chaiml-405b-mini2-12b0-_90840

developer_uid: zonemercy

submission_id: chaiml-405b-mini2-12b0-_90840_v1

model_name: tempv1-3

model_group: ChaiML/405b-mini2-12b0-s

status: torndown

timestamp: 2025-01-03T23:29:19+00:00

num_battles: 14464

num_wins: 7459

celo_rating: 1265.63

family_friendly_score: 0.5996

family_friendly_standard_error: 0.0069293555255882195

submission_type: basic

model_repo: ChaiML/405b-mini2-12b0-sftl1e5r7

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 768

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.6488184627264122, 'latency_mean': 1.541202449798584, 'latency_p50': 1.5431524515151978, 'latency_p90': 1.7075405597686768}, {'batch_size': 3, 'throughput': 1.256697613174174, 'latency_mean': 2.384417247772217, 'latency_p50': 2.372393488883972, 'latency_p90': 2.656196403503418}, {'batch_size': 5, 'throughput': 1.5474978656942926, 'latency_mean': 3.215332316160202, 'latency_p50': 3.1811389923095703, 'latency_p90': 3.604489302635193}, {'batch_size': 6, 'throughput': 1.641625711158621, 'latency_mean': 3.628264982700348, 'latency_p50': 3.614780306816101, 'latency_p90': 4.066811227798462}, {'batch_size': 8, 'throughput': 1.7516345744379607, 'latency_mean': 4.540521963834762, 'latency_p50': 4.503957271575928, 'latency_p90': 5.032894968986511}, {'batch_size': 10, 'throughput': 1.8049497227222167, 'latency_mean': 5.499326809644699, 'latency_p50': 5.479326605796814, 'latency_p90': 6.261955308914184}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: tempv1-3

is_internal_developer: True

language_model: ChaiML/405b-mini2-12b0-sftl1e5r7

model_size: 13B

ranking_group: single

throughput_3p7s: 1.66

us_pacific_date: 2025-01-03

win_ratio: 0.5156941371681416

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': ['Bot:', '####', 'User:', '</s>', 'You:', '\n', '<|im_end|>', '<|eot_id|>'], 'max_input_tokens': 768, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '####\n{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-405b-mini2-12b0-90840-v1-mkmlizer
Waiting for job on chaiml-405b-mini2-12b0-90840-v1-mkmlizer to finish
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
chaiml-405b-mini2-12b0-90840-v1-mkmlizer: Downloaded to shared memory in 53.419s
chaiml-405b-mini2-12b0-90840-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmph_ihrd0b, device:0
chaiml-405b-mini2-12b0-90840-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-405b-mini2-12b0-90840-v1-mkmlizer: quantized model in 37.799s
chaiml-405b-mini2-12b0-90840-v1-mkmlizer: Processed model ChaiML/405b-mini2-12b0-sftl1e5r7 in 91.219s
chaiml-405b-mini2-12b0-90840-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-405b-mini2-12b0-90840-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-405b-mini2-12b0-90840-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-405b-mini2-12b0-90840-v1
chaiml-405b-mini2-12b0-90840-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-405b-mini2-12b0-90840-v1/config.json
chaiml-405b-mini2-12b0-90840-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-405b-mini2-12b0-90840-v1/special_tokens_map.json
chaiml-405b-mini2-12b0-90840-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-405b-mini2-12b0-90840-v1/tokenizer_config.json
chaiml-405b-mini2-12b0-90840-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-405b-mini2-12b0-90840-v1/tokenizer.json
chaiml-405b-mini2-12b0-90840-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-405b-mini2-12b0-90840-v1/flywheel_model.0.safetensors
chaiml-405b-mini2-12b0-90840-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 26.46it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 43.01it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:08, 40.88it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:08, 40.09it/s]
Loading 0:   7%|▋         | 27/363 [00:00<00:08, 41.15it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:10, 32.80it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:08, 40.32it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:08, 39.62it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:07, 39.44it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:07, 40.43it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:07, 41.22it/s]
Loading 0:  18%|█▊        | 64/363 [00:01<00:12, 23.89it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:09, 30.69it/s]
Loading 0:  21%|██        | 76/363 [00:02<00:08, 32.43it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:08, 34.10it/s]
Loading 0:  23%|██▎       | 85/363 [00:02<00:08, 33.61it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:08, 33.85it/s]
Loading 0:  26%|██▌       | 93/363 [00:02<00:08, 32.91it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:07, 35.11it/s]
Loading 0:  28%|██▊       | 102/363 [00:02<00:07, 33.89it/s]
Loading 0:  29%|██▉       | 106/363 [00:03<00:07, 33.96it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:06, 38.26it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:06, 36.13it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 34.59it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:06, 37.01it/s]
Loading 0:  36%|███▌      | 129/363 [00:03<00:06, 35.20it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:06, 37.69it/s]
Loading 0:  38%|███▊      | 138/363 [00:03<00:06, 35.78it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:08, 25.29it/s]
Loading 0:  40%|███▉      | 145/363 [00:04<00:08, 25.12it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:08, 25.61it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:06, 34.25it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:06, 33.51it/s]
Loading 0:  45%|████▌     | 164/363 [00:04<00:05, 34.14it/s]
Loading 0:  46%|████▋     | 168/363 [00:04<00:06, 31.10it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 36.78it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 35.49it/s]
Loading 0:  50%|█████     | 183/363 [00:05<00:04, 37.57it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:04, 35.68it/s]
Loading 0:  53%|█████▎    | 192/363 [00:05<00:04, 38.24it/s]
Loading 0:  54%|█████▍    | 196/363 [00:05<00:04, 36.39it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:04, 38.72it/s]
Loading 0:  56%|█████▋    | 205/363 [00:05<00:04, 36.96it/s]
Loading 0:  58%|█████▊    | 210/363 [00:06<00:03, 40.20it/s]
Loading 0:  59%|█████▉    | 215/363 [00:06<00:03, 39.47it/s]
Loading 0:  61%|██████    | 220/363 [00:06<00:03, 41.04it/s]
Loading 0:  62%|██████▏   | 225/363 [00:06<00:05, 25.70it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 28.18it/s]
Loading 0:  66%|██████▌   | 238/363 [00:06<00:03, 36.90it/s]
Loading 0:  67%|██████▋   | 243/363 [00:06<00:03, 39.48it/s]
Loading 0:  68%|██████▊   | 248/363 [00:07<00:03, 34.60it/s]
Loading 0:  70%|███████   | 255/363 [00:07<00:02, 40.57it/s]
Loading 0:  72%|███████▏  | 260/363 [00:07<00:02, 37.79it/s]
Loading 0:  73%|███████▎  | 265/363 [00:07<00:02, 39.38it/s]
Loading 0:  75%|███████▍  | 271/363 [00:07<00:02, 39.76it/s]
Loading 0:  76%|███████▌  | 276/363 [00:07<00:02, 39.57it/s]
Loading 0:  78%|███████▊  | 283/363 [00:07<00:01, 44.89it/s]
Loading 0:  80%|███████▉  | 289/363 [00:08<00:01, 43.10it/s]
Loading 0:  81%|████████  | 294/363 [00:08<00:01, 42.23it/s]
Loading 0:  83%|████████▎ | 301/363 [00:08<00:01, 48.31it/s]
Loading 0:  85%|████████▍ | 307/363 [00:15<00:20,  2.77it/s]
Loading 0:  86%|████████▌ | 312/363 [00:15<00:13,  3.66it/s]
Loading 0:  88%|████████▊ | 319/363 [00:15<00:08,  5.42it/s]
Loading 0:  89%|████████▉ | 324/363 [00:15<00:05,  7.00it/s]
Loading 0:  91%|█████████ | 329/363 [00:15<00:03,  9.05it/s]
Loading 0:  92%|█████████▏| 334/363 [00:15<00:02, 11.71it/s]
Loading 0:  93%|█████████▎| 339/363 [00:16<00:01, 13.85it/s]
Loading 0:  95%|█████████▌| 346/363 [00:16<00:00, 19.47it/s]
Loading 0:  97%|█████████▋| 351/363 [00:16<00:00, 22.73it/s]
Loading 0:  98%|█████████▊| 356/363 [00:16<00:00, 26.33it/s]
Loading 0:  99%|█████████▉| 361/363 [00:16<00:00, 30.16it/s]
                                                            
Job chaiml-405b-mini2-12b0-90840-v1-mkmlizer completed after 124.11s with status: succeeded
Stopping job with name chaiml-405b-mini2-12b0-90840-v1-mkmlizer
Pipeline stage MKMLizer completed in 124.62s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-405b-mini2-12b0-90840-v1
Waiting for inference service chaiml-405b-mini2-12b0-90840-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-405b-mini2-12b0-90840-v1 ready after 341.8697633743286s
Pipeline stage MKMLDeployer completed in 342.39s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.943408727645874s
Received healthy response to inference request in 1.7452635765075684s
Received healthy response to inference request in 1.5341365337371826s
Received healthy response to inference request in 1.7894744873046875s
Received healthy response to inference request in 1.6095938682556152s
5 requests
0 failed requests
5th percentile: 1.5492280006408692
10th percentile: 1.5643194675445558
20th percentile: 1.5945024013519287
30th percentile: 1.6367278099060059
40th percentile: 1.690995693206787
50th percentile: 1.7452635765075684
60th percentile: 1.762947940826416
70th percentile: 1.7806323051452637
80th percentile: 1.820261335372925
90th percentile: 1.8818350315093995
95th percentile: 1.9126218795776366
99th percentile: 1.9372513580322266
mean time: 1.7243754386901855
Pipeline stage StressChecker completed in 10.04s
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 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 0.63s
Shutdown handler de-registered
chaiml-405b-mini2-12b0-_90840_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 2589.93s
Shutdown handler de-registered
chaiml-405b-mini2-12b0-_90840_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-405b-mini2-12b0-_90840_v1 status is now torndown due to DeploymentManager action
chaiml-405b-mini2-12b0-_90840_v1 status is now torndown due to DeploymentManager action
chaiml-405b-mini2-12b0-_90840_v1 status is now torndown due to DeploymentManager action