chaiml-anthropic-grpo-4_68396

developer_uid: rirv938

submission_id: chaiml-anthropic-grpo-4_68396_v1

model_name: chaiml-anthropic-grpo-4_68396_v1

model_group: ChaiML/anthropic_grpo_40

status: torndown

timestamp: 2025-05-15T23:21:00+00:00

num_battles: 7051

num_wins: 3529

celo_rating: 1285.26

family_friendly_score: 0.5676

family_friendly_standard_error: 0.007006143589736082

submission_type: basic

model_repo: ChaiML/anthropic_grpo_40k_cp624_95ff_beta6_merged

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': 0.6439342702743818, 'latency_mean': 1.5528560590744018, 'latency_p50': 1.5568115711212158, 'latency_p90': 1.7182965755462647}, {'batch_size': 3, 'throughput': 1.2338515878169658, 'latency_mean': 2.4278809773921965, 'latency_p50': 2.4288811683654785, 'latency_p90': 2.667365217208862}, {'batch_size': 5, 'throughput': 1.5111687497777568, 'latency_mean': 3.293096618652344, 'latency_p50': 3.2898370027542114, 'latency_p90': 3.659561109542847}, {'batch_size': 6, 'throughput': 1.604826856046845, 'latency_mean': 3.709161639213562, 'latency_p50': 3.7118090391159058, 'latency_p90': 4.179118371009826}, {'batch_size': 8, 'throughput': 1.7006763566755303, 'latency_mean': 4.675940828323364, 'latency_p50': 4.703101634979248, 'latency_p90': 5.208052039146423}, {'batch_size': 10, 'throughput': 1.7378997467820374, 'latency_mean': 5.7030491805076595, 'latency_p50': 5.704348564147949, 'latency_p90': 6.56661376953125}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-anthropic-grpo-4_68396_v1

is_internal_developer: True

language_model: ChaiML/anthropic_grpo_40k_cp624_95ff_beta6_merged

model_size: 13B

ranking_group: single

throughput_3p7s: 1.62

us_pacific_date: 2025-05-15

win_ratio: 0.5004963834917033

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-4-68396-v1-mkmlizer
Waiting for job on chaiml-anthropic-grpo-4-68396-v1-mkmlizer to finish
chaiml-anthropic-grpo-4-68396-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-anthropic-grpo-4-68396-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-anthropic-grpo-4-68396-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-anthropic-grpo-4-68396-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-anthropic-grpo-4-68396-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-anthropic-grpo-4-68396-v1-mkmlizer: ║       /___/                                                         ║
chaiml-anthropic-grpo-4-68396-v1-mkmlizer: ║                                                                     ║
chaiml-anthropic-grpo-4-68396-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-anthropic-grpo-4-68396-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-anthropic-grpo-4-68396-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-anthropic-grpo-4-68396-v1-mkmlizer: ║                                                                     ║
chaiml-anthropic-grpo-4-68396-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-anthropic-grpo-4-68396-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-anthropic-grpo-4-68396-v1-mkmlizer: ║                                                                     ║
chaiml-anthropic-grpo-4-68396-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-anthropic-grpo-4-68396-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-anthropic-grpo-4-68396-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-anthropic-grpo-4-68396-v1-mkmlizer: ║                                                                     ║
chaiml-anthropic-grpo-4-68396-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-anthropic-grpo-4-68396-v1-mkmlizer: Downloaded to shared memory in 61.273s
chaiml-anthropic-grpo-4-68396-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp754q8c07, device:0
chaiml-anthropic-grpo-4-68396-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-anthropic-grpo-4-68396-v1-mkmlizer: quantized model in 41.235s
chaiml-anthropic-grpo-4-68396-v1-mkmlizer: Processed model ChaiML/anthropic_grpo_40k_cp624_95ff_beta6_merged in 102.508s
chaiml-anthropic-grpo-4-68396-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-anthropic-grpo-4-68396-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-anthropic-grpo-4-68396-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-anthropic-grpo-4-68396-v1
chaiml-anthropic-grpo-4-68396-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-anthropic-grpo-4-68396-v1/special_tokens_map.json
chaiml-anthropic-grpo-4-68396-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-anthropic-grpo-4-68396-v1/config.json
chaiml-anthropic-grpo-4-68396-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-anthropic-grpo-4-68396-v1/tokenizer_config.json
chaiml-anthropic-grpo-4-68396-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-anthropic-grpo-4-68396-v1/tokenizer.json
chaiml-anthropic-grpo-4-68396-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-anthropic-grpo-4-68396-v1/flywheel_model.0.safetensors
chaiml-anthropic-grpo-4-68396-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.13it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:13, 26.58it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:14, 23.82it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:11, 29.89it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:15, 22.25it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:16, 20.02it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:12, 25.72it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:12, 27.02it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 28.13it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 27.18it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 29.58it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 27.64it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:11, 27.69it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:12, 23.49it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:14, 21.07it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:10, 27.85it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:10, 27.64it/s]
Loading 0:  21%|██▏       | 78/363 [00:03<00:11, 25.58it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:09, 28.46it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 25.64it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 32.00it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 30.39it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:10, 23.86it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:12, 21.47it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:08, 28.09it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 27.47it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 29.97it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 29.06it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 31.20it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 29.67it/s]
Loading 0:  38%|███▊      | 137/363 [00:05<00:07, 29.64it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 25.39it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:09, 24.15it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 23.15it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:06, 29.69it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:07, 28.74it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:06, 31.14it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 29.63it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 31.37it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 29.64it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 23.28it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:08, 20.95it/s]
Loading 0:  53%|█████▎    | 192/363 [00:07<00:06, 27.86it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 27.55it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 29.76it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 28.87it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 30.95it/s]
Loading 0:  59%|█████▉    | 214/363 [00:07<00:05, 29.54it/s]
Loading 0:  60%|██████    | 218/363 [00:08<00:04, 29.52it/s]
Loading 0:  61%|██████▏   | 223/363 [00:08<00:05, 25.52it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 24.18it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 23.09it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:04, 30.00it/s]
Loading 0:  66%|██████▋   | 241/363 [00:08<00:04, 29.11it/s]
Loading 0:  68%|██████▊   | 246/363 [00:09<00:03, 30.78it/s]
Loading 0:  69%|██████▉   | 250/363 [00:09<00:03, 29.38it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 31.38it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 29.42it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:04, 23.02it/s]
Loading 0:  73%|███████▎  | 266/363 [00:09<00:04, 20.72it/s]
Loading 0:  75%|███████▍  | 271/363 [00:10<00:03, 26.07it/s]
Loading 0:  76%|███████▌  | 275/363 [00:10<00:03, 24.01it/s]
Loading 0:  77%|███████▋  | 280/363 [00:10<00:02, 29.11it/s]
Loading 0:  78%|███████▊  | 284/363 [00:10<00:03, 25.90it/s]
Loading 0:  80%|███████▉  | 289/363 [00:10<00:02, 30.56it/s]
Loading 0:  81%|████████  | 293/363 [00:10<00:02, 26.03it/s]
Loading 0:  82%|████████▏ | 298/363 [00:10<00:02, 30.76it/s]
Loading 0:  83%|████████▎ | 303/363 [00:11<00:01, 30.61it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 21.65it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 21.28it/s]
Loading 0:  87%|████████▋ | 316/363 [00:11<00:01, 26.23it/s]
Loading 0:  88%|████████▊ | 320/363 [00:11<00:01, 24.20it/s]
Loading 0:  90%|████████▉ | 325/363 [00:12<00:01, 28.98it/s]
Loading 0:  91%|█████████ | 329/363 [00:12<00:01, 25.33it/s]
Loading 0:  92%|█████████▏| 334/363 [00:12<00:00, 29.99it/s]
Loading 0:  93%|█████████▎| 338/363 [00:12<00:00, 26.60it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:08,  2.25it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.92it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  4.11it/s]
Loading 0:  98%|█████████▊| 357/363 [00:19<00:01,  5.23it/s]
Loading 0: 100%|█████████▉| 362/363 [00:20<00:00,  7.35it/s]
                                                            
Job chaiml-anthropic-grpo-4-68396-v1-mkmlizer completed after 124.61s with status: succeeded
Stopping job with name chaiml-anthropic-grpo-4-68396-v1-mkmlizer
Pipeline stage MKMLizer completed in 125.47s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-anthropic-grpo-4-68396-v1
Waiting for inference service chaiml-anthropic-grpo-4-68396-v1 to be ready
Inference service chaiml-anthropic-grpo-4-68396-v1 ready after 130.62125492095947s
Pipeline stage MKMLDeployer completed in 131.24s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0159964561462402s
Received healthy response to inference request in 1.7724440097808838s
Received healthy response to inference request in 1.5985379219055176s
Received healthy response to inference request in 1.819173812866211s
Received healthy response to inference request in 1.6529335975646973s
5 requests
0 failed requests
5th percentile: 1.6094170570373536
10th percentile: 1.6202961921691894
20th percentile: 1.6420544624328612
30th percentile: 1.6768356800079345
40th percentile: 1.7246398448944091
50th percentile: 1.7724440097808838
60th percentile: 1.7911359310150146
70th percentile: 1.8098278522491456
80th percentile: 1.8585383415222168
90th percentile: 1.9372673988342286
95th percentile: 1.9766319274902344
99th percentile: 2.008123550415039
mean time: 1.77181715965271
Pipeline stage StressChecker completed in 10.22s
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 0.73s
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 0.70s
Shutdown handler de-registered
chaiml-anthropic-grpo-4_68396_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 3009.86s
Shutdown handler de-registered
chaiml-anthropic-grpo-4_68396_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-anthropic-grpo-4_68396_v1 status is now torndown due to DeploymentManager action