chaiml-anthropic-grpo-4_66492

developer_uid: rirv938

submission_id: chaiml-anthropic-grpo-4_66492_v1

model_name: chaiml-anthropic-grpo-4_66492_v1

model_group: ChaiML/anthropic_grpo_40

status: torndown

timestamp: 2025-05-01T18:28:58+00:00

num_battles: 7487

num_wins: 3963

celo_rating: 1327.56

family_friendly_score: 0.5569999999999999

family_friendly_standard_error: 0.007024969750824553

submission_type: basic

model_repo: ChaiML/anthropic_grpo_40k_cp1184_95ff

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 768

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.6442449110015127, 'latency_mean': 1.552118685245514, 'latency_p50': 1.5489529371261597, 'latency_p90': 1.7172093868255616}, {'batch_size': 3, 'throughput': 1.2448290085133085, 'latency_mean': 2.400710632801056, 'latency_p50': 2.3802801370620728, 'latency_p90': 2.670950436592102}, {'batch_size': 5, 'throughput': 1.5259593291824718, 'latency_mean': 3.2622670471668243, 'latency_p50': 3.256274461746216, 'latency_p90': 3.687489652633667}, {'batch_size': 6, 'throughput': 1.6165342463029673, 'latency_mean': 3.692354955673218, 'latency_p50': 3.6570043563842773, 'latency_p90': 4.1207033634185795}, {'batch_size': 8, 'throughput': 1.7042343499224628, 'latency_mean': 4.660934828519821, 'latency_p50': 4.654422283172607, 'latency_p90': 5.26537344455719}, {'batch_size': 10, 'throughput': 1.7659488123659262, 'latency_mean': 5.599117329120636, 'latency_p50': 5.592153310775757, 'latency_p90': 6.398187685012817}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-anthropic-grpo-4_66492_v1

is_internal_developer: True

language_model: ChaiML/anthropic_grpo_40k_cp1184_95ff

model_size: 13B

ranking_group: single

throughput_3p7s: 1.63

us_pacific_date: 2025-05-01

win_ratio: 0.5293174836383064

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', 'You:', '</s>', '###'], 'max_input_tokens': 768, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', '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 chaiml-anthropic-grpo-4-66492-v1-mkmlizer
Waiting for job on chaiml-anthropic-grpo-4-66492-v1-mkmlizer to finish
chaiml-anthropic-grpo-4-66492-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-anthropic-grpo-4-66492-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-anthropic-grpo-4-66492-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-anthropic-grpo-4-66492-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-anthropic-grpo-4-66492-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-anthropic-grpo-4-66492-v1-mkmlizer: ║       /___/                                                         ║
chaiml-anthropic-grpo-4-66492-v1-mkmlizer: ║                                                                     ║
chaiml-anthropic-grpo-4-66492-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-anthropic-grpo-4-66492-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-anthropic-grpo-4-66492-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-anthropic-grpo-4-66492-v1-mkmlizer: ║                                                                     ║
chaiml-anthropic-grpo-4-66492-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-anthropic-grpo-4-66492-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-anthropic-grpo-4-66492-v1-mkmlizer: ║                                                                     ║
chaiml-anthropic-grpo-4-66492-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-anthropic-grpo-4-66492-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-anthropic-grpo-4-66492-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-anthropic-grpo-4-66492-v1-mkmlizer: ║                                                                     ║
chaiml-anthropic-grpo-4-66492-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-anthropic-grpo-4-66492-v1-mkmlizer: Downloaded to shared memory in 68.148s
chaiml-anthropic-grpo-4-66492-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp18vvsbmz, device:0
chaiml-anthropic-grpo-4-66492-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-anthropic-grpo-4-66492-v1-mkmlizer: quantized model in 41.177s
chaiml-anthropic-grpo-4-66492-v1-mkmlizer: Processed model ChaiML/anthropic_grpo_40k_cp1184_95ff in 109.326s
chaiml-anthropic-grpo-4-66492-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-anthropic-grpo-4-66492-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-anthropic-grpo-4-66492-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-anthropic-grpo-4-66492-v1
chaiml-anthropic-grpo-4-66492-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-anthropic-grpo-4-66492-v1/config.json
chaiml-anthropic-grpo-4-66492-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-anthropic-grpo-4-66492-v1/special_tokens_map.json
chaiml-anthropic-grpo-4-66492-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-anthropic-grpo-4-66492-v1/tokenizer_config.json
chaiml-anthropic-grpo-4-66492-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-anthropic-grpo-4-66492-v1/tokenizer.json
chaiml-anthropic-grpo-4-66492-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-anthropic-grpo-4-66492-v1/flywheel_model.0.safetensors
chaiml-anthropic-grpo-4-66492-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 22.67it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 28.45it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:13, 25.49it/s]
Loading 0:   6%|▌         | 20/363 [00:00<00:09, 34.68it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:14, 23.55it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:14, 23.53it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 22.70it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:10, 29.59it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 28.96it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 31.04it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 29.44it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:10, 29.76it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 25.66it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:13, 22.63it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:10, 27.88it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:10, 27.50it/s]
Loading 0:  21%|██        | 77/363 [00:02<00:11, 25.29it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:08, 31.64it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 29.66it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 31.20it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 29.82it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:11, 23.74it/s]
Loading 0:  29%|██▊       | 104/363 [00:03<00:12, 21.33it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:08, 28.39it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:08, 28.15it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 30.55it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 29.21it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 30.71it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 29.23it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:07, 29.71it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 25.60it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:09, 24.12it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 23.20it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:06, 29.79it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:07, 28.57it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 30.62it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 29.51it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 31.97it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 30.57it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 23.78it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:08, 21.57it/s]
Loading 0:  53%|█████▎    | 192/363 [00:06<00:05, 28.53it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:05, 28.07it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 30.77it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 29.86it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 32.18it/s]
Loading 0:  59%|█████▉    | 214/363 [00:07<00:04, 30.06it/s]
Loading 0:  60%|██████    | 218/363 [00:07<00:04, 29.07it/s]
Loading 0:  61%|██████    | 222/363 [00:07<00:04, 30.82it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:06, 21.79it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:06, 21.63it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:04, 28.10it/s]
Loading 0:  66%|██████▋   | 241/363 [00:08<00:04, 27.58it/s]
Loading 0:  68%|██████▊   | 246/363 [00:08<00:03, 30.00it/s]
Loading 0:  69%|██████▉   | 250/363 [00:09<00:03, 28.73it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 30.45it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 29.19it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:04, 23.70it/s]
Loading 0:  73%|███████▎  | 266/363 [00:09<00:04, 21.38it/s]
Loading 0:  75%|███████▌  | 273/363 [00:09<00:03, 27.93it/s]
Loading 0:  76%|███████▋  | 277/363 [00:10<00:03, 27.56it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 29.91it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 28.53it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 30.87it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 29.53it/s]
Loading 0:  82%|████████▏ | 299/363 [00:10<00:02, 29.60it/s]
Loading 0:  84%|████████▎ | 304/363 [00:11<00:02, 25.62it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 24.39it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 23.17it/s]
Loading 0:  87%|████████▋ | 316/363 [00:11<00:01, 28.32it/s]
Loading 0:  88%|████████▊ | 320/363 [00:11<00:01, 25.55it/s]
Loading 0:  90%|████████▉ | 325/363 [00:11<00:01, 30.30it/s]
Loading 0:  91%|█████████ | 329/363 [00:11<00:01, 26.52it/s]
Loading 0:  92%|█████████▏| 334/363 [00:12<00:00, 31.30it/s]
Loading 0:  93%|█████████▎| 338/363 [00:12<00:00, 27.42it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:08,  2.21it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.88it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  4.05it/s]
Loading 0:  98%|█████████▊| 357/363 [00:19<00:01,  5.16it/s]
Loading 0: 100%|█████████▉| 362/363 [00:19<00:00,  7.26it/s]
                                                            
Job chaiml-anthropic-grpo-4-66492-v1-mkmlizer completed after 135.46s with status: succeeded
Stopping job with name chaiml-anthropic-grpo-4-66492-v1-mkmlizer
Pipeline stage MKMLizer completed in 135.99s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-anthropic-grpo-4-66492-v1
Waiting for inference service chaiml-anthropic-grpo-4-66492-v1 to be ready
Failed to get response for submission blend_kinam_2025-04-14: HTTPConnectionPool(host='rirv938-0sw-96p-4ff-cha-93234-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 0x7b38d86be190>, 'Connection to rirv938-0sw-96p-4ff-cha-93234-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com timed out. (connect timeout=12.0)'))
Inference service chaiml-anthropic-grpo-4-66492-v1 ready after 150.94987440109253s
Pipeline stage MKMLDeployer completed in 151.44s
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 2.281445264816284s
Received healthy response to inference request in 1.8158564567565918s
Received healthy response to inference request in 1.50636887550354s
Received healthy response to inference request in 1.832730770111084s
5 requests
1 failed requests
5th percentile: 1.5682663917541504
10th percentile: 1.6301639080047607
20th percentile: 1.7539589405059814
30th percentile: 1.8192313194274903
40th percentile: 1.825981044769287
50th percentile: 1.832730770111084
60th percentile: 2.012216567993164
70th percentile: 2.191702365875244
80th percentile: 5.8534262180328405
90th percentile: 12.997388124465944
95th percentile: 16.56936907768249
99th percentile: 19.426953840255738
mean time: 5.51555027961731
%s, retrying in %s seconds...
Received healthy response to inference request in 1.6401381492614746s
Received healthy response to inference request in 1.7944159507751465s
Received healthy response to inference request in 1.6857845783233643s
Received healthy response to inference request in 1.7815163135528564s
Received healthy response to inference request in 1.7804911136627197s
5 requests
0 failed requests
5th percentile: 1.6492674350738525
10th percentile: 1.6583967208862305
20th percentile: 1.6766552925109863
30th percentile: 1.7047258853912353
40th percentile: 1.7426084995269775
50th percentile: 1.7804911136627197
60th percentile: 1.7809011936187744
70th percentile: 1.781311273574829
80th percentile: 1.7840962409973145
90th percentile: 1.7892560958862305
95th percentile: 1.7918360233306885
99th percentile: 1.7938999652862548
mean time: 1.7364692211151123
Pipeline stage StressChecker completed in 38.81s
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 0.70s
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 0.61s
Shutdown handler de-registered
chaiml-anthropic-grpo-4_66492_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 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-anthropic-grpo-4-66492-v1-profiler
Waiting for inference service chaiml-anthropic-grpo-4-66492-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 4134.60s
Shutdown handler de-registered
chaiml-anthropic-grpo-4_66492_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-anthropic-grpo-4_66492_v1 status is now torndown due to DeploymentManager action