camel-ai-camel-13b-role_67205

developer_uid: cycy233
submission_id: camel-ai-camel-13b-role_67205_v1
model_name: camel-ai-camel-13b-role_67205_v1
model_group: camel-ai/CAMEL-13B-Role-
status: torndown
timestamp: 2025-05-22T07:43:11+00:00
num_battles: 9277
num_wins: 3311
celo_rating: 1184.86
family_friendly_score: 0.6033999999999999
family_friendly_standard_error: 0.006918214220447355
submission_type: basic
model_repo: camel-ai/CAMEL-13B-Role-Playing-Data
model_architecture: LlamaForCausalLM
model_num_parameters: 13015864320.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
display_name: camel-ai-camel-13b-role_67205_v1
is_internal_developer: False
language_model: camel-ai/CAMEL-13B-Role-Playing-Data
model_size: 13B
ranking_group: single
us_pacific_date: 2025-05-22
win_ratio: 0.3569041716072006
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 camel-ai-camel-13b-role-67205-v1-mkmlizer
Waiting for job on camel-ai-camel-13b-role-67205-v1-mkmlizer to finish
camel-ai-camel-13b-role-67205-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
camel-ai-camel-13b-role-67205-v1-mkmlizer: ║     _____            __           __                                ║
camel-ai-camel-13b-role-67205-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
camel-ai-camel-13b-role-67205-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
camel-ai-camel-13b-role-67205-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
camel-ai-camel-13b-role-67205-v1-mkmlizer: ║       /___/                                                         ║
camel-ai-camel-13b-role-67205-v1-mkmlizer: ║                                                                     ║
camel-ai-camel-13b-role-67205-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
camel-ai-camel-13b-role-67205-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
camel-ai-camel-13b-role-67205-v1-mkmlizer: ║  https://mk1.ai                                                     ║
camel-ai-camel-13b-role-67205-v1-mkmlizer: ║                                                                     ║
camel-ai-camel-13b-role-67205-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
camel-ai-camel-13b-role-67205-v1-mkmlizer: ║  belonging to:                                                      ║
camel-ai-camel-13b-role-67205-v1-mkmlizer: ║                                                                     ║
camel-ai-camel-13b-role-67205-v1-mkmlizer: ║  Chai Research Corp.                                                ║
camel-ai-camel-13b-role-67205-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
camel-ai-camel-13b-role-67205-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
camel-ai-camel-13b-role-67205-v1-mkmlizer: ║                                                                     ║
camel-ai-camel-13b-role-67205-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
camel-ai-camel-13b-role-67205-v1-mkmlizer: Downloaded to shared memory in 72.605s
camel-ai-camel-13b-role-67205-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5sho2ply, device:0
camel-ai-camel-13b-role-67205-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
camel-ai-camel-13b-role-67205-v1-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.
camel-ai-camel-13b-role-67205-v1-mkmlizer:   tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
camel-ai-camel-13b-role-67205-v1-mkmlizer: 
Loading 0:   0%|          | 0/403 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 9/403 [00:00<00:06, 59.68it/s]
Loading 0:   5%|▍         | 19/403 [00:00<00:04, 76.88it/s]
Loading 0:   7%|▋         | 29/403 [00:00<00:04, 83.00it/s]
Loading 0:  10%|▉         | 39/403 [00:00<00:04, 86.12it/s]
Loading 0:  12%|█▏        | 49/403 [00:00<00:04, 85.11it/s]
Loading 0:  15%|█▍        | 59/403 [00:00<00:03, 86.40it/s]
Loading 0:  17%|█▋        | 69/403 [00:00<00:03, 86.27it/s]
Loading 0:  19%|█▉        | 78/403 [00:02<00:24, 13.44it/s]
Loading 0:  21%|██        | 85/403 [00:02<00:19, 16.44it/s]
Loading 0:  23%|██▎       | 94/403 [00:03<00:14, 22.03it/s]
Loading 0:  26%|██▌       | 104/403 [00:03<00:10, 29.35it/s]
Loading 0:  28%|██▊       | 114/403 [00:03<00:07, 37.70it/s]
Loading 0:  31%|███       | 124/403 [00:03<00:05, 46.52it/s]
Loading 0:  33%|███▎      | 134/403 [00:03<00:04, 54.95it/s]
Loading 0:  36%|███▌      | 144/403 [00:03<00:04, 62.18it/s]
Loading 0:  38%|███▊      | 154/403 [00:05<00:18, 13.60it/s]
Loading 0:  41%|████      | 164/403 [00:05<00:13, 18.33it/s]
Loading 0:  43%|████▎     | 174/403 [00:05<00:09, 24.29it/s]
Loading 0:  46%|████▌     | 184/403 [00:05<00:07, 31.28it/s]
Loading 0:  48%|████▊     | 194/403 [00:06<00:05, 38.76it/s]
Loading 0:  51%|█████     | 204/403 [00:06<00:04, 47.24it/s]
Loading 0:  53%|█████▎    | 214/403 [00:06<00:03, 54.86it/s]
Loading 0:  56%|█████▌    | 224/403 [00:06<00:02, 61.04it/s]
Loading 0:  58%|█████▊    | 233/403 [00:08<00:12, 13.88it/s]
Loading 0:  60%|█████▉    | 240/403 [00:08<00:09, 16.84it/s]
Loading 0:  62%|██████▏   | 249/403 [00:08<00:06, 22.12it/s]
Loading 0:  64%|██████▍   | 259/403 [00:08<00:04, 29.00it/s]
Loading 0:  67%|██████▋   | 269/403 [00:08<00:03, 37.25it/s]
Loading 0:  69%|██████▉   | 279/403 [00:08<00:02, 45.74it/s]
Loading 0:  72%|███████▏  | 289/403 [00:09<00:02, 54.65it/s]
Loading 0:  74%|███████▍  | 299/403 [00:09<00:01, 61.58it/s]
Loading 0:  77%|███████▋  | 309/403 [00:11<00:07, 13.43it/s]
Loading 0:  79%|███████▉  | 319/403 [00:11<00:04, 18.02it/s]
Loading 0:  82%|████████▏ | 329/403 [00:11<00:03, 23.83it/s]
Loading 0:  84%|████████▍ | 339/403 [00:11<00:02, 30.72it/s]
Loading 0:  87%|████████▋ | 349/403 [00:11<00:01, 38.40it/s]
Loading 0:  89%|████████▉ | 359/403 [00:11<00:00, 46.12it/s]
Loading 0:  92%|█████████▏| 369/403 [00:11<00:00, 54.08it/s]
Loading 0:  94%|█████████▍| 379/403 [00:12<00:00, 61.57it/s]
Loading 0:  96%|█████████▋| 388/403 [00:12<00:00, 28.92it/s]
Loading 0:  98%|█████████▊| 395/403 [00:12<00:00, 32.77it/s]
Loading 0: 100%|██████████| 403/403 [00:14<00:00, 12.87it/s]
                                                            
You are using the default legacy behaviour of the <class 'transformers.models.llama.tokenization_llama.LlamaTokenizer'>. This is expected, and simply means that the `legacy` (previous) behavior will be used so nothing changes for you. If you want to use the new behaviour, set `legacy=False`. This should only be set if you understand what it means, and thoroughly read the reason why this was added as explained in https://github.com/huggingface/transformers/pull/24565 - if you loaded a llama tokenizer from a GGUF file you can ignore this message
camel-ai-camel-13b-role-67205-v1-mkmlizer: You are using the default legacy behaviour of the <class 'transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast'>. This is expected, and simply means that the `legacy` (previous) behavior will be used so nothing changes for you. If you want to use the new behaviour, set `legacy=False`. This should only be set if you understand what it means, and thoroughly read the reason why this was added as explained in https://github.com/huggingface/transformers/pull/24565 - if you loaded a llama tokenizer from a GGUF file you can ignore this message.
camel-ai-camel-13b-role-67205-v1-mkmlizer: quantized model in 33.564s
camel-ai-camel-13b-role-67205-v1-mkmlizer: Processed model camel-ai/CAMEL-13B-Role-Playing-Data in 106.169s
camel-ai-camel-13b-role-67205-v1-mkmlizer: creating bucket guanaco-mkml-models
camel-ai-camel-13b-role-67205-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/camel-ai-camel-13b-role-67205-v1/config.json
camel-ai-camel-13b-role-67205-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/camel-ai-camel-13b-role-67205-v1/special_tokens_map.json
camel-ai-camel-13b-role-67205-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/camel-ai-camel-13b-role-67205-v1/tokenizer_config.json
camel-ai-camel-13b-role-67205-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/camel-ai-camel-13b-role-67205-v1/tokenizer.model
camel-ai-camel-13b-role-67205-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/camel-ai-camel-13b-role-67205-v1/tokenizer.json
camel-ai-camel-13b-role-67205-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/camel-ai-camel-13b-role-67205-v1/flywheel_model.0.safetensors
Job camel-ai-camel-13b-role-67205-v1-mkmlizer completed after 135.37s with status: succeeded
Stopping job with name camel-ai-camel-13b-role-67205-v1-mkmlizer
Pipeline stage MKMLizer completed in 135.83s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service camel-ai-camel-13b-role-67205-v1
Waiting for inference service camel-ai-camel-13b-role-67205-v1 to be ready
Inference service camel-ai-camel-13b-role-67205-v1 ready after 150.84421110153198s
Pipeline stage MKMLDeployer completed in 151.38s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.351404905319214s
Received healthy response to inference request in 2.0402536392211914s
Received healthy response to inference request in 1.7114832401275635s
Received healthy response to inference request in 1.6546709537506104s
Received healthy response to inference request in 1.8063724040985107s
5 requests
0 failed requests
5th percentile: 1.6660334110260009
10th percentile: 1.6773958683013916
20th percentile: 1.700120782852173
30th percentile: 1.7304610729217529
40th percentile: 1.768416738510132
50th percentile: 1.8063724040985107
60th percentile: 1.899924898147583
70th percentile: 1.9934773921966553
80th percentile: 2.102483892440796
90th percentile: 2.226944398880005
95th percentile: 2.2891746520996095
99th percentile: 2.338958854675293
mean time: 1.912837028503418
Pipeline stage StressChecker completed in 10.75s
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 0.72s
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 0.67s
Shutdown handler de-registered
camel-ai-camel-13b-role_67205_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 4102.04s
Shutdown handler de-registered
camel-ai-camel-13b-role_67205_v1 status is now inactive due to auto deactivation removed underperforming models
camel-ai-camel-13b-role_67205_v1 status is now torndown due to DeploymentManager action