833975791931s
Pipeline stage MKMLDeployer completed in 100.90s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.0842411518096924s
Received healthy response to inference request in 2.3813412189483643s
Received healthy response to inference request in 2.487298011779785s
Received healthy response to inference request in 2.3608484268188477s
Received healthy response to inference request in 1.5278294086456299s
5 requests
0 failed requests
5th percentile: 1.6944332122802734
10th percentile: 1.861037015914917
20th percentile: 2.194244623184204
30th percentile: 2.364946985244751
40th percentile: 2.373144102096558
50th percentile: 2.3813412189483643
60th percentile: 2.4237239360809326
70th percentile: 2.466106653213501
80th percentile: 2.606686639785767
90th percentile: 2.8454638957977294
95th percentile: 2.9648525238037107
99th percentile: 3.060363426208496
mean time: 2.368311643600464
Pipeline stage StressChecker completed in 13.07s
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 0.64s
Shutdown handler de-registered
chaiml-exp71-dpo-ftexp1_51186_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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-exp71-dpo-ftexp1-51186-v1-profiler
Waiting for inference service chaiml-exp71-dpo-ftexp1-51186-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 5629.29s
Shutdown handler de-registered
chaiml-exp71-dpo-ftexp1_51186_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-exp71-dpo-ftexp1_51186_v1 status is now torndown due to DeploymentManager action