developer_uid: leosheng
submission_id: leosheng-rp-no-repeat_v1
model_name: leosheng-rp-no-repeat_v1
model_group: leosheng/rp-no-repeat
status: torndown
timestamp: 2025-01-24T17:38:19+00:00
num_battles: 8637
num_wins: 3766
celo_rating: 1223.01
family_friendly_score: 0.591
family_friendly_standard_error: 0.006952970588173086
submission_type: basic
model_repo: leosheng/rp-no-repeat
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
display_name: leosheng-rp-no-repeat_v1
is_internal_developer: False
language_model: leosheng/rp-no-repeat
model_size: 8B
ranking_group: single
us_pacific_date: 2025-01-24
win_ratio: 0.4360310292925784
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 leosheng-rp-no-repeat-v1-mkmlizer
Waiting for job on leosheng-rp-no-repeat-v1-mkmlizer to finish
leosheng-rp-no-repeat-v1-mkmlizer: Downloaded to shared memory in 36.486s
leosheng-rp-no-repeat-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpwxw0siho, device:0
leosheng-rp-no-repeat-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
leosheng-rp-no-repeat-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.
leosheng-rp-no-repeat-v1-mkmlizer:   tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
leosheng-rp-no-repeat-v1-mkmlizer: quantized model in 26.702s
leosheng-rp-no-repeat-v1-mkmlizer: Processed model leosheng/rp-no-repeat in 63.188s
leosheng-rp-no-repeat-v1-mkmlizer: creating bucket guanaco-mkml-models
leosheng-rp-no-repeat-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
leosheng-rp-no-repeat-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/leosheng-rp-no-repeat-v1
leosheng-rp-no-repeat-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/leosheng-rp-no-repeat-v1/config.json
leosheng-rp-no-repeat-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/leosheng-rp-no-repeat-v1/special_tokens_map.json
leosheng-rp-no-repeat-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/leosheng-rp-no-repeat-v1/tokenizer_config.json
leosheng-rp-no-repeat-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/leosheng-rp-no-repeat-v1/tokenizer.json
leosheng-rp-no-repeat-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/leosheng-rp-no-repeat-v1/flywheel_model.0.safetensors
leosheng-rp-no-repeat-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 50.64it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:04, 66.35it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 67.85it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:03, 72.75it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:03, 76.09it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:03, 77.92it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:03, 69.19it/s]
Loading 0:  24%|██▍       | 70/291 [00:01<00:03, 65.66it/s]
Loading 0:  27%|██▋       | 79/291 [00:01<00:03, 70.14it/s]
Loading 0:  30%|██▉       | 87/291 [00:02<00:10, 19.76it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:08, 24.19it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:05, 31.53it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:04, 39.42it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 46.95it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 53.35it/s]
Loading 0:  48%|████▊     | 139/291 [00:02<00:02, 60.18it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:02, 64.12it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:01, 68.78it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:01, 70.45it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:01, 73.38it/s]
Loading 0:  63%|██████▎   | 184/291 [00:03<00:01, 76.31it/s]
Loading 0:  66%|██████▋   | 193/291 [00:04<00:04, 20.62it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:03, 25.80it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:02, 31.42it/s]
Loading 0:  76%|███████▌  | 220/291 [00:05<00:01, 37.71it/s]
Loading 0:  79%|███████▊  | 229/291 [00:05<00:01, 42.93it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:01, 47.81it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 52.15it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 54.80it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 56.93it/s]
Loading 0:  94%|█████████▍| 274/291 [00:05<00:00, 59.56it/s]
Loading 0:  97%|█████████▋| 283/291 [00:06<00:00, 60.97it/s]
Loading 0: 100%|█████████▉| 290/291 [00:06<00:00, 36.64it/s]
                                                            

Job leosheng-rp-no-repeat-v1-mkmlizer completed after 93.05s with status: succeeded
Stopping job with name leosheng-rp-no-repeat-v1-mkmlizer
Pipeline stage MKMLizer completed in 93.53s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service leosheng-rp-no-repeat-v1
Waiting for inference service leosheng-rp-no-repeat-v1 to be ready
Inference service leosheng-rp-no-repeat-v1 ready after 181.1252326965332s
Pipeline stage MKMLDeployer completed in 181.53s
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 1.5915746688842773s
Received healthy response to inference request in 1.7160489559173584s
Received healthy response to inference request in 1.4951872825622559s
Received healthy response to inference request in 1.4904284477233887s
5 requests
1 failed requests
5th percentile: 1.491380214691162
10th percentile: 1.4923319816589355
20th percentile: 1.4942355155944824
30th percentile: 1.51446475982666
40th percentile: 1.5530197143554687
50th percentile: 1.5915746688842773
60th percentile: 1.6413643836975098
70th percentile: 1.6911540985107423
80th percentile: 5.393481922149661
90th percentile: 12.74834785461426
95th percentile: 16.425780820846555
99th percentile: 19.367727193832398
mean time: 5.279290628433228
%s, retrying in %s seconds...
Received healthy response to inference request in 1.4366624355316162s
Received healthy response to inference request in 1.4531300067901611s
Received healthy response to inference request in 1.9398670196533203s
Received healthy response to inference request in 1.1653399467468262s
Received healthy response to inference request in 1.1920616626739502s
5 requests
0 failed requests
5th percentile: 1.170684289932251
10th percentile: 1.1760286331176757
20th percentile: 1.1867173194885254
30th percentile: 1.2409818172454834
40th percentile: 1.3388221263885498
50th percentile: 1.4366624355316162
60th percentile: 1.4432494640350342
70th percentile: 1.4498364925384521
80th percentile: 1.550477409362793
90th percentile: 1.7451722145080566
95th percentile: 1.8425196170806883
99th percentile: 1.920397539138794
mean time: 1.4374122142791748
Pipeline stage StressChecker completed in 35.60s
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 0.63s
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 0.55s
Shutdown handler de-registered
leosheng-rp-no-repeat_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 2689.38s
Shutdown handler de-registered
leosheng-rp-no-repeat_v1 status is now inactive due to auto deactivation removed underperforming models
leosheng-rp-no-repeat_v1 status is now torndown due to DeploymentManager action