submission_id: nousresearch-meta-llama_4941_v87
developer_uid: zonemercy
alignment_samples: 0
best_of: 1
celo_rating: 1117.62
display_name: meta-bo1-base
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}
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '<|user|>', '###'], 'max_input_tokens': 512, 'best_of': 1, 'max_output_tokens': 64, 'reward_max_token_input': 256}
is_internal_developer: True
language_model: NousResearch/Meta-Llama-3-8B-Instruct
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: NousResearch/Meta-Llama-
model_name: meta-bo1-base
model_num_parameters: 8030261248.0
model_repo: NousResearch/Meta-Llama-3-8B-Instruct
model_size: 8B
num_battles: 8802
num_wins: 3418
propriety_score: 0.7554945054945055
propriety_total_count: 1092.0
ranking_group: single
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: basic
timestamp: 2024-07-25T17:00:37+00:00
us_pacific_date: 2024-07-25
win_ratio: 0.3883208361735969
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nousresearch-meta-llama-4941-v87-mkmlizer
Waiting for job on nousresearch-meta-llama-4941-v87-mkmlizer to finish
Failed to get response for submission undi95-meta-llama-3-70b_6209_v27: ('http://undi95-meta-llama-3-70b-6209-v27-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission undi95-meta-llama-3-70b_6209_v29: ('http://undi95-meta-llama-3-70b-6209-v29-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission undi95-meta-llama-3-70b_6209_v27: ('http://undi95-meta-llama-3-70b-6209-v27-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission undi95-meta-llama-3-70b_6209_v27: ('http://undi95-meta-llama-3-70b-6209-v27-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission undi95-meta-llama-3-70b_6209_v29: ('http://undi95-meta-llama-3-70b-6209-v29-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission undi95-meta-llama-3-70b_6209_v27: ('http://undi95-meta-llama-3-70b-6209-v27-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission undi95-meta-llama-3-70b_6209_v29: ('http://undi95-meta-llama-3-70b-6209-v29-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission undi95-meta-llama-3-70b_6209_v27: ('http://undi95-meta-llama-3-70b-6209-v27-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission undi95-meta-llama-3-70b_6209_v27: ('http://undi95-meta-llama-3-70b-6209-v27-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
nousresearch-meta-llama-4941-v87-mkmlizer: Downloaded to shared memory in 22.159s
nousresearch-meta-llama-4941-v87-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmprmtz1xvb, device:0
nousresearch-meta-llama-4941-v87-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission undi95-meta-llama-3-70b_6209_v27: ('http://undi95-meta-llama-3-70b-6209-v27-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
nousresearch-meta-llama-4941-v87-mkmlizer: quantized model in 26.112s
nousresearch-meta-llama-4941-v87-mkmlizer: Processed model NousResearch/Meta-Llama-3-8B-Instruct in 48.271s
nousresearch-meta-llama-4941-v87-mkmlizer: creating bucket guanaco-mkml-models
nousresearch-meta-llama-4941-v87-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nousresearch-meta-llama-4941-v87-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v87
nousresearch-meta-llama-4941-v87-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v87/config.json
nousresearch-meta-llama-4941-v87-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v87/special_tokens_map.json
nousresearch-meta-llama-4941-v87-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v87/tokenizer_config.json
nousresearch-meta-llama-4941-v87-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v87/tokenizer.json
Failed to get response for submission undi95-meta-llama-3-70b_6209_v27: ('http://undi95-meta-llama-3-70b-6209-v27-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
nousresearch-meta-llama-4941-v87-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v87/flywheel_model.0.safetensors
nousresearch-meta-llama-4941-v87-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
nousresearch-meta-llama-4941-v87-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:08, 34.74it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:04, 57.06it/s] Loading 0: 7%|▋ | 20/291 [00:00<00:04, 55.72it/s] Loading 0: 9%|▉ | 26/291 [00:00<00:05, 52.92it/s] Loading 0: 11%|█ | 32/291 [00:00<00:05, 45.49it/s] Loading 0: 14%|█▍ | 41/291 [00:00<00:05, 48.21it/s] Loading 0: 17%|█▋ | 50/291 [00:00<00:04, 50.68it/s] Loading 0: 20%|██ | 59/291 [00:01<00:04, 52.04it/s] Loading 0: 23%|██▎ | 67/291 [00:01<00:03, 57.81it/s] Loading 0: 25%|██▌ | 74/291 [00:01<00:03, 55.67it/s] Loading 0: 27%|██▋ | 80/291 [00:01<00:03, 53.88it/s] Loading 0: 30%|██▉ | 86/291 [00:01<00:06, 34.08it/s] Loading 0: 32%|███▏ | 94/291 [00:01<00:04, 41.29it/s] Loading 0: 34%|███▍ | 100/291 [00:02<00:04, 40.15it/s] Loading 0: 36%|███▌ | 105/291 [00:02<00:04, 41.44it/s] Loading 0: 38%|███▊ | 112/291 [00:02<00:03, 47.56it/s] Loading 0: 41%|████ | 118/291 [00:02<00:03, 46.42it/s] Loading 0: 43%|████▎ | 124/291 [00:02<00:03, 47.48it/s] Loading 0: 45%|████▍ | 130/291 [00:02<00:03, 50.01it/s] Loading 0: 47%|████▋ | 136/291 [00:02<00:03, 46.83it/s] Loading 0: 48%|████▊ | 141/291 [00:02<00:03, 45.96it/s] Loading 0: 51%|█████ | 148/291 [00:03<00:02, 50.99it/s] Loading 0: 53%|█████▎ | 154/291 [00:03<00:02, 48.01it/s] Loading 0: 55%|█████▍ | 159/291 [00:03<00:02, 45.86it/s] Loading 0: 57%|█████▋ | 165/291 [00:03<00:02, 49.33it/s] Loading 0: 59%|█████▉ | 171/291 [00:03<00:02, 51.40it/s] Loading 0: 61%|██████ | 177/291 [00:03<00:02, 48.28it/s] Loading 0: 63%|██████▎ | 182/291 [00:03<00:02, 46.59it/s] Loading 0: 64%|██████▍ | 187/291 [00:04<00:02, 35.66it/s] Loading 0: 66%|██████▌ | 192/291 [00:04<00:02, 37.23it/s] Loading 0: 68%|██████▊ | 198/291 [00:04<00:02, 42.09it/s] Loading 0: 70%|██████▉ | 203/291 [00:04<00:02, 38.39it/s] Loading 0: 72%|███████▏ | 210/291 [00:04<00:01, 44.82it/s] Loading 0: 74%|███████▍ | 215/291 [00:04<00:01, 44.96it/s] Loading 0: 76%|███████▌ | 221/291 [00:04<00:01, 41.18it/s] Loading 0: 79%|███████▊ | 229/291 [00:04<00:01, 49.82it/s] Loading 0: 81%|████████ | 235/291 [00:05<00:01, 48.07it/s] Loading 0: 83%|████████▎ | 241/291 [00:05<00:01, 49.42it/s] Loading 0: 85%|████████▌ | 248/291 [00:05<00:00, 46.84it/s] Loading 0: 88%|████████▊ | 256/291 [00:05<00:00, 53.97it/s] Loading 0: 90%|█████████ | 262/291 [00:05<00:00, 50.90it/s] Loading 0: 92%|█████████▏| 268/291 [00:05<00:00, 50.62it/s] Loading 0: 95%|█████████▍| 275/291 [00:05<00:00, 47.59it/s] Loading 0: 97%|█████████▋| 282/291 [00:06<00:00, 46.01it/s] Loading 0: 99%|█████████▊| 287/291 [00:11<00:01, 3.58it/s] /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:957: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
nousresearch-meta-llama-4941-v87-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v87-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:785: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
nousresearch-meta-llama-4941-v87-mkmlizer: warnings.warn(
Failed to get response for submission undi95-meta-llama-3-70b_6209_v29: ('http://undi95-meta-llama-3-70b-6209-v29-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
nousresearch-meta-llama-4941-v87-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:05<00:05, 5.52s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.02s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.25s/it]
nousresearch-meta-llama-4941-v87-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.35it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.90it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.55it/s]
nousresearch-meta-llama-4941-v87-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nousresearch-meta-llama-4941-v87-mkmlizer: Saving duration: 1.364s
nousresearch-meta-llama-4941-v87-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 14.392s
nousresearch-meta-llama-4941-v87-mkmlizer: creating bucket guanaco-reward-models
nousresearch-meta-llama-4941-v87-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nousresearch-meta-llama-4941-v87-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nousresearch-meta-llama-4941-v87_reward
nousresearch-meta-llama-4941-v87-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v87_reward/special_tokens_map.json
nousresearch-meta-llama-4941-v87-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v87_reward/config.json
nousresearch-meta-llama-4941-v87-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v87_reward/tokenizer_config.json
nousresearch-meta-llama-4941-v87-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nousresearch-meta-llama-4941-v87_reward/merges.txt
nousresearch-meta-llama-4941-v87-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v87_reward/vocab.json
Failed to get response for submission undi95-meta-llama-3-70b_6209_v29: ('http://undi95-meta-llama-3-70b-6209-v29-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
nousresearch-meta-llama-4941-v87-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v87_reward/tokenizer.json
nousresearch-meta-llama-4941-v87-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nousresearch-meta-llama-4941-v87_reward/reward.tensors
Job nousresearch-meta-llama-4941-v87-mkmlizer completed after 229.45s with status: succeeded
Stopping job with name nousresearch-meta-llama-4941-v87-mkmlizer
Pipeline stage MKMLizer completed in 230.39s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service nousresearch-meta-llama-4941-v87
Waiting for inference service nousresearch-meta-llama-4941-v87 to be ready
Failed to get response for submission undi95-meta-llama-3-70b_6209_v29: ('http://undi95-meta-llama-3-70b-6209-v29-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission undi95-meta-llama-3-70b_6209_v29: ('http://undi95-meta-llama-3-70b-6209-v29-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission undi95-meta-llama-3-70b_6209_v27: ('http://undi95-meta-llama-3-70b-6209-v27-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission undi95-meta-llama-3-70b_6209_v29: ('http://undi95-meta-llama-3-70b-6209-v29-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Inference service nousresearch-meta-llama-4941-v87 ready after 70.63262248039246s
Pipeline stage ISVCDeployer completed in 72.43s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8985602855682373s
Failed to get response for submission undi95-meta-llama-3-70b_6209_v29: ('http://undi95-meta-llama-3-70b-6209-v29-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Received healthy response to inference request in 0.9415090084075928s
Received healthy response to inference request in 1.0645625591278076s
Received healthy response to inference request in 1.0617270469665527s
Received healthy response to inference request in 1.0354926586151123s
5 requests
0 failed requests
5th percentile: 0.9603057384490967
10th percentile: 0.9791024684906006
20th percentile: 1.0166959285736084
30th percentile: 1.0407395362854004
40th percentile: 1.0512332916259766
50th percentile: 1.0617270469665527
60th percentile: 1.0628612518310547
70th percentile: 1.0639954566955567
80th percentile: 1.2313621044158938
90th percentile: 1.5649611949920654
95th percentile: 1.7317607402801511
99th percentile: 1.86520037651062
mean time: 1.2003703117370605
Pipeline stage StressChecker completed in 6.67s
nousresearch-meta-llama_4941_v87 status is now deployed due to DeploymentManager action
nousresearch-meta-llama_4941_v87 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of nousresearch-meta-llama_4941_v87
Running pipeline stage ISVCDeleter
Checking if service nousresearch-meta-llama-4941-v87 is running
Tearing down inference service nousresearch-meta-llama-4941-v87
Service nousresearch-meta-llama-4941-v87 has been torndown
Pipeline stage ISVCDeleter completed in 4.70s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key nousresearch-meta-llama-4941-v87/config.json from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4941-v87/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4941-v87/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4941-v87/tokenizer.json from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4941-v87/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key nousresearch-meta-llama-4941-v87_reward/config.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v87_reward/merges.txt from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v87_reward/reward.tensors from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v87_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v87_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v87_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v87_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.42s
nousresearch-meta-llama_4941_v87 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics