chaiml-gy-exp13-sftdpo-_37649

developer_uid: bogoconic1

submission_id: chaiml-gy-exp13-sftdpo-_37649_v1

model_name: chaiml-gy-exp13-sftdpo-_37649_v1

model_group: ChaiML/gy-exp13-sftdpo-g

status: torndown

timestamp: 2025-06-26T16:25:05+00:00

num_battles: 9774

num_wins: 4911

celo_rating: 1289.88

family_friendly_score: 0.5576

family_friendly_standard_error: 0.007023990888376778

submission_type: basic

model_repo: ChaiML/gy-exp13-sftdpo-gy-1266-1301-7850x4-grok-ranked-pref-ep1

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.5932022835289025, 'latency_mean': 1.685644418001175, 'latency_p50': 1.6852638721466064, 'latency_p90': 1.8788973569869996}, {'batch_size': 3, 'throughput': 1.0599202803894965, 'latency_mean': 2.819305064678192, 'latency_p50': 2.8386945724487305, 'latency_p90': 3.0857674360275267}, {'batch_size': 5, 'throughput': 1.2724858348407828, 'latency_mean': 3.9071211934089662, 'latency_p50': 3.9028546810150146, 'latency_p90': 4.408154392242432}, {'batch_size': 6, 'throughput': 1.3278852573490019, 'latency_mean': 4.489158251285553, 'latency_p50': 4.5130040645599365, 'latency_p90': 4.9800780534744264}, {'batch_size': 8, 'throughput': 1.3952887799750986, 'latency_mean': 5.689143491983414, 'latency_p50': 5.690234422683716, 'latency_p90': 6.4908140897750854}, {'batch_size': 10, 'throughput': 1.4193499002618568, 'latency_mean': 6.980526214838028, 'latency_p50': 6.964164733886719, 'latency_p90': 7.817858290672302}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-gy-exp13-sftdpo-_37649_v1

is_internal_developer: True

language_model: ChaiML/gy-exp13-sftdpo-gy-1266-1301-7850x4-grok-ranked-pref-ep1

model_size: 13B

ranking_group: single

throughput_3p7s: 1.25

us_pacific_date: 2025-06-26

win_ratio: 0.5024554941682013

generation_params: {'temperature': 0.8, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['<|im_start|>', '<|im_end|>', '\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|system|>Family Friendly{memory}\n', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\nYou:{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', '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-gy-exp13-sftdpo-37649-v1-mkmlizer
Waiting for job on chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer to finish
Retrying (%r) after connection broken by '%r': %s
chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer: Downloaded to shared memory in 53.527s
chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer: Checking if ChaiML/gy-exp13-sftdpo-gy-1266-1301-7850x4-grok-ranked-pref-ep1 already exists in ChaiML
chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpmilg6xcv, device:0
chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Unable to obtain autoscaler chaiml-anthropic-40k-24_11629_v1 due to error: Failed to establish a connection: HTTPSConnectionPool(host='guanaco-autoscalers.firebaseio.com', port=443): Max retries exceeded with url: /autoscalers/chaiml-anthropic-40k-24_11629_v1/actions.json (Caused by ProtocolError('Connection aborted.', RemoteDisconnected('Remote end closed connection without response'))). Falling back to minimal defaults: logs=None autoscaler_id='fallback' status='deployed' metric=<function null_metric at 0x782f7370a660> observations=[] max_observations_length=1000 target=0.0 actions=[SubmissionAutoscalerParameterAction(generation_parameter='max_input_tokens', current_scale=128, min_scale=512, max_scale=2048)] scale_up_policy=AutoscalerPolicy(max_percent_change=0.25, period=0.1, stabilisation_window=0, tolerance=0.1) scale_down_policy=AutoscalerPolicy(max_percent_change=0.25, period=0.1, stabilisation_window=0, tolerance=0.1) panic_policy=AutoscalerPanicPolicy(max_percent_change=1.0, period=0.1, stabilisation_window=0, tolerance=-1e-06, z_score=3, num_observations=5, num_historical_observations=100)
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer: quantized model in 31.275s
chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer: Processed model ChaiML/gy-exp13-sftdpo-gy-1266-1301-7850x4-grok-ranked-pref-ep1 in 84.802s
chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp13-sftdpo-37649-v1
chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp13-sftdpo-37649-v1/config.json
chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp13-sftdpo-37649-v1/special_tokens_map.json
chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp13-sftdpo-37649-v1/tokenizer_config.json
chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp13-sftdpo-37649-v1/tokenizer.json
chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp13-sftdpo-37649-v1/flywheel_model.0.safetensors
chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 31.61it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 50.22it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:08, 42.47it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 41.18it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 46.72it/s]
Loading 0:  10%|▉         | 36/363 [00:00<00:07, 46.47it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:08, 36.79it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:07, 44.36it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:07, 43.76it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:06, 45.02it/s]
Loading 0:  17%|█▋        | 63/363 [00:01<00:10, 29.81it/s]
Loading 0:  18%|█▊        | 67/363 [00:01<00:09, 31.70it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:08, 34.39it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:08, 35.32it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:07, 35.82it/s]
Loading 0:  23%|██▎       | 84/363 [00:02<00:08, 34.50it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:07, 36.76it/s]
Loading 0:  26%|██▌       | 93/363 [00:02<00:07, 35.65it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:07, 37.55it/s]
Loading 0:  28%|██▊       | 102/363 [00:02<00:07, 35.94it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:07, 35.30it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:06, 39.87it/s]
Loading 0:  32%|███▏      | 117/363 [00:03<00:06, 38.12it/s]
Loading 0:  33%|███▎      | 121/363 [00:03<00:06, 37.59it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:06, 37.23it/s]
Loading 0:  36%|███▌      | 129/363 [00:03<00:06, 35.91it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:06, 37.65it/s]
Loading 0:  38%|███▊      | 138/363 [00:03<00:06, 36.23it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:08, 26.08it/s]
Loading 0:  40%|███▉      | 145/363 [00:04<00:08, 25.64it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:08, 25.39it/s]
Loading 0:  43%|████▎     | 155/363 [00:04<00:06, 32.92it/s]
Loading 0:  44%|████▍     | 159/363 [00:04<00:06, 31.60it/s]
Loading 0:  45%|████▌     | 165/363 [00:04<00:05, 37.06it/s]
Loading 0:  47%|████▋     | 169/363 [00:04<00:05, 36.01it/s]
Loading 0:  48%|████▊     | 174/363 [00:04<00:04, 38.09it/s]
Loading 0:  49%|████▉     | 178/363 [00:04<00:05, 36.70it/s]
Loading 0:  50%|█████     | 183/363 [00:05<00:04, 39.17it/s]
Loading 0:  52%|█████▏    | 188/363 [00:05<00:04, 38.03it/s]
Loading 0:  53%|█████▎    | 192/363 [00:05<00:04, 37.16it/s]
Loading 0:  54%|█████▍    | 196/363 [00:05<00:04, 35.52it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:04, 37.38it/s]
Loading 0:  56%|█████▋    | 205/363 [00:05<00:04, 35.87it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:04, 38.09it/s]
Loading 0:  59%|█████▉    | 214/363 [00:05<00:04, 37.14it/s]
Loading 0:  60%|██████    | 218/363 [00:05<00:03, 36.68it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:04, 28.25it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:04, 29.85it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:04, 29.19it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 34.58it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 34.45it/s]
Loading 0:  68%|██████▊   | 246/363 [00:06<00:03, 37.17it/s]
Loading 0:  69%|██████▉   | 250/363 [00:06<00:03, 36.65it/s]
Loading 0:  70%|███████   | 255/363 [00:07<00:02, 38.88it/s]
Loading 0:  71%|███████▏  | 259/363 [00:07<00:02, 37.46it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 39.40it/s]
Loading 0:  74%|███████▍  | 268/363 [00:07<00:02, 37.77it/s]
Loading 0:  75%|███████▌  | 273/363 [00:07<00:02, 38.97it/s]
Loading 0:  76%|███████▋  | 277/363 [00:07<00:02, 37.80it/s]
Loading 0:  78%|███████▊  | 282/363 [00:07<00:02, 39.98it/s]
Loading 0:  79%|███████▉  | 287/363 [00:07<00:01, 39.87it/s]
Loading 0:  80%|████████  | 292/363 [00:08<00:01, 40.62it/s]
Loading 0:  82%|████████▏ | 297/363 [00:08<00:01, 42.22it/s]
Loading 0:  83%|████████▎ | 302/363 [00:08<00:01, 43.17it/s]
Loading 0:  85%|████████▍ | 307/363 [00:08<00:02, 20.17it/s]
Loading 0:  86%|████████▌ | 312/363 [00:08<00:02, 22.70it/s]
Loading 0:  88%|████████▊ | 319/363 [00:09<00:01, 30.38it/s]
Loading 0:  89%|████████▉ | 324/363 [00:09<00:01, 32.84it/s]
Loading 0:  91%|█████████ | 329/363 [00:09<00:00, 35.47it/s]
Loading 0:  92%|█████████▏| 334/363 [00:09<00:00, 38.19it/s]
Loading 0:  93%|█████████▎| 339/363 [00:09<00:00, 33.42it/s]
Loading 0:  95%|█████████▌| 346/363 [00:09<00:00, 40.30it/s]
Loading 0:  97%|█████████▋| 351/363 [00:09<00:00, 40.61it/s]
Loading 0:  98%|█████████▊| 356/363 [00:09<00:00, 41.86it/s]
Loading 0:  99%|█████████▉| 361/363 [00:10<00:00, 43.27it/s]
                                                            
Job chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer completed after 114.95s with status: succeeded
Stopping job with name chaiml-gy-exp13-sftdpo-37649-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.67s
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-gy-exp13-sftdpo-37649-v1
Waiting for inference service chaiml-gy-exp13-sftdpo-37649-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-gy-exp13-sftdpo-37649-v1 ready after 150.50540709495544s
Pipeline stage MKMLDeployer completed in 151.03s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2601938247680664s
Received healthy response to inference request in 1.5833072662353516s
Received healthy response to inference request in 1.9505679607391357s
Received healthy response to inference request in 1.5077221393585205s
Received healthy response to inference request in 1.694561243057251s
5 requests
0 failed requests
5th percentile: 1.5228391647338868
10th percentile: 1.5379561901092529
20th percentile: 1.5681902408599853
30th percentile: 1.6055580615997314
40th percentile: 1.6500596523284912
50th percentile: 1.694561243057251
60th percentile: 1.7969639301300049
70th percentile: 1.8993666172027588
80th percentile: 2.012493133544922
90th percentile: 2.136343479156494
95th percentile: 2.1982686519622803
99th percentile: 2.2478087902069093
mean time: 1.7992704868316651
Pipeline stage StressChecker completed in 10.41s
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 0.74s
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-gy-exp13-sftdpo-_37649_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4944.09s
Shutdown handler de-registered
chaiml-gy-exp13-sftdpo-_37649_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp13-sftdpo-_37649_v1 status is now torndown due to DeploymentManager action