billxbf-nemo-sft-orpo

developer_uid: billxbf
submission_id: billxbf-nemo-sft-orpo_v1
model_name: billxbf-nemo-sft-orpo_v1
model_group: billxbf/nemo-sft-orpo
status: torndown
timestamp: 2025-02-09T20:12:34+00:00
num_battles: 12092
num_wins: 5901
celo_rating: 1260.95
family_friendly_score: 0.569
family_friendly_standard_error: 0.007003413453452538
submission_type: basic
model_repo: billxbf/nemo-sft-orpo
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: billxbf-nemo-sft-orpo_v1
is_internal_developer: False
language_model: billxbf/nemo-sft-orpo
model_size: 13B
ranking_group: single
us_pacific_date: 2025-02-09
win_ratio: 0.48800860072775387
generation_params: {'temperature': 1.1, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{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 billxbf-nemo-sft-orpo-v1-mkmlizer
Waiting for job on billxbf-nemo-sft-orpo-v1-mkmlizer to finish
billxbf-nemo-sft-orpo-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
billxbf-nemo-sft-orpo-v1-mkmlizer: ║     _____            __           __                                ║
billxbf-nemo-sft-orpo-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
billxbf-nemo-sft-orpo-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
billxbf-nemo-sft-orpo-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
billxbf-nemo-sft-orpo-v1-mkmlizer: ║       /___/                                                         ║
billxbf-nemo-sft-orpo-v1-mkmlizer: ║                                                                     ║
billxbf-nemo-sft-orpo-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
billxbf-nemo-sft-orpo-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
billxbf-nemo-sft-orpo-v1-mkmlizer: ║  https://mk1.ai                                                     ║
billxbf-nemo-sft-orpo-v1-mkmlizer: ║                                                                     ║
billxbf-nemo-sft-orpo-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
billxbf-nemo-sft-orpo-v1-mkmlizer: ║  belonging to:                                                      ║
billxbf-nemo-sft-orpo-v1-mkmlizer: ║                                                                     ║
billxbf-nemo-sft-orpo-v1-mkmlizer: ║  Chai Research Corp.                                                ║
billxbf-nemo-sft-orpo-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
billxbf-nemo-sft-orpo-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
billxbf-nemo-sft-orpo-v1-mkmlizer: ║                                                                     ║
billxbf-nemo-sft-orpo-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission leosheng-ft-dpo-10074_v2: HTTPConnectionPool(host='leosheng-ft-dpo-10074-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
billxbf-nemo-sft-orpo-v1-mkmlizer: Downloaded to shared memory in 48.354s
billxbf-nemo-sft-orpo-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmppx5wd1zx, device:0
billxbf-nemo-sft-orpo-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
billxbf-nemo-sft-orpo-v1-mkmlizer: quantized model in 35.441s
billxbf-nemo-sft-orpo-v1-mkmlizer: Processed model billxbf/nemo-sft-orpo in 83.796s
billxbf-nemo-sft-orpo-v1-mkmlizer: creating bucket guanaco-mkml-models
billxbf-nemo-sft-orpo-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
billxbf-nemo-sft-orpo-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/billxbf-nemo-sft-orpo-v1
billxbf-nemo-sft-orpo-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/billxbf-nemo-sft-orpo-v1/config.json
billxbf-nemo-sft-orpo-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/billxbf-nemo-sft-orpo-v1/special_tokens_map.json
billxbf-nemo-sft-orpo-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/billxbf-nemo-sft-orpo-v1/tokenizer_config.json
billxbf-nemo-sft-orpo-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/billxbf-nemo-sft-orpo-v1/tokenizer.json
Failed to get response for submission leosheng-ft-dpo-10074_v2: HTTPConnectionPool(host='leosheng-ft-dpo-10074-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
billxbf-nemo-sft-orpo-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/billxbf-nemo-sft-orpo-v1/flywheel_model.0.safetensors
billxbf-nemo-sft-orpo-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:11,  3.02s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:51,  1.23it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:43,  3.38it/s]
Loading 0:   6%|▌         | 20/363 [00:06<00:56,  6.11it/s]
Loading 0:   7%|▋         | 25/363 [00:06<00:39,  8.57it/s]
Loading 0:   9%|▉         | 32/363 [00:06<00:25, 13.13it/s]
Loading 0:  10%|█         | 38/363 [00:06<00:19, 17.09it/s]
Loading 0:  12%|█▏        | 43/363 [00:07<00:18, 17.48it/s]
Loading 0:  14%|█▍        | 50/363 [00:07<00:13, 23.44it/s]
Loading 0:  15%|█▌        | 56/363 [00:07<00:11, 27.39it/s]
Loading 0:  17%|█▋        | 61/363 [00:07<00:10, 30.19it/s]
Loading 0:  18%|█▊        | 67/363 [00:07<00:08, 35.65it/s]
Loading 0:  20%|█▉        | 72/363 [00:07<00:07, 36.73it/s]
Loading 0:  21%|██        | 77/363 [00:07<00:07, 39.00it/s]
Loading 0:  23%|██▎       | 83/363 [00:07<00:06, 40.53it/s]
Loading 0:  24%|██▍       | 88/363 [00:08<00:06, 41.27it/s]
Loading 0:  26%|██▌       | 95/363 [00:08<00:05, 46.98it/s]
Loading 0:  28%|██▊       | 101/363 [00:08<00:05, 46.34it/s]
Loading 0:  29%|██▉       | 106/363 [00:08<00:05, 45.84it/s]
Loading 0:  31%|███       | 112/363 [00:08<00:05, 49.32it/s]
Loading 0:  33%|███▎      | 118/363 [00:08<00:04, 50.90it/s]
Loading 0:  34%|███▍      | 124/363 [00:08<00:07, 33.61it/s]
Loading 0:  36%|███▌      | 130/363 [00:09<00:06, 38.71it/s]
Loading 0:  37%|███▋      | 135/363 [00:09<00:05, 40.32it/s]
Loading 0:  39%|███▊      | 140/363 [00:09<00:05, 42.40it/s]
Loading 0:  40%|████      | 146/363 [00:09<00:05, 42.14it/s]
Loading 0:  42%|████▏     | 151/363 [00:09<00:05, 40.73it/s]
Loading 0:  43%|████▎     | 157/363 [00:09<00:04, 43.70it/s]
Loading 0:  45%|████▍     | 162/363 [00:09<00:04, 43.95it/s]
Loading 0:  46%|████▌     | 167/363 [00:09<00:04, 45.13it/s]
Loading 0:  48%|████▊     | 173/363 [00:09<00:04, 43.62it/s]
Loading 0:  49%|████▉     | 178/363 [00:10<00:04, 42.16it/s]
Loading 0:  51%|█████     | 184/363 [00:10<00:03, 45.69it/s]
Loading 0:  52%|█████▏    | 189/363 [00:10<00:03, 45.39it/s]
Loading 0:  53%|█████▎    | 194/363 [00:10<00:03, 45.97it/s]
Loading 0:  55%|█████▌    | 200/363 [00:10<00:03, 43.43it/s]
Loading 0:  56%|█████▋    | 205/363 [00:10<00:05, 30.14it/s]
Loading 0:  58%|█████▊    | 211/363 [00:11<00:04, 34.25it/s]
Loading 0:  59%|█████▉    | 215/363 [00:11<00:04, 34.71it/s]
Loading 0:  61%|██████    | 220/363 [00:11<00:03, 37.06it/s]
Loading 0:  62%|██████▏   | 225/363 [00:11<00:03, 39.58it/s]
Loading 0:  63%|██████▎   | 230/363 [00:11<00:03, 42.16it/s]
Loading 0:  65%|██████▌   | 236/363 [00:11<00:02, 42.58it/s]
Loading 0:  66%|██████▋   | 241/363 [00:11<00:02, 42.41it/s]
Loading 0:  68%|██████▊   | 247/363 [00:11<00:02, 46.48it/s]
Loading 0:  69%|██████▉   | 252/363 [00:11<00:02, 47.00it/s]
Loading 0:  71%|███████   | 257/363 [00:12<00:02, 47.22it/s]
Loading 0:  72%|███████▏  | 263/363 [00:12<00:02, 44.58it/s]
Loading 0:  74%|███████▍  | 268/363 [00:12<00:02, 44.26it/s]
Loading 0:  76%|███████▌  | 275/363 [00:12<00:01, 48.32it/s]
Loading 0:  77%|███████▋  | 281/363 [00:12<00:01, 45.47it/s]
Loading 0:  79%|███████▉  | 286/363 [00:12<00:02, 32.39it/s]
Loading 0:  80%|████████  | 292/363 [00:12<00:01, 37.82it/s]
Loading 0:  82%|████████▏ | 297/363 [00:13<00:01, 39.22it/s]
Loading 0:  83%|████████▎ | 302/363 [00:13<00:01, 41.17it/s]
Loading 0:  85%|████████▍ | 308/363 [00:13<00:01, 42.45it/s]
Loading 0:  86%|████████▌ | 313/363 [00:13<00:01, 43.06it/s]
Loading 0:  88%|████████▊ | 320/363 [00:13<00:00, 47.67it/s]
Loading 0:  90%|████████▉ | 326/363 [00:13<00:00, 45.73it/s]
Loading 0:  91%|█████████ | 331/363 [00:13<00:00, 45.84it/s]
Loading 0:  93%|█████████▎| 338/363 [00:13<00:00, 50.18it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:00, 46.46it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 44.18it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 48.12it/s]
Loading 0:  99%|█████████▉| 361/363 [00:14<00:00, 48.58it/s]
                                                            
Job billxbf-nemo-sft-orpo-v1-mkmlizer completed after 113.85s with status: succeeded
Stopping job with name billxbf-nemo-sft-orpo-v1-mkmlizer
Pipeline stage MKMLizer completed in 114.31s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service billxbf-nemo-sft-orpo-v1
Waiting for inference service billxbf-nemo-sft-orpo-v1 to be ready
Failed to get response for submission leosheng-ft-dpo-10074_v2: HTTPConnectionPool(host='leosheng-ft-dpo-10074-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission leosheng-ft-dpo-10074_v2: HTTPConnectionPool(host='leosheng-ft-dpo-10074-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service billxbf-nemo-sft-orpo-v1 ready after 180.89997673034668s
Pipeline stage MKMLDeployer completed in 181.39s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.039379596710205s
Received healthy response to inference request in 1.5847880840301514s
Received healthy response to inference request in 1.8313038349151611s
Received healthy response to inference request in 1.549591064453125s
Received healthy response to inference request in 1.6475181579589844s
5 requests
0 failed requests
5th percentile: 1.5566304683685304
10th percentile: 1.5636698722839355
20th percentile: 1.577748680114746
30th percentile: 1.597334098815918
40th percentile: 1.6224261283874513
50th percentile: 1.6475181579589844
60th percentile: 1.7210324287414551
70th percentile: 1.7945466995239256
80th percentile: 1.87291898727417
90th percentile: 1.9561492919921875
95th percentile: 1.9977644443511962
99th percentile: 2.0310565662384032
mean time: 1.7305161476135253
Pipeline stage StressChecker completed in 9.97s
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 0.69s
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 0.68s
Shutdown handler de-registered
billxbf-nemo-sft-orpo_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
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 4118.34s
Shutdown handler de-registered
billxbf-nemo-sft-orpo_v1 status is now inactive due to auto deactivation removed underperforming models
billxbf-nemo-sft-orpo_v1 status is now torndown due to DeploymentManager action
billxbf-nemo-sft-orpo_v1 status is now torndown due to DeploymentManager action
billxbf-nemo-sft-orpo_v1 status is now torndown due to DeploymentManager action