developer_uid: AlexCuadron
submission_id: alexcuadron-chai-v2-sft_14944_v3
model_name: alexcuadron-chai-v2-sft_14944_v3
model_group: AlexCuadron/chai-v2-sft-
status: torndown
timestamp: 2025-03-24T13:31:37+00:00
num_battles: 8486
num_wins: 3998
celo_rating: 1257.96
family_friendly_score: 0.601
family_friendly_standard_error: 0.006925301437482704
submission_type: basic
model_repo: AlexCuadron/chai-v2-sft-12k-12b
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.5995746833418725, 'latency_mean': 1.667759485244751, 'latency_p50': 1.6756128072738647, 'latency_p90': 1.8379053831100465}, {'batch_size': 3, 'throughput': 1.0731929289162874, 'latency_mean': 2.787699658870697, 'latency_p50': 2.8026410341262817, 'latency_p90': 3.082752156257629}, {'batch_size': 5, 'throughput': 1.295689693849558, 'latency_mean': 3.8417034769058227, 'latency_p50': 3.8379710912704468, 'latency_p90': 4.259364485740662}, {'batch_size': 6, 'throughput': 1.3513670429243356, 'latency_mean': 4.41493748664856, 'latency_p50': 4.45677387714386, 'latency_p90': 4.8553574800491335}, {'batch_size': 8, 'throughput': 1.4176678335541455, 'latency_mean': 5.604184935092926, 'latency_p50': 5.591136574745178, 'latency_p90': 6.284954333305359}, {'batch_size': 10, 'throughput': 1.4404322571568084, 'latency_mean': 6.8911034107208256, 'latency_p50': 6.907013416290283, 'latency_p90': 7.744973444938659}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: alexcuadron-chai-v2-sft_14944_v3
is_internal_developer: False
language_model: AlexCuadron/chai-v2-sft-12k-12b
model_size: 13B
ranking_group: single
throughput_3p7s: 1.28
us_pacific_date: 2025-03-24
win_ratio: 0.4711289182182418
generation_params: {'temperature': 1.0, 'top_p': 0.9, 'min_p': 0.1, 'top_k': 40, 'presence_penalty': 0.1, 'frequency_penalty': 0.0, 'stopping_words': ['</s>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "<s>{bot_name}'s Persona: {memory}\n", 'prompt_template': '{prompt}', 'bot_template': '{bot_name}: {message}</s>', 'user_template': '[INST]{user_name}: {message}[/INST]', '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 alexcuadron-chai-v2-sft-14944-v3-mkmlizer
Waiting for job on alexcuadron-chai-v2-sft-14944-v3-mkmlizer to finish
alexcuadron-chai-v2-sft-14944-v3-mkmlizer: Downloaded to shared memory in 39.302s
alexcuadron-chai-v2-sft-14944-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmppm7z5t22, device:0
alexcuadron-chai-v2-sft-14944-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexcuadron-chai-v2-sft-14944-v3-mkmlizer: quantized model in 37.721s
alexcuadron-chai-v2-sft-14944-v3-mkmlizer: Processed model AlexCuadron/chai-v2-sft-12k-12b in 77.024s
alexcuadron-chai-v2-sft-14944-v3-mkmlizer: creating bucket guanaco-mkml-models
alexcuadron-chai-v2-sft-14944-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexcuadron-chai-v2-sft-14944-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexcuadron-chai-v2-sft-14944-v3
alexcuadron-chai-v2-sft-14944-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexcuadron-chai-v2-sft-14944-v3/special_tokens_map.json
alexcuadron-chai-v2-sft-14944-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexcuadron-chai-v2-sft-14944-v3/config.json
alexcuadron-chai-v2-sft-14944-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexcuadron-chai-v2-sft-14944-v3/tokenizer_config.json
alexcuadron-chai-v2-sft-14944-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexcuadron-chai-v2-sft-14944-v3/tokenizer.json
alexcuadron-chai-v2-sft-14944-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexcuadron-chai-v2-sft-14944-v3/flywheel_model.0.safetensors
alexcuadron-chai-v2-sft-14944-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 28.50it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 44.81it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:08, 42.17it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:08, 41.59it/s]
Loading 0:   7%|▋         | 27/363 [00:00<00:07, 42.58it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 33.36it/s]
Loading 0:  11%|█         | 39/363 [00:00<00:07, 41.21it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:07, 40.32it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:07, 40.16it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:07, 41.34it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:07, 42.84it/s]
Loading 0:  18%|█▊        | 64/363 [00:01<00:11, 25.14it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:09, 31.93it/s]
Loading 0:  21%|██        | 76/363 [00:02<00:08, 33.64it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:07, 35.67it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:07, 37.36it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:08, 31.77it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 38.40it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:07, 37.05it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:06, 38.63it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:07, 32.19it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:07, 32.89it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:06, 39.04it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:06, 36.59it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:06, 37.79it/s]
Loading 0:  38%|███▊      | 139/363 [00:03<00:06, 35.12it/s]
Loading 0:  39%|███▉      | 143/363 [00:04<00:08, 26.34it/s]
Loading 0:  40%|████      | 147/363 [00:04<00:07, 27.63it/s]
Loading 0:  42%|████▏     | 151/363 [00:04<00:07, 28.45it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:06, 31.92it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:06, 31.82it/s]
Loading 0:  45%|████▌     | 165/363 [00:04<00:05, 35.11it/s]
Loading 0:  47%|████▋     | 169/363 [00:04<00:05, 33.85it/s]
Loading 0:  48%|████▊     | 174/363 [00:04<00:05, 37.16it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 35.60it/s]
Loading 0:  50%|█████     | 183/363 [00:05<00:04, 38.84it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:04, 37.20it/s]
Loading 0:  53%|█████▎    | 192/363 [00:05<00:04, 39.27it/s]
Loading 0:  54%|█████▍    | 196/363 [00:05<00:04, 37.11it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:04, 40.28it/s]
Loading 0:  57%|█████▋    | 206/363 [00:05<00:03, 40.02it/s]
Loading 0:  58%|█████▊    | 211/363 [00:05<00:03, 40.45it/s]
Loading 0:  60%|█████▉    | 216/363 [00:05<00:03, 40.63it/s]
Loading 0:  61%|██████    | 221/363 [00:06<00:03, 42.46it/s]
Loading 0:  62%|██████▏   | 226/363 [00:06<00:05, 26.17it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:05, 26.24it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 33.25it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 32.89it/s]
Loading 0:  68%|██████▊   | 246/363 [00:06<00:03, 34.99it/s]
Loading 0:  69%|██████▉   | 250/363 [00:07<00:03, 32.92it/s]
Loading 0:  70%|███████   | 255/363 [00:07<00:03, 35.49it/s]
Loading 0:  71%|███████▏  | 259/363 [00:07<00:03, 34.63it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 37.60it/s]
Loading 0:  74%|███████▍  | 268/363 [00:07<00:02, 35.82it/s]
Loading 0:  75%|███████▌  | 273/363 [00:07<00:02, 38.69it/s]
Loading 0:  76%|███████▋  | 277/363 [00:07<00:02, 36.85it/s]
Loading 0:  78%|███████▊  | 282/363 [00:07<00:02, 38.97it/s]
Loading 0:  79%|███████▉  | 286/363 [00:08<00:02, 36.65it/s]
Loading 0:  80%|████████  | 291/363 [00:08<00:01, 38.95it/s]
Loading 0:  81%|████████▏ | 295/363 [00:08<00:01, 37.13it/s]
Loading 0:  82%|████████▏ | 299/363 [00:08<00:01, 36.78it/s]
Loading 0:  84%|████████▎ | 304/363 [00:15<00:27,  2.12it/s]
Loading 0:  85%|████████▍ | 307/363 [00:15<00:21,  2.66it/s]
Loading 0:  86%|████████▌ | 312/363 [00:15<00:13,  3.91it/s]
Loading 0:  88%|████████▊ | 320/363 [00:15<00:06,  6.69it/s]
Loading 0:  90%|████████▉ | 325/363 [00:15<00:04,  8.84it/s]
Loading 0:  91%|█████████ | 330/363 [00:15<00:03, 10.88it/s]
Loading 0:  93%|█████████▎| 337/363 [00:16<00:01, 15.73it/s]
Loading 0:  94%|█████████▍| 342/363 [00:16<00:01, 18.84it/s]
Loading 0:  96%|█████████▌| 347/363 [00:16<00:00, 22.45it/s]
Loading 0:  97%|█████████▋| 352/363 [00:16<00:00, 26.29it/s]
Loading 0:  98%|█████████▊| 357/363 [00:16<00:00, 25.77it/s]
                                                            

Job alexcuadron-chai-v2-sft-14944-v3-mkmlizer completed after 104.3s with status: succeeded
Stopping job with name alexcuadron-chai-v2-sft-14944-v3-mkmlizer
Pipeline stage MKMLizer completed in 104.76s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.43s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service alexcuadron-chai-v2-sft-14944-v3
Waiting for inference service alexcuadron-chai-v2-sft-14944-v3 to be ready
Inference service alexcuadron-chai-v2-sft-14944-v3 ready after 90.30114436149597s
Pipeline stage MKMLDeployer completed in 90.75s
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 2.209887981414795s
Received healthy response to inference request in 1.5771687030792236s
Received healthy response to inference request in 1.5968077182769775s
Received healthy response to inference request in 1.6314308643341064s
5 requests
1 failed requests
5th percentile: 1.5810965061187745
10th percentile: 1.5850243091583252
20th percentile: 1.5928799152374267
30th percentile: 1.6037323474884033
40th percentile: 1.6175816059112549
50th percentile: 1.6314308643341064
60th percentile: 1.8628137111663818
70th percentile: 2.0941965579986572
80th percentile: 5.793488025665287
90th percentile: 12.960688114166262
95th percentile: 16.544288158416744
99th percentile: 19.411168193817137
mean time: 5.428636693954468
%s, retrying in %s seconds...
Received healthy response to inference request in 1.567389965057373s
Received healthy response to inference request in 1.5492823123931885s
Received healthy response to inference request in 1.5610551834106445s
Received healthy response to inference request in 1.590620756149292s
Received healthy response to inference request in 1.7003769874572754s
5 requests
0 failed requests
5th percentile: 1.5516368865966796
10th percentile: 1.5539914608001708
20th percentile: 1.5587006092071534
30th percentile: 1.5623221397399902
40th percentile: 1.5648560523986816
50th percentile: 1.567389965057373
60th percentile: 1.5766822814941406
70th percentile: 1.5859745979309081
80th percentile: 1.6125720024108887
90th percentile: 1.656474494934082
95th percentile: 1.6784257411956787
99th percentile: 1.695986738204956
mean time: 1.5937450408935547
Pipeline stage StressChecker completed in 37.68s
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 0.71s
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 0.65s
Shutdown handler de-registered
alexcuadron-chai-v2-sft_14944_v3 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service alexcuadron-chai-v2-sft-14944-v3-profiler
Waiting for inference service alexcuadron-chai-v2-sft-14944-v3-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 4653.16s
Shutdown handler de-registered
alexcuadron-chai-v2-sft_14944_v3 status is now inactive due to auto deactivation removed underperforming models
alexcuadron-chai-v2-sft_14944_v3 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1