jic062-orpo-v0-6-nemo

developer_uid: chace9580

submission_id: jic062-orpo-v0-6-nemo_v1

model_name: jic062-orpo-v0-6-nemo_v1

model_group: jic062/orpo-v0.6-Nemo

status: torndown

timestamp: 2024-10-28T05:19:43+00:00

num_battles: 10986

num_wins: 6138

celo_rating: 1275.51

family_friendly_score: 0.5682

family_friendly_standard_error: 0.0070049805138915275

submission_type: basic

model_repo: jic062/orpo-v0.6-Nemo

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

display_name: jic062-orpo-v0-6-nemo_v1

is_internal_developer: False

language_model: jic062/orpo-v0.6-Nemo

model_size: 13B

ranking_group: single

us_pacific_date: 2024-10-27

win_ratio: 0.5587110868377936

generation_params: {'temperature': 1.0, 'top_p': 0.9, 'min_p': 0.05, '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': '[INST]system\n{memory}[/INST]\n', 'prompt_template': '[INST]user\n{prompt}[/INST]\n', 'bot_template': '[INST]assistant\n{bot_name}: {message}[/INST]\n', 'user_template': '[INST]user\n{user_name}: {message}[/INST]\n', 'response_template': '[INST]assistant\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 jic062-orpo-v0-6-nemo-v1-mkmlizer
Waiting for job on jic062-orpo-v0-6-nemo-v1-mkmlizer to finish
jic062-orpo-v0-6-nemo-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-orpo-v0-6-nemo-v1-mkmlizer: ║     _____            __           __                                ║
jic062-orpo-v0-6-nemo-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jic062-orpo-v0-6-nemo-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jic062-orpo-v0-6-nemo-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jic062-orpo-v0-6-nemo-v1-mkmlizer: ║       /___/                                                         ║
jic062-orpo-v0-6-nemo-v1-mkmlizer: ║                                                                     ║
jic062-orpo-v0-6-nemo-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
jic062-orpo-v0-6-nemo-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jic062-orpo-v0-6-nemo-v1-mkmlizer: ║  https://mk1.ai                                                     ║
jic062-orpo-v0-6-nemo-v1-mkmlizer: ║                                                                     ║
jic062-orpo-v0-6-nemo-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
jic062-orpo-v0-6-nemo-v1-mkmlizer: ║  belonging to:                                                      ║
jic062-orpo-v0-6-nemo-v1-mkmlizer: ║                                                                     ║
jic062-orpo-v0-6-nemo-v1-mkmlizer: ║  Chai Research Corp.                                                ║
jic062-orpo-v0-6-nemo-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jic062-orpo-v0-6-nemo-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
jic062-orpo-v0-6-nemo-v1-mkmlizer: ║                                                                     ║
jic062-orpo-v0-6-nemo-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jic062-orpo-v0-6-nemo-v1-mkmlizer: Downloaded to shared memory in 54.632s
jic062-orpo-v0-6-nemo-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5pn7lwm6, device:0
jic062-orpo-v0-6-nemo-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-orpo-v0-6-nemo-v1-mkmlizer: quantized model in 36.166s
jic062-orpo-v0-6-nemo-v1-mkmlizer: Processed model jic062/orpo-v0.6-Nemo in 90.799s
jic062-orpo-v0-6-nemo-v1-mkmlizer: creating bucket guanaco-mkml-models
jic062-orpo-v0-6-nemo-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-orpo-v0-6-nemo-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-orpo-v0-6-nemo-v1
jic062-orpo-v0-6-nemo-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-orpo-v0-6-nemo-v1/config.json
jic062-orpo-v0-6-nemo-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-orpo-v0-6-nemo-v1/special_tokens_map.json
jic062-orpo-v0-6-nemo-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-orpo-v0-6-nemo-v1/tokenizer_config.json
jic062-orpo-v0-6-nemo-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-orpo-v0-6-nemo-v1/tokenizer.json
jic062-orpo-v0-6-nemo-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-orpo-v0-6-nemo-v1/flywheel_model.0.safetensors
jic062-orpo-v0-6-nemo-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 30.33it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 51.01it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 45.35it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 41.75it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 48.82it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 47.25it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:06, 46.26it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 51.67it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 49.42it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 36.17it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 36.74it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 40.94it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:06, 41.19it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 42.11it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:05, 47.06it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:05, 45.85it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:05, 45.12it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:04, 53.26it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:05, 47.76it/s]
Loading 0:  33%|███▎      | 120/363 [00:02<00:05, 45.40it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:04, 47.64it/s]
Loading 0:  36%|███▋      | 132/363 [00:02<00:05, 45.52it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:05, 44.14it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 34.27it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 34.35it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 33.82it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 39.95it/s]
Loading 0:  44%|████▍     | 161/363 [00:03<00:04, 41.83it/s]
Loading 0:  46%|████▌     | 166/363 [00:03<00:04, 42.60it/s]
Loading 0:  47%|████▋     | 172/363 [00:03<00:04, 42.69it/s]
Loading 0:  49%|████▉     | 177/363 [00:04<00:04, 42.35it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:03, 47.30it/s]
Loading 0:  52%|█████▏    | 190/363 [00:04<00:03, 45.66it/s]
Loading 0:  54%|█████▎    | 195/363 [00:04<00:03, 44.40it/s]
Loading 0:  56%|█████▌    | 202/363 [00:04<00:03, 48.60it/s]
Loading 0:  57%|█████▋    | 208/363 [00:04<00:03, 46.55it/s]
Loading 0:  59%|█████▊    | 213/363 [00:04<00:03, 44.22it/s]
Loading 0:  61%|██████    | 220/363 [00:04<00:02, 50.00it/s]
Loading 0:  62%|██████▏   | 226/363 [00:05<00:04, 32.27it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:03, 33.20it/s]
Loading 0:  65%|██████▌   | 237/363 [00:05<00:03, 37.56it/s]
Loading 0:  67%|██████▋   | 242/363 [00:05<00:03, 37.34it/s]
Loading 0:  68%|██████▊   | 247/363 [00:05<00:02, 39.01it/s]
Loading 0:  69%|██████▉   | 252/363 [00:05<00:02, 39.91it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:03, 32.02it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 37.97it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 37.17it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:02, 37.74it/s]
Loading 0:  77%|███████▋  | 280/363 [00:06<00:02, 38.38it/s]
Loading 0:  78%|███████▊  | 284/363 [00:06<00:02, 35.18it/s]
Loading 0:  80%|████████  | 291/363 [00:06<00:01, 41.12it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 42.02it/s]
Loading 0:  83%|████████▎ | 302/363 [00:07<00:01, 46.33it/s]
Loading 0:  85%|████████▍ | 307/363 [00:14<00:22,  2.54it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:14,  3.46it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:07,  5.52it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:04,  7.45it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:03,  9.45it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 13.32it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:01, 16.76it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 19.99it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 26.23it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 29.93it/s]
                                                            
Job jic062-orpo-v0-6-nemo-v1-mkmlizer completed after 114.79s with status: succeeded
Stopping job with name jic062-orpo-v0-6-nemo-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.36s
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 jic062-orpo-v0-6-nemo-v1
Waiting for inference service jic062-orpo-v0-6-nemo-v1 to be ready
Failed to get response for submission sao10k-mn-12b-lyra-v4a1_v12: ('http://sao10k-mn-12b-lyra-v4a1-v12-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:33888->127.0.0.1:8080: read: connection reset by peer\n')
Inference service jic062-orpo-v0-6-nemo-v1 ready after 110.50850987434387s
Pipeline stage MKMLDeployer completed in 111.32s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3310022354125977s
Received healthy response to inference request in 1.929380178451538s
Received healthy response to inference request in 1.737119436264038s
Received healthy response to inference request in 1.7263975143432617s
Received healthy response to inference request in 1.7607600688934326s
5 requests
0 failed requests
5th percentile: 1.728541898727417
10th percentile: 1.7306862831115724
20th percentile: 1.7349750518798828
30th percentile: 1.741847562789917
40th percentile: 1.7513038158416747
50th percentile: 1.7607600688934326
60th percentile: 1.8282081127166747
70th percentile: 1.895656156539917
80th percentile: 2.00970458984375
90th percentile: 2.170353412628174
95th percentile: 2.2506778240203857
99th percentile: 2.3149373531341553
mean time: 1.8969318866729736
Pipeline stage StressChecker completed in 11.30s
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 6.19s
Shutdown handler de-registered
jic062-orpo-v0-6-nemo_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 2552.55s
Shutdown handler de-registered
jic062-orpo-v0-6-nemo_v1 status is now inactive due to auto deactivation removed underperforming models
jic062-orpo-v0-6-nemo_v1 status is now torndown due to DeploymentManager action