submission_id: chaiml-sao10k-l3-rp-v3-3_v52
developer_uid: robert_irvine
alignment_samples: 0
best_of: 1
celo_rating: 1154.46
display_name: chaiml-sao10k-l3-rp-v3-3_v52
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>,', '<|eot_id|>,', '\n\n{user_name}'], 'max_input_tokens': 512, 'best_of': 1, 'max_output_tokens': 64, 'reward_max_token_input': 512}
is_internal_developer: True
language_model: ChaiML/sao10k-l3-rp-v3-3
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: ChaiML/sao10k-l3-rp-v3-3
model_name: chaiml-sao10k-l3-rp-v3-3_v52
model_num_parameters: 8030261248.0
model_repo: ChaiML/sao10k-l3-rp-v3-3
model_size: 8B
num_battles: 12152
num_wins: 5305
propriety_score: 0.7191709844559585
propriety_total_count: 965.0
ranking_group: single
reward_formatter: {'bot_template': 'Bot: {message}\n', 'memory_template': '', 'prompt_template': '', 'response_template': 'Bot:', 'truncate_by_message': False, 'user_template': 'User: {message}\n'}
reward_repo: rirv938/gpt2_improves_the_story_512
status: torndown
submission_type: basic
timestamp: 2024-07-24T02:53:16+00:00
us_pacific_date: 2024-07-23
win_ratio: 0.43655365371955235
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer to finish
Failed to get response for submission undi95-meta-llama-3-70b_6209_v18: ('http://undi95-meta-llama-3-70b-6209-v18-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"TypeError : SamplingParameters.__init__() got an unexpected keyword argument \'reward_max_tokens\'"}')
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: ║ _____ __ __ ║
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: ║ /___/ ║
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: ║ Version: 0.9.5.post3 ║
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: ║ https://mk1.ai ║
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: ║ belonging to: ║
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: ║ Chai Research Corp. ║
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: Downloaded to shared memory in 23.951s
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpng064mkl, device:0
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:54, 2.47s/it] Loading 0: 5%|▍ | 14/291 [00:05<01:13, 3.76it/s] Loading 0: 11%|█ | 31/291 [00:05<00:25, 10.13it/s] Loading 0: 15%|█▌ | 45/291 [00:05<00:14, 16.85it/s] Loading 0: 20%|██ | 59/291 [00:05<00:09, 25.29it/s] Loading 0: 25%|██▍ | 72/291 [00:05<00:07, 29.41it/s] Loading 0: 30%|██▉ | 86/291 [00:05<00:05, 40.10it/s] Loading 0: 35%|███▌ | 103/291 [00:05<00:03, 55.44it/s] Loading 0: 40%|███▉ | 116/291 [00:05<00:02, 66.26it/s] Loading 0: 45%|████▌ | 131/291 [00:06<00:01, 80.12it/s] Loading 0: 51%|█████ | 148/291 [00:06<00:01, 96.79it/s] Loading 0: 56%|█████▌ | 163/291 [00:06<00:01, 106.48it/s] Loading 0: 61%|██████ | 177/291 [00:06<00:01, 78.30it/s] Loading 0: 67%|██████▋ | 194/291 [00:06<00:01, 93.99it/s] Loading 0: 73%|███████▎ | 211/291 [00:06<00:00, 107.46it/s] Loading 0: 78%|███████▊ | 226/291 [00:06<00:00, 115.96it/s] Loading 0: 82%|████████▏ | 240/291 [00:07<00:00, 118.64it/s] Loading 0: 88%|████████▊ | 257/291 [00:07<00:00, 130.36it/s] Loading 0: 93%|█████████▎| 272/291 [00:07<00:00, 92.04it/s] Loading 0: 98%|█████████▊| 284/291 [00:07<00:00, 96.59it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: quantized model in 22.788s
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: Processed model ChaiML/sao10k-l3-rp-v3-3 in 46.740s
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v52
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v52/config.json
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v52/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v52/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v52/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v52/flywheel_model.0.safetensors
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:950: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: loading reward model from rirv938/gpt2_improves_the_story_512
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:778: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:469: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:05<00:05, 5.49s/it] Downloading shards: 100%|██████████| 2/2 [00:11<00:00, 5.66s/it] Downloading shards: 100%|██████████| 2/2 [00:11<00:00, 5.63s/it]
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.28it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.77it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.43it/s]
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: Saving duration: 1.354s
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: Processed model rirv938/gpt2_improves_the_story_512 in 14.317s
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: creating bucket guanaco-reward-models
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v52_reward
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v52_reward/config.json
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v52_reward/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v52_reward/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v52_reward/merges.txt
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v52_reward/vocab.json
chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v52_reward/tokenizer.json
Job chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer completed after 271.74s with status: succeeded
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v52-mkmlizer
Pipeline stage MKMLizer completed in 272.83s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-sao10k-l3-rp-v3-3-v52
Waiting for inference service chaiml-sao10k-l3-rp-v3-3-v52 to be ready
Inference service chaiml-sao10k-l3-rp-v3-3-v52 ready after 50.424676179885864s
Pipeline stage ISVCDeployer completed in 52.01s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.2703461647033691s
Received healthy response to inference request in 0.6268258094787598s
Received healthy response to inference request in 0.7424371242523193s
Received healthy response to inference request in 0.8346326351165771s
Received healthy response to inference request in 0.7190041542053223s
5 requests
0 failed requests
5th percentile: 0.6452614784240722
10th percentile: 0.6636971473693848
20th percentile: 0.7005684852600098
30th percentile: 0.7236907482147217
40th percentile: 0.7330639362335205
50th percentile: 0.7424371242523193
60th percentile: 0.7793153285980224
70th percentile: 0.8161935329437255
80th percentile: 0.9217753410339357
90th percentile: 1.0960607528686523
95th percentile: 1.1832034587860107
99th percentile: 1.2529176235198975
mean time: 0.8386491775512696
Pipeline stage StressChecker completed in 4.81s
chaiml-sao10k-l3-rp-v3-3_v52 status is now deployed due to DeploymentManager action
chaiml-sao10k-l3-rp-v3-3_v52 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-sao10k-l3-rp-v3-3_v52
Running pipeline stage ISVCDeleter
Checking if service chaiml-sao10k-l3-rp-v3-3-v52 is running
Tearing down inference service chaiml-sao10k-l3-rp-v3-3-v52
Service chaiml-sao10k-l3-rp-v3-3-v52 has been torndown
Pipeline stage ISVCDeleter completed in 4.39s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v52/config.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v52/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v52/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v52/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v52/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v52_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v52_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v52_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v52_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v52_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v52_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v52_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.44s
chaiml-sao10k-l3-rp-v3-3_v52 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics