chaiml-elo-alignment-run-3

developer_uid: jxlu90
submission_id: chaiml-elo-alignment-run-3_v63
model_name: chaiml-elo-alignment-run-3_v63
model_group: ChaiML/elo_alignment_run
status: inactive
timestamp: 2024-12-17T22:42:06+00:00
num_battles: 2958
num_wins: 1552
celo_rating: 1284.6
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: ChaiML/elo_alignment_run_3
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 2048
max_output_tokens: 64
display_name: chaiml-elo-alignment-run-3_v63
ineligible_reason: num_battles<5000
is_internal_developer: True
language_model: ChaiML/elo_alignment_run_3
model_size: 8B
ranking_group: single
us_pacific_date: 2024-12-17
win_ratio: 0.5246788370520622
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 2048, 'best_of': 16, '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 chaiml-elo-alignment-run-3-v63-mkmlizer
Waiting for job on chaiml-elo-alignment-run-3-v63-mkmlizer to finish
chaiml-elo-alignment-run-3-v63-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-elo-alignment-run-3-v63-mkmlizer: ║     _____            __           __                                ║
chaiml-elo-alignment-run-3-v63-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-elo-alignment-run-3-v63-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-elo-alignment-run-3-v63-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-elo-alignment-run-3-v63-mkmlizer: ║       /___/                                                         ║
chaiml-elo-alignment-run-3-v63-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v63-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-elo-alignment-run-3-v63-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-elo-alignment-run-3-v63-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-elo-alignment-run-3-v63-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v63-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-elo-alignment-run-3-v63-mkmlizer: ║  belonging to:                                                      ║
chaiml-elo-alignment-run-3-v63-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v63-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-elo-alignment-run-3-v63-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-elo-alignment-run-3-v63-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-elo-alignment-run-3-v63-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v63-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-elo-alignment-run-3-v63-mkmlizer: Downloaded to shared memory in 45.032s
chaiml-elo-alignment-run-3-v63-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3kv9wpqy, device:0
chaiml-elo-alignment-run-3-v63-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-elo-alignment-run-3-v63-mkmlizer: quantized model in 29.959s
chaiml-elo-alignment-run-3-v63-mkmlizer: Processed model ChaiML/elo_alignment_run_3 in 74.991s
chaiml-elo-alignment-run-3-v63-mkmlizer: creating bucket guanaco-mkml-models
chaiml-elo-alignment-run-3-v63-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-elo-alignment-run-3-v63-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v63
chaiml-elo-alignment-run-3-v63-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v63/tokenizer_config.json
chaiml-elo-alignment-run-3-v63-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v63/tokenizer.json
chaiml-elo-alignment-run-3-v63-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v63/flywheel_model.0.safetensors
chaiml-elo-alignment-run-3-v63-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:11, 25.07it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:07, 35.78it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:08, 32.48it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:07, 35.53it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:08, 32.97it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:06, 39.07it/s]
Loading 0:  12%|█▏        | 36/291 [00:01<00:11, 22.74it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:10, 24.51it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:07, 30.53it/s]
Loading 0:  18%|█▊        | 52/291 [00:01<00:07, 30.26it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:07, 33.32it/s]
Loading 0:  21%|██        | 61/291 [00:01<00:07, 32.53it/s]
Loading 0:  23%|██▎       | 66/291 [00:02<00:06, 34.85it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:06, 33.16it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:06, 33.65it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:06, 33.68it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:09, 23.14it/s]
Loading 0:  29%|██▉       | 85/291 [00:02<00:08, 23.78it/s]
Loading 0:  31%|███       | 90/291 [00:03<00:07, 28.05it/s]
Loading 0:  32%|███▏      | 94/291 [00:03<00:07, 28.06it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:06, 31.32it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:06, 31.04it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:05, 34.40it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 33.15it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:05, 33.97it/s]
Loading 0:  42%|████▏     | 122/291 [00:03<00:04, 38.81it/s]
Loading 0:  44%|████▎     | 127/291 [00:04<00:04, 35.73it/s]
Loading 0:  46%|████▌     | 133/291 [00:04<00:05, 29.58it/s]
Loading 0:  47%|████▋     | 137/291 [00:04<00:05, 29.64it/s]
Loading 0:  48%|████▊     | 141/291 [00:04<00:05, 27.22it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:04, 32.54it/s]
Loading 0:  52%|█████▏    | 151/291 [00:04<00:04, 30.95it/s]
Loading 0:  53%|█████▎    | 155/291 [00:05<00:04, 32.19it/s]
Loading 0:  55%|█████▍    | 159/291 [00:05<00:04, 28.62it/s]
Loading 0:  57%|█████▋    | 165/291 [00:05<00:03, 33.85it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 32.83it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 35.48it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 33.05it/s]
Loading 0:  63%|██████▎   | 182/291 [00:05<00:03, 34.28it/s]
Loading 0:  64%|██████▍   | 186/291 [00:06<00:04, 24.92it/s]
Loading 0:  65%|██████▍   | 189/291 [00:06<00:04, 22.16it/s]
Loading 0:  67%|██████▋   | 194/291 [00:06<00:04, 23.47it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 30.36it/s]
Loading 0:  70%|███████   | 205/291 [00:06<00:02, 29.31it/s]
Loading 0:  72%|███████▏  | 209/291 [00:06<00:02, 30.80it/s]
Loading 0:  73%|███████▎  | 213/291 [00:07<00:02, 27.41it/s]
Loading 0:  75%|███████▍  | 217/291 [00:07<00:02, 29.55it/s]
Loading 0:  76%|███████▌  | 221/291 [00:07<00:02, 26.55it/s]
Loading 0:  78%|███████▊  | 227/291 [00:07<00:02, 31.31it/s]
Loading 0:  79%|███████▉  | 231/291 [00:07<00:02, 29.43it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 23.01it/s]
Loading 0:  82%|████████▏ | 239/291 [00:08<00:02, 23.17it/s]
Loading 0:  85%|████████▍ | 246/291 [00:08<00:01, 30.45it/s]
Loading 0:  86%|████████▌ | 250/291 [00:08<00:01, 30.27it/s]
Loading 0:  88%|████████▊ | 255/291 [00:08<00:01, 32.91it/s]
Loading 0:  89%|████████▉ | 259/291 [00:08<00:01, 31.60it/s]
Loading 0:  91%|█████████ | 264/291 [00:08<00:00, 34.01it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 31.73it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 35.10it/s]
Loading 0:  95%|█████████▌| 277/291 [00:09<00:00, 32.40it/s]
Loading 0:  97%|█████████▋| 281/291 [00:09<00:00, 32.61it/s]
Loading 0:  98%|█████████▊| 286/291 [00:14<00:01,  2.52it/s]
Loading 0:  99%|█████████▉| 289/291 [00:15<00:00,  3.14it/s]
                                                            
Job chaiml-elo-alignment-run-3-v63-mkmlizer completed after 94.23s with status: succeeded
Stopping job with name chaiml-elo-alignment-run-3-v63-mkmlizer
Pipeline stage MKMLizer completed in 94.75s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-elo-alignment-run-3-v63
Waiting for inference service chaiml-elo-alignment-run-3-v63 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-elo-alignment-run-3-v63 ready after 230.95724415779114s
Pipeline stage MKMLDeployer completed in 231.50s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0715532302856445s
Received healthy response to inference request in 1.418274164199829s
Received healthy response to inference request in 1.8981289863586426s
Received healthy response to inference request in 1.3797330856323242s
Received healthy response to inference request in 1.6804437637329102s
5 requests
0 failed requests
5th percentile: 1.387441301345825
10th percentile: 1.3951495170593262
20th percentile: 1.4105659484863282
30th percentile: 1.4707080841064453
40th percentile: 1.5755759239196778
50th percentile: 1.6804437637329102
60th percentile: 1.7675178527832032
70th percentile: 1.854591941833496
80th percentile: 1.932813835144043
90th percentile: 2.002183532714844
95th percentile: 2.036868381500244
99th percentile: 2.0646162605285645
mean time: 1.68962664604187
Pipeline stage StressChecker completed in 9.67s
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 2.42s
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 2.28s
Shutdown handler de-registered
chaiml-elo-alignment-run-3_v63 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-elo-alignment-run-3-v63-profiler
Waiting for inference service chaiml-elo-alignment-run-3-v63-profiler to be ready
Inference service chaiml-elo-alignment-run-3-v63-profiler ready after 240.51404762268066s
Pipeline stage MKMLProfilerDeployer completed in 240.82s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-elo-alignment7b00fa64c0f8d0cb4be4ee144b539a21-deplohwtr5:/code/chaiverse_profiler_1734475938 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-elo-alignment7b00fa64c0f8d0cb4be4ee144b539a21-deplohwtr5 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1734475938 && python profiles.py profile --best_of_n 16 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 2048 --output_tokens 64 --summary /code/chaiverse_profiler_1734475938/summary.json'
Received signal 15, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-elo-alignment-run-3-v63-profiler is running
Tearing down inference service chaiml-elo-alignment-run-3-v63-profiler
Service chaiml-elo-alignment-run-3-v63-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.33s
Shutdown handler de-registered
chaiml-elo-alignment-run-3_v63 status is now inactive due to admin request