submission_id: chaiml-sao10k-l3-rp-v3-3_v54
developer_uid: robert_irvine
alignment_samples: 0
best_of: 4
celo_rating: 1163.78
display_name: chaiml-sao10k-l3-rp-v3-3_v54
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': 4, '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_v54
model_num_parameters: 8030261248.0
model_repo: ChaiML/sao10k-l3-rp-v3-3
model_size: 8B
num_battles: 12000
num_wins: 5410
propriety_score: 0.705242334322453
propriety_total_count: 1011.0
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: 2024-07-24T02:53:34+00:00
us_pacific_date: 2024-07-23
win_ratio: 0.4508333333333333
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v54-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
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Failed to get response for submission blend_dunet_2024-07-19: ('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-v54-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer: ║ _____ __ __ ║
chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer: ║ /___/ ║
chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer: ║ Version: 0.9.5.post3 ║
chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer: ║ https://mk1.ai ║
chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer: ║ belonging to: ║
chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer: ║ Chai Research Corp. ║
chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer: Downloaded to shared memory in 23.397s
chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxi403z3l, device:0
chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:41, 2.43s/it] Loading 0: 4%|▍ | 13/291 [00:04<01:18, 3.54it/s] Loading 0: 8%|▊ | 24/291 [00:05<00:34, 7.71it/s] Loading 0: 14%|█▍ | 41/291 [00:05<00:15, 16.16it/s] Loading 0: 19%|█▉ | 56/291 [00:05<00:09, 25.49it/s] Loading 0: 24%|██▎ | 69/291 [00:05<00:07, 28.01it/s] Loading 0: 29%|██▉ | 85/291 [00:05<00:05, 40.31it/s] Loading 0: 33%|███▎ | 97/291 [00:05<00:03, 49.30it/s] Loading 0: 39%|███▉ | 113/291 [00:05<00:02, 63.95it/s] Loading 0: 45%|████▍ | 130/291 [00:06<00:02, 79.77it/s] Loading 0: 49%|████▉ | 144/291 [00:06<00:01, 89.37it/s] Loading 0: 54%|█████▍ | 158/291 [00:06<00:01, 99.17it/s] Loading 0: 59%|█████▉ | 172/291 [00:06<00:01, 74.33it/s] Loading 0: 64%|██████▎ | 185/291 [00:06<00:01, 83.77it/s] Loading 0: 69%|██████▉ | 202/291 [00:06<00:00, 98.77it/s] Loading 0: 74%|███████▍ | 215/291 [00:06<00:00, 105.40it/s] Loading 0: 79%|███████▉ | 230/291 [00:07<00:00, 112.27it/s] Loading 0: 84%|████████▍ | 245/291 [00:07<00:00, 121.45it/s] Loading 0: 89%|████████▉ | 259/291 [00:07<00:00, 121.09it/s] Loading 0: 93%|█████████▎| 272/291 [00:07<00:00, 81.70it/s] Loading 0: 98%|█████████▊| 284/291 [00:07<00:00, 89.01it/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-v54-mkmlizer: quantized model in 22.581s
chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer: Processed model ChaiML/sao10k-l3-rp-v3-3 in 45.978s
chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v54
chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v54/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v54/config.json
chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v54/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v54/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v54/flywheel_model.0.safetensors
chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer: loading reward model from rirv938/gpt2_improves_the_story_512
chaiml-sao10k-l3-rp-v3-3-v54-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-v54-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v54-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-v54-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v54-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-v54-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:05<00:05, 5.72s/it] Downloading shards: 100%|██████████| 2/2 [00:11<00:00, 5.73s/it] Downloading shards: 100%|██████████| 2/2 [00:11<00:00, 5.73s/it]
chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.41it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.87it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.55it/s]
chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer: Saving duration: 1.345s
chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer: Processed model rirv938/gpt2_improves_the_story_512 in 15.194s
chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer: creating bucket guanaco-reward-models
chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v54_reward/reward.tensors
Job chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer completed after 542.88s with status: succeeded
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v54-mkmlizer
Pipeline stage MKMLizer completed in 543.84s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-sao10k-l3-rp-v3-3-v54
Waiting for inference service chaiml-sao10k-l3-rp-v3-3-v54 to be ready
Inference service chaiml-sao10k-l3-rp-v3-3-v54 ready after 40.39262247085571s
Pipeline stage ISVCDeployer completed in 42.22s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.114584445953369s
Received healthy response to inference request in 1.1397013664245605s
Received healthy response to inference request in 1.1431763172149658s
Received healthy response to inference request in 1.1153907775878906s
Received healthy response to inference request in 0.8368768692016602s
5 requests
0 failed requests
5th percentile: 0.8925796508789062
10th percentile: 0.9482824325561523
20th percentile: 1.0596879959106444
30th percentile: 1.1202528953552247
40th percentile: 1.1299771308898925
50th percentile: 1.1397013664245605
60th percentile: 1.1410913467407227
70th percentile: 1.1424813270568848
80th percentile: 1.3374579429626468
90th percentile: 1.726021194458008
95th percentile: 1.9203028202056882
99th percentile: 2.075728120803833
mean time: 1.2699459552764893
Pipeline stage StressChecker completed in 7.03s
chaiml-sao10k-l3-rp-v3-3_v54 status is now deployed due to DeploymentManager action
chaiml-sao10k-l3-rp-v3-3_v54 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-sao10k-l3-rp-v3-3_v54
Running pipeline stage ISVCDeleter
Checking if service chaiml-sao10k-l3-rp-v3-3-v54 is running
Tearing down inference service chaiml-sao10k-l3-rp-v3-3-v54
Service chaiml-sao10k-l3-rp-v3-3-v54 has been torndown
Pipeline stage ISVCDeleter completed in 5.23s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v54/config.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v54/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v54/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v54/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v54/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v54_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v54_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v54_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v54_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v54_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v54_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v54_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.28s
chaiml-sao10k-l3-rp-v3-3_v54 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics