chaiml-innkeeper1-6-12b_79581

developer_uid: zonemercy

submission_id: chaiml-innkeeper1-6-12b_79581_v2

model_name: tempv1-2

model_group: ChaiML/InnKeeper1.6-12b0

status: torndown

timestamp: 2024-12-28T23:10:02+00:00

num_battles: 22910

num_wins: 11872

celo_rating: 1277.19

family_friendly_score: 0.598

family_friendly_standard_error: 0.0069339166421294686

submission_type: basic

model_repo: ChaiML/InnKeeper1.6-12b0-l1e5r7

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.6430059182503847, 'latency_mean': 1.5551043140888214, 'latency_p50': 1.5560648441314697, 'latency_p90': 1.7041266441345215}, {'batch_size': 3, 'throughput': 1.2756570976650148, 'latency_mean': 2.3466159284114836, 'latency_p50': 2.3525017499923706, 'latency_p90': 2.584115219116211}, {'batch_size': 5, 'throughput': 1.6267791823435065, 'latency_mean': 3.056049772500992, 'latency_p50': 3.0803005695343018, 'latency_p90': 3.3951534271240233}, {'batch_size': 6, 'throughput': 1.7181774805021832, 'latency_mean': 3.46700976729393, 'latency_p50': 3.450408101081848, 'latency_p90': 3.909595561027527}, {'batch_size': 8, 'throughput': 1.877767271703615, 'latency_mean': 4.233743450641632, 'latency_p50': 4.194350242614746, 'latency_p90': 4.750553631782532}, {'batch_size': 10, 'throughput': 1.9649702124563981, 'latency_mean': 5.041186864376068, 'latency_p50': 5.077696323394775, 'latency_p90': 5.7098757266998295}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: tempv1-2

is_internal_developer: True

language_model: ChaiML/InnKeeper1.6-12b0-l1e5r7

model_size: 13B

ranking_group: single

throughput_3p7s: 1.79

us_pacific_date: 2024-12-28

win_ratio: 0.5182016586643388

generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<|eot_id|>', '</s>', 'User:', '####', '<|im_end|>', 'Bot:', '\n', 'You:'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', '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 chaiml-innkeeper1-6-12b-79581-v2-mkmlizer
Waiting for job on chaiml-innkeeper1-6-12b-79581-v2-mkmlizer to finish
chaiml-innkeeper1-6-12b-79581-v2-mkmlizer: Downloaded to shared memory in 34.232s
chaiml-innkeeper1-6-12b-79581-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpztsaofnh, device:0
chaiml-innkeeper1-6-12b-79581-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-innkeeper1-6-12b-79581-v2-mkmlizer: quantized model in 38.558s
chaiml-innkeeper1-6-12b-79581-v2-mkmlizer: Processed model ChaiML/InnKeeper1.6-12b0-l1e5r7 in 72.790s
chaiml-innkeeper1-6-12b-79581-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-innkeeper1-6-12b-79581-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-innkeeper1-6-12b-79581-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-innkeeper1-6-12b-79581-v2
chaiml-innkeeper1-6-12b-79581-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-innkeeper1-6-12b-79581-v2/config.json
chaiml-innkeeper1-6-12b-79581-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-innkeeper1-6-12b-79581-v2/special_tokens_map.json
chaiml-innkeeper1-6-12b-79581-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-innkeeper1-6-12b-79581-v2/tokenizer_config.json
chaiml-innkeeper1-6-12b-79581-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-innkeeper1-6-12b-79581-v2/tokenizer.json
chaiml-innkeeper1-6-12b-79581-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-innkeeper1-6-12b-79581-v2/flywheel_model.0.safetensors
chaiml-innkeeper1-6-12b-79581-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 25.92it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 41.03it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:08, 39.54it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:08, 38.58it/s]
Loading 0:   7%|▋         | 26/363 [00:00<00:08, 38.53it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:08, 38.30it/s]
Loading 0:   9%|▉         | 34/363 [00:00<00:09, 36.35it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:08, 39.14it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:08, 37.09it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:07, 39.77it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:07, 38.96it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:07, 38.62it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:11, 26.97it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:11, 27.07it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:08, 32.74it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:08, 32.19it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:08, 34.77it/s]
Loading 0:  23%|██▎       | 84/363 [00:02<00:08, 34.20it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:07, 37.49it/s]
Loading 0:  26%|██▌       | 93/363 [00:02<00:07, 36.11it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:07, 37.74it/s]
Loading 0:  28%|██▊       | 102/363 [00:02<00:07, 36.00it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:07, 35.99it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:06, 40.79it/s]
Loading 0:  32%|███▏      | 117/363 [00:03<00:06, 39.41it/s]
Loading 0:  33%|███▎      | 121/363 [00:03<00:06, 38.49it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:06, 37.43it/s]
Loading 0:  36%|███▌      | 129/363 [00:03<00:06, 35.70it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:06, 37.20it/s]
Loading 0:  38%|███▊      | 138/363 [00:03<00:06, 35.66it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:08, 27.26it/s]
Loading 0:  40%|████      | 146/363 [00:04<00:07, 28.22it/s]
Loading 0:  41%|████▏     | 150/363 [00:04<00:07, 27.40it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:07, 29.61it/s]
Loading 0:  44%|████▎     | 158/363 [00:04<00:07, 28.84it/s]
Loading 0:  45%|████▌     | 164/363 [00:04<00:05, 36.10it/s]
Loading 0:  46%|████▋     | 168/363 [00:04<00:05, 32.77it/s]
Loading 0:  47%|████▋     | 172/363 [00:04<00:05, 32.92it/s]
Loading 0:  48%|████▊     | 176/363 [00:05<00:06, 29.95it/s]
Loading 0:  50%|█████     | 183/363 [00:05<00:04, 37.13it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:04, 35.62it/s]
Loading 0:  53%|█████▎    | 192/363 [00:05<00:04, 38.01it/s]
Loading 0:  54%|█████▍    | 196/363 [00:05<00:04, 36.36it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:04, 38.10it/s]
Loading 0:  56%|█████▋    | 205/363 [00:05<00:04, 36.27it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 38.57it/s]
Loading 0:  59%|█████▉    | 214/363 [00:06<00:03, 38.47it/s]
Loading 0:  60%|██████    | 218/363 [00:06<00:03, 38.14it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:04, 30.17it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:04, 30.04it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:04, 28.48it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 35.26it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 35.38it/s]
Loading 0:  68%|██████▊   | 247/363 [00:07<00:02, 39.68it/s]
Loading 0:  69%|██████▉   | 252/363 [00:07<00:02, 40.59it/s]
Loading 0:  71%|███████   | 257/363 [00:07<00:03, 32.39it/s]
Loading 0:  72%|███████▏  | 262/363 [00:07<00:02, 35.89it/s]
Loading 0:  73%|███████▎  | 266/363 [00:07<00:02, 32.48it/s]
Loading 0:  75%|███████▍  | 271/363 [00:07<00:02, 35.40it/s]
Loading 0:  76%|███████▌  | 275/363 [00:07<00:02, 32.18it/s]
Loading 0:  77%|███████▋  | 280/363 [00:08<00:02, 36.15it/s]
Loading 0:  78%|███████▊  | 284/363 [00:08<00:02, 33.36it/s]
Loading 0:  80%|████████  | 291/363 [00:08<00:01, 39.68it/s]
Loading 0:  82%|████████▏ | 296/363 [00:08<00:01, 38.74it/s]
Loading 0:  83%|████████▎ | 300/363 [00:08<00:01, 37.89it/s]
Loading 0:  84%|████████▎ | 304/363 [00:15<00:28,  2.10it/s]
Loading 0:  85%|████████▍ | 307/363 [00:15<00:21,  2.61it/s]
Loading 0:  86%|████████▌ | 312/363 [00:15<00:13,  3.82it/s]
Loading 0:  88%|████████▊ | 319/363 [00:15<00:07,  6.18it/s]
Loading 0:  89%|████████▉ | 323/363 [00:16<00:05,  7.75it/s]
Loading 0:  90%|█████████ | 328/363 [00:16<00:03, 10.37it/s]
Loading 0:  91%|█████████▏| 332/363 [00:16<00:02, 12.53it/s]
Loading 0:  93%|█████████▎| 337/363 [00:16<00:01, 16.12it/s]
Loading 0:  94%|█████████▍| 341/363 [00:16<00:01, 18.49it/s]
Loading 0:  95%|█████████▌| 346/363 [00:16<00:00, 22.65it/s]
Loading 0:  96%|█████████▋| 350/363 [00:16<00:00, 24.10it/s]
Loading 0:  98%|█████████▊| 354/363 [00:16<00:00, 25.94it/s]
Loading 0:  99%|█████████▊| 358/363 [00:17<00:00, 26.09it/s]
                                                            
Job chaiml-innkeeper1-6-12b-79581-v2-mkmlizer completed after 144.08s with status: succeeded
Stopping job with name chaiml-innkeeper1-6-12b-79581-v2-mkmlizer
Pipeline stage MKMLizer completed in 144.52s
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-innkeeper1-6-12b-79581-v2
Waiting for inference service chaiml-innkeeper1-6-12b-79581-v2 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-innkeeper1-6-12b-79581-v2 ready after 301.4615225791931s
Pipeline stage MKMLDeployer completed in 301.96s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9110510349273682s
Received healthy response to inference request in 1.6434829235076904s
Received healthy response to inference request in 1.7154104709625244s
Received healthy response to inference request in 1.6283349990844727s
Received healthy response to inference request in 1.5635457038879395s
5 requests
0 failed requests
5th percentile: 1.5765035629272461
10th percentile: 1.5894614219665528
20th percentile: 1.615377140045166
30th percentile: 1.6313645839691162
40th percentile: 1.6374237537384033
50th percentile: 1.6434829235076904
60th percentile: 1.6722539424896241
70th percentile: 1.7010249614715576
80th percentile: 1.7545385837554932
90th percentile: 1.8327948093414306
95th percentile: 1.8719229221343994
99th percentile: 1.9032254123687744
mean time: 1.6923650264739991
Pipeline stage StressChecker completed in 9.72s
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 0.75s
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
chaiml-innkeeper1-6-12b_79581_v2 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.07s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-innkeeper1-6-12b-79581-v2-profiler
Waiting for inference service chaiml-innkeeper1-6-12b-79581-v2-profiler to be ready
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 2558.76s
Shutdown handler de-registered
chaiml-innkeeper1-6-12b_79581_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-innkeeper1-6-12b_79581_v2 status is now torndown due to DeploymentManager action
chaiml-innkeeper1-6-12b_79581_v2 status is now torndown due to DeploymentManager action
chaiml-innkeeper1-6-12b_79581_v2 status is now torndown due to DeploymentManager action