developer_uid: azuruce
submission_id: chaiml-small-story-607-e_8056_v4
model_name: temp1p1
model_group: ChaiML/small_story_607-e
status: inactive
timestamp: 2024-11-27T20:54:33+00:00
num_battles: 12768
num_wins: 6215
celo_rating: 1250.32
family_friendly_score: 0.5778
family_friendly_standard_error: 0.006984943235273999
submission_type: basic
model_repo: ChaiML/small_story_607-ed10-100_true_rpg_v3_sft
model_architecture: MistralForCausalLM
model_num_parameters: 22247282688.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.3889715148723849, 'latency_mean': 2.5708045077323916, 'latency_p50': 2.588428020477295, 'latency_p90': 2.8399166584014894}, {'batch_size': 3, 'throughput': 0.8291239038393676, 'latency_mean': 3.6019260263442994, 'latency_p50': 3.617555022239685, 'latency_p90': 3.9487443923950196}, {'batch_size': 5, 'throughput': 1.097367641548586, 'latency_mean': 4.539618320465088, 'latency_p50': 4.554925918579102, 'latency_p90': 5.0706686735153195}, {'batch_size': 6, 'throughput': 1.1841787277614635, 'latency_mean': 5.038969877958298, 'latency_p50': 5.030524134635925, 'latency_p90': 5.581705117225647}, {'batch_size': 10, 'throughput': 1.417854068032341, 'latency_mean': 7.004969946146011, 'latency_p50': 6.9734169244766235, 'latency_p90': 7.93855619430542}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: temp1p1
is_internal_developer: True
language_model: ChaiML/small_story_607-ed10-100_true_rpg_v3_sft
model_size: 22B
ranking_group: single
throughput_3p7s: 0.87
us_pacific_date: 2024-11-27
win_ratio: 0.48676378446115287
generation_params: {'temperature': 1.1, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '####', 'Bot:', 'User:', 'You:', '<|im_end|>', '<|eot_id|>'], '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-small-story-607-e-8056-v4-mkmlizer
Waiting for job on chaiml-small-story-607-e-8056-v4-mkmlizer to finish
chaiml-small-story-607-e-8056-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-small-story-607-e-8056-v4-mkmlizer: ║ _____ __ __ ║
chaiml-small-story-607-e-8056-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-small-story-607-e-8056-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-small-story-607-e-8056-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-small-story-607-e-8056-v4-mkmlizer: ║ /___/ ║
chaiml-small-story-607-e-8056-v4-mkmlizer: ║ ║
chaiml-small-story-607-e-8056-v4-mkmlizer: ║ Version: 0.11.12 ║
chaiml-small-story-607-e-8056-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-small-story-607-e-8056-v4-mkmlizer: ║ https://mk1.ai ║
chaiml-small-story-607-e-8056-v4-mkmlizer: ║ ║
chaiml-small-story-607-e-8056-v4-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-small-story-607-e-8056-v4-mkmlizer: ║ belonging to: ║
chaiml-small-story-607-e-8056-v4-mkmlizer: ║ ║
chaiml-small-story-607-e-8056-v4-mkmlizer: ║ Chai Research Corp. ║
chaiml-small-story-607-e-8056-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-small-story-607-e-8056-v4-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
chaiml-small-story-607-e-8056-v4-mkmlizer: ║ ║
chaiml-small-story-607-e-8056-v4-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
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Failed to get response for submission function_pifab_2024-11-27: max() arg is an empty sequence
chaiml-small-story-607-e-8056-v4-mkmlizer: Downloaded to shared memory in 54.760s
chaiml-small-story-607-e-8056-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmprudo1dnc, device:0
chaiml-small-story-607-e-8056-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-small-story-607-e-8056-v4-mkmlizer: quantized model in 55.536s
chaiml-small-story-607-e-8056-v4-mkmlizer: Processed model ChaiML/small_story_607-ed10-100_true_rpg_v3_sft in 110.296s
chaiml-small-story-607-e-8056-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-small-story-607-e-8056-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-small-story-607-e-8056-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-small-story-607-e-8056-v4
chaiml-small-story-607-e-8056-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-small-story-607-e-8056-v4/config.json
chaiml-small-story-607-e-8056-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-small-story-607-e-8056-v4/special_tokens_map.json
chaiml-small-story-607-e-8056-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-small-story-607-e-8056-v4/tokenizer_config.json
chaiml-small-story-607-e-8056-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-small-story-607-e-8056-v4/tokenizer.json
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-small-story-607-e-8056-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-small-story-607-e-8056-v4/flywheel_model.1.safetensors
chaiml-small-story-607-e-8056-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-small-story-607-e-8056-v4/flywheel_model.0.safetensors
chaiml-small-story-607-e-8056-v4-mkmlizer: Loading 0: 0%| | 0/507 [00:00<?, ?it/s] Loading 0: 1%| | 5/507 [00:00<00:22, 22.32it/s] Loading 0: 2%|▏ | 10/507 [00:00<00:15, 32.23it/s] Loading 0: 3%|▎ | 14/507 [00:00<00:17, 27.96it/s] Loading 0: 4%|▎ | 19/507 [00:00<00:14, 33.56it/s] Loading 0: 5%|▍ | 23/507 [00:00<00:16, 30.03it/s] Loading 0: 6%|▌ | 28/507 [00:00<00:13, 35.13it/s] Loading 0: 6%|▋ | 32/507 [00:01<00:15, 31.13it/s] Loading 0: 7%|▋ | 37/507 [00:01<00:13, 35.30it/s] Loading 0: 8%|▊ | 41/507 [00:01<00:15, 30.89it/s] Loading 0: 9%|▉ | 46/507 [00:01<00:13, 35.34it/s] Loading 0: 10%|▉ | 50/507 [00:01<00:14, 31.61it/s] Loading 0: 11%|█ | 54/507 [00:01<00:20, 22.39it/s] Loading 0: 11%|█ | 57/507 [00:02<00:20, 22.05it/s] Loading 0: 12%|█▏ | 61/507 [00:02<00:17, 25.09it/s] Loading 0: 13%|█▎ | 65/507 [00:02<00:18, 23.71it/s] Loading 0: 14%|█▍ | 70/507 [00:02<00:15, 28.40it/s] Loading 0: 15%|█▍ | 75/507 [00:02<00:13, 31.74it/s] Loading 0: 16%|█▌ | 80/507 [00:02<00:13, 31.07it/s] Loading 0: 17%|█▋ | 85/507 [00:02<00:12, 34.93it/s] Loading 0: 18%|█▊ | 89/507 [00:03<00:13, 30.81it/s] Loading 0: 19%|█▊ | 94/507 [00:03<00:12, 34.26it/s] Loading 0: 19%|█▉ | 98/507 [00:03<00:13, 30.52it/s] Loading 0: 20%|██ | 103/507 [00:03<00:11, 34.59it/s] Loading 0: 21%|██ | 107/507 [00:03<00:12, 31.00it/s] Loading 0: 22%|██▏ | 113/507 [00:03<00:14, 27.45it/s] Loading 0: 23%|██▎ | 117/507 [00:04<00:15, 25.58it/s] Loading 0: 24%|██▍ | 122/507 [00:04<00:14, 25.73it/s] Loading 0: 25%|██▌ | 127/507 [00:04<00:12, 30.12it/s] Loading 0: 26%|██▌ | 131/507 [00:04<00:13, 27.67it/s] Loading 0: 27%|██▋ | 136/507 [00:04<00:11, 31.53it/s] Loading 0: 28%|██▊ | 140/507 [00:04<00:12, 28.34it/s] Loading 0: 29%|██▊ | 145/507 [00:04<00:11, 32.56it/s] Loading 0: 29%|██▉ | 149/507 [00:05<00:12, 29.53it/s] Loading 0: 30%|███ | 154/507 [00:05<00:10, 33.62it/s] Loading 0: 31%|███ | 158/507 [00:05<00:11, 30.08it/s] Loading 0: 32%|███▏ | 163/507 [00:05<00:09, 34.46it/s] Loading 0: 33%|███▎ | 168/507 [00:05<00:09, 35.41it/s] Loading 0: 34%|███▍ | 172/507 [00:05<00:14, 23.49it/s] Loading 0: 35%|███▍ | 176/507 [00:06<00:14, 22.90it/s] Loading 0: 36%|███▌ | 183/507 [00:06<00:10, 29.92it/s] Loading 0: 37%|███▋ | 187/507 [00:06<00:10, 29.68it/s] Loading 0: 38%|███▊ | 192/507 [00:06<00:09, 32.87it/s] Loading 0: 39%|███▊ | 196/507 [00:06<00:09, 32.25it/s] Loading 0: 40%|███▉ | 201/507 [00:06<00:08, 34.71it/s] Loading 0: 40%|████ | 205/507 [00:06<00:08, 34.03it/s] Loading 0: 41%|████▏ | 210/507 [00:06<00:08, 36.82it/s] Loading 0: 42%|████▏ | 214/507 [00:07<00:08, 36.21it/s] Loading 0: 43%|████▎ | 218/507 [00:07<00:07, 36.62it/s] Loading 0: 44%|████▍ | 222/507 [00:07<00:07, 36.08it/s] Loading 0: 45%|████▍ | 226/507 [00:07<00:10, 27.51it/s] Loading 0: 45%|████▌ | 230/507 [00:07<00:10, 26.51it/s] Loading 0: 46%|████▋ | 235/507 [00:07<00:08, 31.35it/s] Loading 0: 47%|████▋ | 239/507 [00:07<00:09, 29.24it/s] Loading 0: 49%|████▊ | 246/507 [00:08<00:07, 36.21it/s] Loading 0: 49%|████▉ | 250/507 [00:08<00:07, 33.69it/s] Loading 0: 50%|█████ | 255/507 [00:08<00:07, 34.59it/s] Loading 0: 51%|█████ | 259/507 [00:08<00:07, 33.44it/s] Loading 0: 52%|█████▏ | 264/507 [00:08<00:07, 34.53it/s] Loading 0: 53%|█████▎ | 268/507 [00:08<00:07, 32.82it/s] Loading 0: 54%|█████▍ | 273/507 [00:08<00:06, 35.54it/s] Loading 0: 55%|█████▍ | 277/507 [00:08<00:06, 34.11it/s] Loading 0: 56%|█████▌ | 283/507 [00:09<00:06, 36.05it/s] Loading 0: 57%|█████▋ | 287/507 [00:09<00:09, 23.90it/s] Loading 0: 58%|█████▊ | 293/507 [00:09<00:08, 26.67it/s] Loading 0: 59%|█████▉ | 299/507 [00:19<00:07, 26.67it/s] Loading 0: 59%|█████▉ | 300/507 [00:30<03:59, 1.16s/it] Loading 0: 60%|█████▉ | 302/507 [00:31<03:27, 1.01s/it] Loading 0: 61%|██████ | 307/507 [00:31<02:19, 1.43it/s] Loading 0: 61%|██████ | 310/507 [00:31<01:50, 1.79it/s] Loading 0: 62%|██████▏ | 315/507 [00:31<01:12, 2.65it/s] Loading 0: 63%|██████▎ | 319/507 [00:31<00:52, 3.58it/s] Loading 0: 64%|██████▎ | 323/507 [00:31<00:38, 4.83it/s] Loading 0: 64%|██████▍ | 327/507 [00:31<00:27, 6.45it/s] Loading 0: 65%|██████▌ | 331/507 [00:31<00:20, 8.41it/s] Loading 0: 66%|██████▌ | 335/507 [00:32<00:15, 10.87it/s] Loading 0: 67%|██████▋ | 340/507 [00:32<00:12, 13.01it/s] Loading 0: 68%|██████▊ | 344/507 [00:32<00:10, 15.34it/s] Loading 0: 68%|██████▊ | 347/507 [00:32<00:10, 15.70it/s] Loading 0: 69%|██████▉ | 352/507 [00:32<00:07, 20.66it/s] Loading 0: 70%|███████ | 356/507 [00:32<00:06, 21.66it/s] Loading 0: 71%|███████▏ | 362/507 [00:32<00:05, 28.67it/s] Loading 0: 72%|███████▏ | 366/507 [00:33<00:05, 27.50it/s] Loading 0: 73%|███████▎ | 372/507 [00:33<00:04, 32.56it/s] Loading 0: 74%|███████▍ | 376/507 [00:33<00:04, 31.96it/s] Loading 0: 75%|███████▌ | 381/507 [00:33<00:03, 34.86it/s] Loading 0: 76%|███████▌ | 385/507 [00:33<00:03, 33.11it/s] Loading 0: 77%|███████▋ | 389/507 [00:33<00:03, 33.04it/s] Loading 0: 78%|███████▊ | 393/507 [00:33<00:03, 32.80it/s] Loading 0: 78%|███████▊ | 397/507 [00:34<00:04, 24.79it/s] Loading 0: 79%|███████▉ | 401/507 [00:34<00:04, 24.73it/s] Loading 0: 80%|████████ | 408/507 [00:34<00:03, 31.79it/s] Loading 0: 81%|████████▏ | 412/507 [00:34<00:03, 30.92it/s] Loading 0: 82%|████████▏ | 417/507 [00:34<00:02, 33.45it/s] Loading 0: 83%|████████▎ | 421/507 [00:34<00:02, 32.75it/s] Loading 0: 84%|████████▍ | 426/507 [00:34<00:02, 35.83it/s] Loading 0: 85%|████████▍ | 430/507 [00:35<00:02, 34.54it/s] Loading 0: 86%|████████▌ | 435/507 [00:35<00:01, 37.32it/s] Loading 0: 87%|████████▋ | 439/507 [00:35<00:01, 36.23it/s] Loading 0: 88%|████████▊ | 444/507 [00:35<00:01, 39.16it/s] Loading 0: 88%|████████▊ | 448/507 [00:35<00:01, 37.43it/s] Loading 0: 90%|████████▉ | 454/507 [00:35<00:01, 37.86it/s] Loading 0: 90%|█████████ | 458/507 [00:38<00:08, 5.61it/s] Loading 0: 91%|█████████ | 461/507 [00:38<00:06, 6.76it/s] Loading 0: 92%|█████████▏| 465/507 [00:38<00:04, 8.71it/s] Loading 0: 93%|█████████▎| 472/507 [00:38<00:02, 13.58it/s] Loading 0: 94%|█████████▍| 476/507 [00:38<00:01, 16.03it/s] Loading 0: 95%|█████████▍| 481/507 [00:38<00:01, 20.15it/s] Loading 0: 96%|█████████▌| 485/507 [00:38<00:00, 22.50it/s] Loading 0: 97%|█████████▋| 490/507 [00:38<00:00, 26.33it/s] Loading 0: 97%|█████████▋| 494/507 [00:39<00:00, 27.33it/s] Loading 0: 98%|█████████▊| 499/507 [00:39<00:00, 30.91it/s] Loading 0: 99%|█████████▉| 503/507 [00:39<00:00, 31.15it/s]
Job chaiml-small-story-607-e-8056-v4-mkmlizer completed after 146.43s with status: succeeded
Stopping job with name chaiml-small-story-607-e-8056-v4-mkmlizer
Pipeline stage MKMLizer completed in 146.91s
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 chaiml-small-story-607-e-8056-v4
Waiting for inference service chaiml-small-story-607-e-8056-v4 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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-small-story-607-e-8056-v4 ready after 130.71987533569336s
Pipeline stage MKMLDeployer completed in 131.49s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.056750774383545s
Received healthy response to inference request in 2.4155609607696533s
Received healthy response to inference request in 2.261056900024414s
Received healthy response to inference request in 3.278455972671509s
Received healthy response to inference request in 2.3024747371673584s
5 requests
0 failed requests
5th percentile: 2.269340467453003
10th percentile: 2.2776240348815917
20th percentile: 2.2941911697387694
30th percentile: 2.3250919818878173
40th percentile: 2.3703264713287355
50th percentile: 2.4155609607696533
60th percentile: 2.67203688621521
70th percentile: 2.9285128116607666
80th percentile: 3.101091814041138
90th percentile: 3.1897738933563233
95th percentile: 3.234114933013916
99th percentile: 3.26958776473999
mean time: 2.662859869003296
Pipeline stage StressChecker completed in 14.61s
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 2.18s
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 1.98s
Shutdown handler de-registered
chaiml-small-story-607-e_8056_v4 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 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-small-story-607-e-8056-v4-profiler
Waiting for inference service chaiml-small-story-607-e-8056-v4-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 3519.47s
Shutdown handler de-registered
chaiml-small-story-607-e_8056_v4 status is now inactive due to auto deactivation removed underperforming models