stark2000s-axolotl-coupl_9267

developer_uid: stark2000s

submission_id: stark2000s-axolotl-coupl_9267_v1

model_name: stark2000s-axolotl-coupl_9267_v1

model_group: stark2000s/axolotl_Coupl

status: inactive

timestamp: 2024-12-01T14:40:41+00:00

num_battles: 20144

num_wins: 7864

celo_rating: 1184.57

family_friendly_score: 0.5736

family_friendly_standard_error: 0.006994040892073766

submission_type: basic

model_repo: stark2000s/axolotl_CoupleRP_calm_v1

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.8731823535733422, 'latency_mean': 1.1451806712150574, 'latency_p50': 1.1417304277420044, 'latency_p90': 1.2639403820037842}, {'batch_size': 4, 'throughput': 1.8589528998501859, 'latency_mean': 2.141941245794296, 'latency_p50': 2.1484063863754272, 'latency_p90': 2.380108141899109}, {'batch_size': 5, 'throughput': 1.986898594636647, 'latency_mean': 2.497313281297684, 'latency_p50': 2.496602773666382, 'latency_p90': 2.830266237258911}, {'batch_size': 8, 'throughput': 2.2176083145423067, 'latency_mean': 3.5899838840961458, 'latency_p50': 3.603403091430664, 'latency_p90': 4.068721795082093}, {'batch_size': 10, 'throughput': 2.285734265560488, 'latency_mean': 4.346841875314713, 'latency_p50': 4.319789528846741, 'latency_p90': 4.98059458732605}, {'batch_size': 12, 'throughput': 2.310980974343703, 'latency_mean': 5.147222381830216, 'latency_p50': 5.18804669380188, 'latency_p90': 5.832139039039612}, {'batch_size': 15, 'throughput': 2.325543628086674, 'latency_mean': 6.373442122936249, 'latency_p50': 6.346398711204529, 'latency_p90': 7.132691740989685}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: stark2000s-axolotl-coupl_9267_v1

is_internal_developer: False

language_model: stark2000s/axolotl_CoupleRP_calm_v1

model_size: 8B

ranking_group: single

throughput_3p7s: 2.24

us_pacific_date: 2024-12-01

win_ratio: 0.3903891977760127

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 stark2000s-axolotl-coupl-9267-v1-mkmlizer
Waiting for job on stark2000s-axolotl-coupl-9267-v1-mkmlizer to finish
stark2000s-axolotl-coupl-9267-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
stark2000s-axolotl-coupl-9267-v1-mkmlizer: ║     _____            __           __                                ║
stark2000s-axolotl-coupl-9267-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
stark2000s-axolotl-coupl-9267-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
stark2000s-axolotl-coupl-9267-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
stark2000s-axolotl-coupl-9267-v1-mkmlizer: ║       /___/                                                         ║
stark2000s-axolotl-coupl-9267-v1-mkmlizer: ║                                                                     ║
stark2000s-axolotl-coupl-9267-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
stark2000s-axolotl-coupl-9267-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
stark2000s-axolotl-coupl-9267-v1-mkmlizer: ║  https://mk1.ai                                                     ║
stark2000s-axolotl-coupl-9267-v1-mkmlizer: ║                                                                     ║
stark2000s-axolotl-coupl-9267-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
stark2000s-axolotl-coupl-9267-v1-mkmlizer: ║  belonging to:                                                      ║
stark2000s-axolotl-coupl-9267-v1-mkmlizer: ║                                                                     ║
stark2000s-axolotl-coupl-9267-v1-mkmlizer: ║  Chai Research Corp.                                                ║
stark2000s-axolotl-coupl-9267-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
stark2000s-axolotl-coupl-9267-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
stark2000s-axolotl-coupl-9267-v1-mkmlizer: ║                                                                     ║
stark2000s-axolotl-coupl-9267-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
stark2000s-axolotl-coupl-9267-v1-mkmlizer: Downloaded to shared memory in 36.733s
stark2000s-axolotl-coupl-9267-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpkc4f34j2, device:0
stark2000s-axolotl-coupl-9267-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
stark2000s-axolotl-coupl-9267-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.
stark2000s-axolotl-coupl-9267-v1-mkmlizer:   tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
stark2000s-axolotl-coupl-9267-v1-mkmlizer: quantized model in 25.991s
stark2000s-axolotl-coupl-9267-v1-mkmlizer: Processed model stark2000s/axolotl_CoupleRP_calm_v1 in 62.724s
stark2000s-axolotl-coupl-9267-v1-mkmlizer: creating bucket guanaco-mkml-models
stark2000s-axolotl-coupl-9267-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/stark2000s-axolotl-coupl-9267-v1/config.json
stark2000s-axolotl-coupl-9267-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/stark2000s-axolotl-coupl-9267-v1/special_tokens_map.json
stark2000s-axolotl-coupl-9267-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/stark2000s-axolotl-coupl-9267-v1/tokenizer_config.json
stark2000s-axolotl-coupl-9267-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/stark2000s-axolotl-coupl-9267-v1/tokenizer.json
stark2000s-axolotl-coupl-9267-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/stark2000s-axolotl-coupl-9267-v1/flywheel_model.0.safetensors
stark2000s-axolotl-coupl-9267-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 49.47it/s]
Loading 0:   6%|▌         | 17/291 [00:00<00:03, 74.79it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 75.95it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:02, 90.06it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:02, 88.06it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:02, 88.48it/s]
Loading 0:  24%|██▍       | 70/291 [00:00<00:02, 86.59it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:08, 24.86it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:07, 28.53it/s]
Loading 0:  34%|███▎      | 98/291 [00:02<00:05, 34.28it/s]
Loading 0:  36%|███▋      | 106/291 [00:02<00:04, 39.16it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:03, 47.16it/s]
Loading 0:  43%|████▎     | 125/291 [00:02<00:02, 57.05it/s]
Loading 0:  46%|████▌     | 134/291 [00:02<00:02, 62.97it/s]
Loading 0:  49%|████▉     | 143/291 [00:02<00:02, 66.97it/s]
Loading 0:  54%|█████▍    | 157/291 [00:02<00:01, 77.33it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:01, 79.62it/s]
Loading 0:  62%|██████▏   | 179/291 [00:03<00:01, 83.29it/s]
Loading 0:  65%|██████▍   | 188/291 [00:04<00:04, 23.67it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:03, 28.72it/s]
Loading 0:  70%|███████   | 205/291 [00:04<00:02, 35.23it/s]
Loading 0:  74%|███████▎  | 214/291 [00:04<00:01, 42.77it/s]
Loading 0:  77%|███████▋  | 223/291 [00:04<00:01, 49.55it/s]
Loading 0:  82%|████████▏ | 238/291 [00:04<00:00, 63.24it/s]
Loading 0:  85%|████████▍ | 247/291 [00:04<00:00, 67.79it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 72.27it/s]
Loading 0:  92%|█████████▏| 268/291 [00:05<00:00, 73.96it/s]
Loading 0:  97%|█████████▋| 283/291 [00:05<00:00, 82.38it/s]
                                                            
Job stark2000s-axolotl-coupl-9267-v1-mkmlizer completed after 84.07s with status: succeeded
Stopping job with name stark2000s-axolotl-coupl-9267-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.60s
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 stark2000s-axolotl-coupl-9267-v1
Waiting for inference service stark2000s-axolotl-coupl-9267-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Failed to get response for submission blend_rugen_2024-11-26: HTTPConnectionPool(host='chaiml-elo-alignment-run-3-v44-predictor.tenant-chaiml-guanaco.k2.chaiverse.com', port=80): Max retries exceeded with url: /v1/models/GPT-J-6B-lit-v2:predict (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x713304565250>: Failed to establish a new connection: [Errno -3] Temporary failure in name resolution'))
Inference service stark2000s-axolotl-coupl-9267-v1 ready after 150.70581650733948s
Pipeline stage MKMLDeployer completed in 151.22s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 7.5937440395355225s
Received healthy response to inference request in 6.340810298919678s
Received healthy response to inference request in 2.629132032394409s
Received healthy response to inference request in 6.428687334060669s
Received healthy response to inference request in 1.5445575714111328s
5 requests
0 failed requests
5th percentile: 1.761472463607788
10th percentile: 1.9783873558044434
20th percentile: 2.412217140197754
30th percentile: 3.3714676856994625
40th percentile: 4.856138992309571
50th percentile: 6.340810298919678
60th percentile: 6.375961112976074
70th percentile: 6.41111192703247
80th percentile: 6.66169867515564
90th percentile: 7.127721357345581
95th percentile: 7.360732698440551
99th percentile: 7.547141771316528
mean time: 4.907386255264282
%s, retrying in %s seconds...
{"detail":"HTTPConnectionPool(host='stark2000s-axolotl-coupl-9267-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Max retries exceeded with url: /v1/models/GPT-J-6B-lit-v2:predict (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7623745ae650>: Failed to establish a new connection: [Errno -3] Temporary failure in name resolution'))"}
Received unhealthy response to inference request!
Received healthy response to inference request in 11.515271425247192s
Received healthy response to inference request in 1.2521648406982422s
Received healthy response to inference request in 1.6495962142944336s
Received healthy response to inference request in 1.599198341369629s
5 requests
1 failed requests
5th percentile: 1.3215715408325195
10th percentile: 1.3909782409667968
20th percentile: 1.5297916412353516
30th percentile: 1.6092779159545898
40th percentile: 1.6294370651245118
50th percentile: 1.6495962142944336
60th percentile: 5.061327171325683
70th percentile: 8.473058128356932
80th percentile: 10.446193170547486
90th percentile: 10.980732297897339
95th percentile: 11.248001861572265
99th percentile: 11.461817512512207
mean time: 5.239030885696411
%s, retrying in %s seconds...
Received healthy response to inference request in 1.2092957496643066s
Received healthy response to inference request in 1.3795931339263916s
Received healthy response to inference request in 1.2306139469146729s
Received healthy response to inference request in 1.183610439300537s
Received healthy response to inference request in 1.1528332233428955s
5 requests
0 failed requests
5th percentile: 1.1589886665344238
10th percentile: 1.165144109725952
20th percentile: 1.1774549961090088
30th percentile: 1.188747501373291
40th percentile: 1.1990216255187989
50th percentile: 1.2092957496643066
60th percentile: 1.2178230285644531
70th percentile: 1.2263503074645996
80th percentile: 1.2604097843170166
90th percentile: 1.3200014591217042
95th percentile: 1.349797296524048
99th percentile: 1.373633966445923
mean time: 1.2311892986297608
Pipeline stage StressChecker completed in 61.04s
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 2.24s
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 2.43s
Shutdown handler de-registered
stark2000s-axolotl-coupl_9267_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 2660.19s
Shutdown handler de-registered
stark2000s-axolotl-coupl_9267_v1 status is now inactive due to auto deactivation removed underperforming models