rica40325-9-15-sftdpo

developer_uid: rica40325

submission_id: rica40325-9-15-sftdpo_v9

model_name: rica40325-9-15-sftdpo_v9

model_group: rica40325/9-15-sftdpo

status: torndown

timestamp: 2025-03-10T02:39:14+00:00

num_battles: 8188

num_wins: 3842

celo_rating: 1250.3

family_friendly_score: 0.5534

family_friendly_standard_error: 0.007030625007778469

submission_type: basic

model_repo: rica40325/9-15-sftdpo

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.8543956855077735, 'latency_mean': 1.1703560900688172, 'latency_p50': 1.1664682626724243, 'latency_p90': 1.2856376409530639}, {'batch_size': 4, 'throughput': 1.8034286295950337, 'latency_mean': 2.2081349897384643, 'latency_p50': 2.2161680459976196, 'latency_p90': 2.442183780670166}, {'batch_size': 5, 'throughput': 1.9511719578538886, 'latency_mean': 2.555305845737457, 'latency_p50': 2.552116274833679, 'latency_p90': 2.8361580610275268}, {'batch_size': 8, 'throughput': 2.1442968811195056, 'latency_mean': 3.7120578038692473, 'latency_p50': 3.690522074699402, 'latency_p90': 4.131653070449829}, {'batch_size': 10, 'throughput': 2.210884165037604, 'latency_mean': 4.4889291620254514, 'latency_p50': 4.477925181388855, 'latency_p90': 5.081231665611267}, {'batch_size': 12, 'throughput': 2.236920824862101, 'latency_mean': 5.312042914628982, 'latency_p50': 5.3188716173172, 'latency_p90': 5.992533802986145}, {'batch_size': 15, 'throughput': 2.2505431107532776, 'latency_mean': 6.578774425983429, 'latency_p50': 6.642500996589661, 'latency_p90': 7.324802327156067}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rica40325-9-15-sftdpo_v9

is_internal_developer: False

language_model: rica40325/9-15-sftdpo

model_size: 8B

ranking_group: single

throughput_3p7s: 2.15

us_pacific_date: 2025-03-09

win_ratio: 0.4692232535417684

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], '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 rica40325-9-15-sftdpo-v9-mkmlizer
Waiting for job on rica40325-9-15-sftdpo-v9-mkmlizer to finish
rica40325-9-15-sftdpo-v9-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-9-15-sftdpo-v9-mkmlizer: ║     _____            __           __                                ║
rica40325-9-15-sftdpo-v9-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rica40325-9-15-sftdpo-v9-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rica40325-9-15-sftdpo-v9-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rica40325-9-15-sftdpo-v9-mkmlizer: ║       /___/                                                         ║
rica40325-9-15-sftdpo-v9-mkmlizer: ║                                                                     ║
rica40325-9-15-sftdpo-v9-mkmlizer: ║  Version: 0.12.8                                                    ║
rica40325-9-15-sftdpo-v9-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rica40325-9-15-sftdpo-v9-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-9-15-sftdpo-v9-mkmlizer: ║                                                                     ║
rica40325-9-15-sftdpo-v9-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-9-15-sftdpo-v9-mkmlizer: ║  belonging to:                                                      ║
rica40325-9-15-sftdpo-v9-mkmlizer: ║                                                                     ║
rica40325-9-15-sftdpo-v9-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-9-15-sftdpo-v9-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-9-15-sftdpo-v9-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
rica40325-9-15-sftdpo-v9-mkmlizer: ║                                                                     ║
rica40325-9-15-sftdpo-v9-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-9-15-sftdpo-v9-mkmlizer: Downloaded to shared memory in 31.301s
rica40325-9-15-sftdpo-v9-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmppepukcbv, device:0
rica40325-9-15-sftdpo-v9-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-9-15-sftdpo-v9-mkmlizer: /opt/conda/lib/python3.10/site-packages/mk1/flywheel/functional/loader.py:55: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
rica40325-9-15-sftdpo-v9-mkmlizer:   tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
rica40325-9-15-sftdpo-v9-mkmlizer: quantized model in 26.676s
rica40325-9-15-sftdpo-v9-mkmlizer: Processed model rica40325/9-15-sftdpo in 57.978s
rica40325-9-15-sftdpo-v9-mkmlizer: creating bucket guanaco-mkml-models
rica40325-9-15-sftdpo-v9-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-9-15-sftdpo-v9-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-9-15-sftdpo-v9
rica40325-9-15-sftdpo-v9-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-9-15-sftdpo-v9/config.json
rica40325-9-15-sftdpo-v9-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-9-15-sftdpo-v9/special_tokens_map.json
rica40325-9-15-sftdpo-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-9-15-sftdpo-v9/tokenizer_config.json
rica40325-9-15-sftdpo-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-9-15-sftdpo-v9/tokenizer.json
rica40325-9-15-sftdpo-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-9-15-sftdpo-v9/flywheel_model.0.safetensors
rica40325-9-15-sftdpo-v9-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 4/291 [00:00<00:08, 34.06it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:04, 61.77it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:03, 70.85it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:03, 73.54it/s]
Loading 0:  14%|█▍        | 41/291 [00:00<00:03, 82.34it/s]
Loading 0:  17%|█▋        | 50/291 [00:00<00:02, 82.64it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:02, 80.15it/s]
Loading 0:  24%|██▍       | 70/291 [00:00<00:02, 81.78it/s]
Loading 0:  27%|██▋       | 80/291 [00:01<00:02, 86.90it/s]
Loading 0:  31%|███       | 89/291 [00:02<00:09, 21.61it/s]
Loading 0:  33%|███▎      | 97/291 [00:02<00:07, 26.85it/s]
Loading 0:  36%|███▋      | 106/291 [00:02<00:05, 33.76it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:04, 40.93it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:03, 45.71it/s]
Loading 0:  46%|████▌     | 133/291 [00:02<00:03, 51.71it/s]
Loading 0:  49%|████▉     | 142/291 [00:02<00:02, 57.77it/s]
Loading 0:  52%|█████▏    | 151/291 [00:03<00:02, 61.72it/s]
Loading 0:  55%|█████▍    | 160/291 [00:03<00:02, 65.50it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:01, 69.41it/s]
Loading 0:  61%|██████    | 178/291 [00:03<00:01, 72.33it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:05, 19.66it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:03, 25.34it/s]
Loading 0:  70%|███████   | 205/291 [00:04<00:02, 31.46it/s]
Loading 0:  74%|███████▎  | 214/291 [00:04<00:02, 38.23it/s]
Loading 0:  77%|███████▋  | 223/291 [00:05<00:01, 44.82it/s]
Loading 0:  80%|███████▉  | 232/291 [00:05<00:01, 49.40it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:00, 54.98it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 57.94it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 62.05it/s]
Loading 0:  92%|█████████▏| 268/291 [00:05<00:00, 66.38it/s]
Loading 0:  95%|█████████▌| 277/291 [00:05<00:00, 69.38it/s]
Loading 0:  98%|█████████▊| 286/291 [00:05<00:00, 71.66it/s]
                                                            
Job rica40325-9-15-sftdpo-v9-mkmlizer completed after 84.29s with status: succeeded
Stopping job with name rica40325-9-15-sftdpo-v9-mkmlizer
Pipeline stage MKMLizer completed in 84.74s
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 rica40325-9-15-sftdpo-v9
Waiting for inference service rica40325-9-15-sftdpo-v9 to be ready
Inference service rica40325-9-15-sftdpo-v9 ready after 90.30577063560486s
Pipeline stage MKMLDeployer completed in 91.09s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9907398223876953s
Received healthy response to inference request in 1.3754379749298096s
Received healthy response to inference request in 1.1597988605499268s
Received healthy response to inference request in 1.382418155670166s
Received healthy response to inference request in 1.2858185768127441s
5 requests
0 failed requests
5th percentile: 1.1850028038024902
10th percentile: 1.2102067470550537
20th percentile: 1.2606146335601807
30th percentile: 1.3037424564361573
40th percentile: 1.3395902156829833
50th percentile: 1.3754379749298096
60th percentile: 1.378230047225952
70th percentile: 1.3810221195220946
80th percentile: 1.504082489013672
90th percentile: 1.7474111557006837
95th percentile: 1.8690754890441894
99th percentile: 1.966406955718994
mean time: 1.4388426780700683
Pipeline stage StressChecker completed in 8.52s
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 0.69s
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 0.62s
Shutdown handler de-registered
rica40325-9-15-sftdpo_v9 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 3563.14s
Shutdown handler de-registered
rica40325-9-15-sftdpo_v9 status is now inactive due to auto deactivation removed underperforming models
rica40325-9-15-sftdpo_v9 status is now torndown due to DeploymentManager action