albertwang8192-2025-07-08-7

developer_uid: RandomForest1024

submission_id: albertwang8192-2025-07-08-7_v1

model_name: 2025-07-08_7

model_group: AlbertWang8192/2025-07-0

status: torndown

timestamp: 2025-07-08T20:05:24+00:00

num_battles: 9342

num_wins: 4227

celo_rating: 1256.61

family_friendly_score: 0.5446

family_friendly_standard_error: 0.0070428806606387985

submission_type: basic

model_repo: AlbertWang8192/2025-07-08_7

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.5934241495148539, 'latency_mean': 1.6850314795970918, 'latency_p50': 1.6897425651550293, 'latency_p90': 1.8516317129135131}, {'batch_size': 3, 'throughput': 1.0669085061531478, 'latency_mean': 2.809103605747223, 'latency_p50': 2.792128324508667, 'latency_p90': 3.0634744644165037}, {'batch_size': 5, 'throughput': 1.2814695485127359, 'latency_mean': 3.8883872723579405, 'latency_p50': 3.9191861152648926, 'latency_p90': 4.36957197189331}, {'batch_size': 6, 'throughput': 1.3501016117634987, 'latency_mean': 4.4176172769069675, 'latency_p50': 4.4105823040008545, 'latency_p90': 4.962274360656738}, {'batch_size': 8, 'throughput': 1.3963199665000712, 'latency_mean': 5.683609561920166, 'latency_p50': 5.6954275369644165, 'latency_p90': 6.341883635520935}, {'batch_size': 10, 'throughput': 1.4415045624136091, 'latency_mean': 6.882598377466202, 'latency_p50': 6.899142146110535, 'latency_p90': 7.7638102054595945}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: 2025-07-08_7

is_internal_developer: False

language_model: AlbertWang8192/2025-07-08_7

model_size: 13B

ranking_group: single

throughput_3p7s: 1.26

us_pacific_date: 2025-07-08

win_ratio: 0.4524727039177906

generation_params: {'temperature': 0.6, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['<|im_end|>', '\n', '<|im_start|>'], '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 albertwang8192-2025-07-08-7-v1-mkmlizer
Waiting for job on albertwang8192-2025-07-08-7-v1-mkmlizer to finish
Failed to get response for submission rirv938-prefgrok-r2-cp3_99593_v1: HTTPConnectionPool(host='rirv938-prefgrok-r2-cp3-99593-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
albertwang8192-2025-07-08-7-v1-mkmlizer: Downloaded to shared memory in 74.471s
albertwang8192-2025-07-08-7-v1-mkmlizer: Checking if AlbertWang8192/2025-07-08_7 already exists in ChaiML
albertwang8192-2025-07-08-7-v1-mkmlizer: Creating repo ChaiML/2025-07-08_7 and uploading /tmp/tmp2174jczi to it
albertwang8192-2025-07-08-7-v1-mkmlizer: 
  0%|          | 0/6 [00:00<?, ?it/s]
 17%|█▋        | 1/6 [00:08<00:41,  8.23s/it]
 33%|███▎      | 2/6 [00:28<01:00, 15.20s/it]
 50%|█████     | 3/6 [00:33<00:31, 10.47s/it]
 67%|██████▋   | 4/6 [00:37<00:16,  8.09s/it]
 83%|████████▎ | 5/6 [00:41<00:06,  6.76s/it]
100%|██████████| 6/6 [00:43<00:00,  4.99s/it]
100%|██████████| 6/6 [00:43<00:00,  7.26s/it]
albertwang8192-2025-07-08-7-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp2174jczi, device:0
albertwang8192-2025-07-08-7-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
albertwang8192-2025-07-08-7-v1-mkmlizer: quantized model in 31.491s
albertwang8192-2025-07-08-7-v1-mkmlizer: Processed model AlbertWang8192/2025-07-08_7 in 175.342s
albertwang8192-2025-07-08-7-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
albertwang8192-2025-07-08-7-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/albertwang8192-2025-07-08-7-v1/nvidia
albertwang8192-2025-07-08-7-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/albertwang8192-2025-07-08-7-v1/nvidia/special_tokens_map.json
albertwang8192-2025-07-08-7-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/albertwang8192-2025-07-08-7-v1/nvidia/config.json
albertwang8192-2025-07-08-7-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/albertwang8192-2025-07-08-7-v1/nvidia/tokenizer_config.json
albertwang8192-2025-07-08-7-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/albertwang8192-2025-07-08-7-v1/nvidia/tokenizer.json
albertwang8192-2025-07-08-7-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/albertwang8192-2025-07-08-7-v1/nvidia/flywheel_model.0.safetensors
albertwang8192-2025-07-08-7-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 26.91it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:09, 36.34it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:11, 31.28it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:09, 36.40it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 32.12it/s]
Loading 0:   8%|▊         | 28/363 [00:00<00:09, 36.76it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:10, 32.92it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:08, 37.00it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:09, 33.02it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:08, 37.22it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:09, 34.13it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:06, 45.24it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 32.44it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 39.07it/s]
Loading 0:  21%|██▏       | 78/363 [00:02<00:07, 39.09it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:07, 39.68it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:05, 45.56it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:06, 44.25it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 41.44it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:06, 40.90it/s]
Loading 0:  31%|███       | 111/363 [00:02<00:05, 42.29it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:06, 36.18it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 33.61it/s]
Loading 0:  34%|███▍      | 124/363 [00:03<00:06, 34.67it/s]
Loading 0:  35%|███▌      | 128/363 [00:03<00:07, 31.37it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:07, 31.87it/s]
Loading 0:  37%|███▋      | 136/363 [00:03<00:07, 28.51it/s]
Loading 0:  39%|███▉      | 141/363 [00:03<00:06, 32.55it/s]
Loading 0:  40%|███▉      | 145/363 [00:04<00:10, 21.58it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:09, 21.97it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:07, 26.17it/s]
Loading 0:  44%|████▎     | 158/363 [00:04<00:08, 25.44it/s]
Loading 0:  45%|████▍     | 163/363 [00:04<00:06, 29.42it/s]
Loading 0:  46%|████▌     | 167/363 [00:04<00:07, 27.80it/s]
Loading 0:  47%|████▋     | 172/363 [00:05<00:05, 31.86it/s]
Loading 0:  48%|████▊     | 176/363 [00:05<00:06, 30.00it/s]
Loading 0:  50%|█████     | 183/363 [00:05<00:04, 37.98it/s]
Loading 0:  52%|█████▏    | 188/363 [00:05<00:04, 39.15it/s]
Loading 0:  53%|█████▎    | 193/363 [00:05<00:04, 40.93it/s]
Loading 0:  55%|█████▍    | 199/363 [00:05<00:04, 40.08it/s]
Loading 0:  56%|█████▌    | 204/363 [00:05<00:04, 38.87it/s]
Loading 0:  58%|█████▊    | 211/363 [00:06<00:03, 44.40it/s]
Loading 0:  60%|█████▉    | 216/363 [00:06<00:03, 45.65it/s]
Loading 0:  61%|██████    | 222/363 [00:06<00:03, 44.83it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:04, 32.03it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:04, 32.47it/s]
Loading 0:  66%|██████▌   | 238/363 [00:06<00:03, 38.93it/s]
Loading 0:  67%|██████▋   | 244/363 [00:06<00:03, 39.64it/s]
Loading 0:  69%|██████▊   | 249/363 [00:07<00:02, 38.92it/s]
Loading 0:  70%|███████   | 255/363 [00:07<00:02, 43.58it/s]
Loading 0:  72%|███████▏  | 260/363 [00:07<00:02, 43.60it/s]
Loading 0:  73%|███████▎  | 265/363 [00:07<00:02, 43.64it/s]
Loading 0:  74%|███████▍  | 270/363 [00:07<00:02, 44.98it/s]
Loading 0:  76%|███████▌  | 275/363 [00:07<00:02, 36.83it/s]
Loading 0:  78%|███████▊  | 283/363 [00:07<00:01, 44.85it/s]
Loading 0:  80%|███████▉  | 289/363 [00:07<00:01, 42.55it/s]
Loading 0:  81%|████████  | 294/363 [00:08<00:01, 41.66it/s]
Loading 0:  82%|████████▏ | 299/363 [00:08<00:01, 41.21it/s]
Loading 0:  84%|████████▎ | 304/363 [00:08<00:02, 21.17it/s]
Loading 0:  85%|████████▍ | 308/363 [00:08<00:02, 22.41it/s]
Loading 0:  86%|████████▌ | 312/363 [00:09<00:02, 22.14it/s]
Loading 0:  87%|████████▋ | 317/363 [00:09<00:01, 26.63it/s]
Loading 0:  88%|████████▊ | 321/363 [00:09<00:01, 26.30it/s]
Loading 0:  90%|████████▉ | 326/363 [00:09<00:01, 30.58it/s]
Loading 0:  91%|█████████ | 330/363 [00:09<00:01, 28.52it/s]
Loading 0:  92%|█████████▏| 335/363 [00:09<00:00, 32.50it/s]
Loading 0:  93%|█████████▎| 339/363 [00:09<00:00, 30.15it/s]
Loading 0:  95%|█████████▍| 344/363 [00:09<00:00, 33.88it/s]
Loading 0:  96%|█████████▌| 348/363 [00:10<00:00, 30.56it/s]
Loading 0:  97%|█████████▋| 353/363 [00:10<00:00, 34.21it/s]
Loading 0:  98%|█████████▊| 357/363 [00:10<00:00, 31.10it/s]
Loading 0: 100%|█████████▉| 362/363 [00:10<00:00, 34.55it/s]
                                                            
Job albertwang8192-2025-07-08-7-v1-mkmlizer completed after 209.24s with status: succeeded
Stopping job with name albertwang8192-2025-07-08-7-v1-mkmlizer
Pipeline stage MKMLizer completed in 209.86s
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 albertwang8192-2025-07-08-7-v1
Waiting for inference service albertwang8192-2025-07-08-7-v1 to be ready
Inference service albertwang8192-2025-07-08-7-v1 ready after 200.74551510810852s
Pipeline stage MKMLDeployer completed in 201.53s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.268083333969116s
Received healthy response to inference request in 1.5865814685821533s
Received healthy response to inference request in 1.8284227848052979s
Received healthy response to inference request in 1.5506997108459473s
Received healthy response to inference request in 1.5947785377502441s
5 requests
0 failed requests
5th percentile: 1.5578760623931884
10th percentile: 1.5650524139404296
20th percentile: 1.5794051170349122
30th percentile: 1.5882208824157715
40th percentile: 1.5914997100830077
50th percentile: 1.5947785377502441
60th percentile: 1.6882362365722656
70th percentile: 1.781693935394287
80th percentile: 1.9163548946380615
90th percentile: 2.092219114303589
95th percentile: 2.1801512241363525
99th percentile: 2.2504969120025633
mean time: 1.7657131671905517
Pipeline stage StressChecker completed in 10.27s
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 0.77s
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
Failed to get response for submission chaiml-exp-grpo-cp312-9_36146_v4: ('http://chaiml-20250611-retune-u-1558-v3-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:45798->127.0.0.1:8080: read: connection reset by peer\n')
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.83s
Shutdown handler de-registered
albertwang8192-2025-07-08-7_v1 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
Pipeline stage OfflineFamilyFriendlyScorer completed in 4410.91s
Shutdown handler de-registered
albertwang8192-2025-07-08-7_v1 status is now inactive due to auto deactivation removed underperforming models
albertwang8192-2025-07-08-7_v1 status is now torndown due to DeploymentManager action