submission_id: chaiml-sao10k-l3-rp-v3-3_v58
developer_uid: robert_irvine
alignment_samples: 0
best_of: 4
celo_rating: 1152.03
display_name: chaiml-sao10k-l3-rp-v3-3_v58
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_v58
model_num_parameters: 8030261248.0
model_repo: ChaiML/sao10k-l3-rp-v3-3
model_size: 8B
num_battles: 25952
num_wins: 11691
propriety_score: 0.7507029053420806
propriety_total_count: 1067.0
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_rep_weakly_disagree_512
status: torndown
submission_type: basic
timestamp: 2024-07-24T15:28:24+00:00
us_pacific_date: 2024-07-24
win_ratio: 0.4504855117139334
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer to finish
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: ║ _____ __ __ ║
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: ║ /___/ ║
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: ║ Version: 0.9.6 ║
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: ║ https://mk1.ai ║
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: ║ belonging to: ║
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: ║ Chai Research Corp. ║
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission blend_kobem_2024-07-23: ('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-v58-mkmlizer: Downloaded to shared memory in 22.221s
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmprogr_fps, device:0
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:36, 2.41s/it] Loading 0: 2%|▏ | 6/291 [00:04<03:05, 1.54it/s] Loading 0: 4%|▍ | 13/291 [00:05<01:06, 4.20it/s] Loading 0: 6%|▌ | 17/291 [00:05<00:45, 6.09it/s] Loading 0: 8%|▊ | 24/291 [00:05<00:26, 10.08it/s] Loading 0: 11%|█ | 32/291 [00:05<00:16, 16.17it/s] Loading 0: 13%|█▎ | 38/291 [00:05<00:12, 19.94it/s] Loading 0: 15%|█▍ | 43/291 [00:05<00:10, 23.46it/s] Loading 0: 17%|█▋ | 50/291 [00:05<00:07, 30.36it/s] Loading 0: 19%|█▉ | 56/291 [00:05<00:07, 32.43it/s] Loading 0: 21%|██ | 61/291 [00:06<00:08, 25.92it/s] Loading 0: 23%|██▎ | 68/291 [00:06<00:06, 32.72it/s] Loading 0: 25%|██▌ | 74/291 [00:06<00:06, 34.73it/s] Loading 0: 27%|██▋ | 79/291 [00:06<00:05, 36.92it/s] Loading 0: 30%|██▉ | 86/291 [00:06<00:04, 42.57it/s] Loading 0: 31%|███▏ | 91/291 [00:06<00:04, 43.42it/s] Loading 0: 33%|███▎ | 96/291 [00:07<00:05, 38.56it/s] Loading 0: 36%|███▌ | 104/291 [00:07<00:03, 47.31it/s] Loading 0: 38%|███▊ | 110/291 [00:07<00:03, 45.72it/s] Loading 0: 40%|███▉ | 115/291 [00:07<00:03, 45.46it/s] Loading 0: 42%|████▏ | 122/291 [00:07<00:03, 50.38it/s] Loading 0: 44%|████▍ | 128/291 [00:07<00:03, 46.43it/s] Loading 0: 46%|████▌ | 133/291 [00:07<00:03, 45.85it/s] Loading 0: 48%|████▊ | 140/291 [00:07<00:02, 50.76it/s] Loading 0: 50%|█████ | 146/291 [00:08<00:03, 44.79it/s] Loading 0: 52%|█████▏ | 151/291 [00:08<00:03, 43.72it/s] Loading 0: 54%|█████▍ | 158/291 [00:08<00:02, 49.16it/s] Loading 0: 56%|█████▋ | 164/291 [00:08<00:02, 45.81it/s] Loading 0: 58%|█████▊ | 169/291 [00:08<00:03, 31.20it/s] Loading 0: 60%|██████ | 176/291 [00:08<00:03, 37.78it/s] Loading 0: 63%|██████▎ | 182/291 [00:08<00:02, 38.52it/s] Loading 0: 64%|██████▍ | 187/291 [00:09<00:02, 39.97it/s] Loading 0: 67%|██████▋ | 194/291 [00:09<00:02, 46.19it/s] Loading 0: 69%|██████▊ | 200/291 [00:09<00:02, 43.71it/s] Loading 0: 70%|███████ | 205/291 [00:09<00:01, 43.75it/s] Loading 0: 73%|███████▎ | 212/291 [00:09<00:01, 49.49it/s] Loading 0: 75%|███████▍ | 218/291 [00:09<00:01, 45.13it/s] Loading 0: 77%|███████▋ | 223/291 [00:09<00:01, 42.84it/s] Loading 0: 79%|███████▉ | 230/291 [00:09<00:01, 47.54it/s] Loading 0: 81%|████████ | 236/291 [00:10<00:01, 43.57it/s] Loading 0: 83%|████████▎ | 241/291 [00:10<00:01, 43.25it/s] Loading 0: 85%|████████▌ | 248/291 [00:10<00:00, 48.25it/s] Loading 0: 87%|████████▋ | 253/291 [00:10<00:00, 47.92it/s] Loading 0: 89%|████████▊ | 258/291 [00:10<00:00, 40.34it/s] Loading 0: 91%|█████████▏| 266/291 [00:10<00:00, 33.60it/s] Loading 0: 93%|█████████▎| 272/291 [00:11<00:00, 34.15it/s] Loading 0: 95%|█████████▍| 276/291 [00:11<00:00, 33.81it/s] Loading 0: 98%|█████████▊| 284/291 [00:11<00:00, 42.44it/s] Loading 0: 100%|█████████▉| 290/291 [00:11<00:00, 40.46it/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-v58-mkmlizer: quantized model in 26.581s
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: Processed model ChaiML/sao10k-l3-rp-v3-3 in 48.803s
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v58
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v58/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v58/flywheel_model.0.safetensors
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: loading reward model from rirv938/gpt2_rep_weakly_disagree_512
chaiml-sao10k-l3-rp-v3-3-v58-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-v58-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v58-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-v58-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v58-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-v58-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:05<00:05, 5.89s/it] Downloading shards: 100%|██████████| 2/2 [00:09<00:00, 4.45s/it] Downloading shards: 100%|██████████| 2/2 [00:09<00:00, 4.67s/it]
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.40it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.90it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.56it/s]
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: Saving duration: 1.332s
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: Processed model rirv938/gpt2_rep_weakly_disagree_512 in 14.280s
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: creating bucket guanaco-reward-models
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v58_reward
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v58_reward/config.json
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v58_reward/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v58_reward/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v58_reward/merges.txt
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v58_reward/vocab.json
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v58_reward/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v58_reward/reward.tensors
Job chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer completed after 106.2s with status: succeeded
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v58-mkmlizer
Pipeline stage MKMLizer completed in 107.25s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-sao10k-l3-rp-v3-3-v58
Waiting for inference service chaiml-sao10k-l3-rp-v3-3-v58 to be ready
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\'"}')
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\'"}')
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\'"}')
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\'"}')
Inference service chaiml-sao10k-l3-rp-v3-3-v58 ready after 352.8085718154907s
Pipeline stage ISVCDeployer completed in 354.35s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9104888439178467s
%s, retrying in %s seconds...
%s, retrying in %s seconds...
Received healthy response to inference request in 18.78159523010254s
Received healthy response to inference request in 1.129852056503296s
Received healthy response to inference request in 1.126103401184082s
Received healthy response to inference request in 1.1079142093658447s
Received healthy response to inference request in 1.0891358852386475s
5 requests
0 failed requests
5th percentile: 1.092891550064087
10th percentile: 1.0966472148895263
20th percentile: 1.1041585445404052
30th percentile: 1.1115520477294922
40th percentile: 1.118827724456787
50th percentile: 1.126103401184082
60th percentile: 1.1276028633117676
70th percentile: 1.1291023254394532
80th percentile: 4.660200691223148
90th percentile: 11.720897960662843
95th percentile: 15.251246595382687
99th percentile: 18.07552550315857
mean time: 4.646920156478882
Pipeline stage StressChecker completed in 66.16s
chaiml-sao10k-l3-rp-v3-3_v58 status is now deployed due to DeploymentManager action
chaiml-sao10k-l3-rp-v3-3_v58 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-sao10k-l3-rp-v3-3_v58
Running pipeline stage ISVCDeleter
Checking if service chaiml-sao10k-l3-rp-v3-3-v58 is running
Tearing down inference service chaiml-sao10k-l3-rp-v3-3-v58
Service chaiml-sao10k-l3-rp-v3-3-v58 has been torndown
Pipeline stage ISVCDeleter completed in 4.97s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v58/config.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v58/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v58/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v58/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v58/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v58_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v58_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v58_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v58_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v58_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v58_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v58_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.58s
chaiml-sao10k-l3-rp-v3-3_v58 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics