submission_id: nousresearch-meta-llama_4941_v62
developer_uid: chai_backend_admin
status: inactive
model_repo: NousResearch/Meta-Llama-3-8B-Instruct
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
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}
reward_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}
timestamp: 2024-06-27T20:20:59+00:00
model_name: nousresearch-meta-llama_4941_v62
model_group: NousResearch/Meta-Llama-
num_battles: 14769
num_wins: 7751
celo_rating: 1199.63
propriety_score: 0.727462728159398
propriety_total_count: 7177.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: nousresearch-meta-llama_4941_v62
ineligible_reason: None
language_model: NousResearch/Meta-Llama-3-8B-Instruct
model_size: 8B
reward_model: ChaiML/gpt2_xl_pairwise_89m_step_347634
us_pacific_date: 2024-06-27
win_ratio: 0.5248154919087278
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nousresearch-meta-llama-4941-v62-mkmlizer
Waiting for job on nousresearch-meta-llama-4941-v62-mkmlizer to finish
nousresearch-meta-llama-4941-v62-mkmlizer: Downloaded to shared memory in 44.601s
nousresearch-meta-llama-4941-v62-mkmlizer: quantizing model to /dev/shm/model_cache
nousresearch-meta-llama-4941-v62-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nousresearch-meta-llama-4941-v62-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 120.02it/s] Loading 0: 10%|▉ | 28/291 [00:00<00:01, 136.09it/s] Loading 0: 14%|█▍ | 42/291 [00:00<00:02, 124.48it/s] Loading 0: 20%|█▉ | 57/291 [00:00<00:01, 132.17it/s] Loading 0: 24%|██▍ | 71/291 [00:00<00:01, 129.00it/s] Loading 0: 29%|██▉ | 84/291 [00:00<00:02, 72.74it/s] Loading 0: 33%|███▎ | 95/291 [00:01<00:02, 79.51it/s] Loading 0: 38%|███▊ | 111/291 [00:01<00:01, 97.19it/s] Loading 0: 42%|████▏ | 123/291 [00:01<00:01, 100.52it/s] Loading 0: 48%|████▊ | 139/291 [00:01<00:01, 110.48it/s] Loading 0: 53%|█████▎ | 153/291 [00:01<00:01, 118.00it/s] Loading 0: 57%|█████▋ | 166/291 [00:01<00:01, 119.06it/s] Loading 0: 62%|██████▏ | 180/291 [00:01<00:00, 124.38it/s] Loading 0: 66%|██████▋ | 193/291 [00:01<00:01, 75.41it/s] Loading 0: 71%|███████ | 207/291 [00:02<00:00, 87.75it/s] Loading 0: 76%|███████▌ | 220/291 [00:02<00:00, 95.13it/s] Loading 0: 81%|████████ | 235/291 [00:02<00:00, 107.74it/s] Loading 0: 85%|████████▌ | 248/291 [00:02<00:00, 107.23it/s] Loading 0: 91%|█████████ | 265/291 [00:02<00:00, 117.81it/s] Loading 0: 96%|█████████▌| 280/291 [00:02<00:00, 125.84it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
nousresearch-meta-llama-4941-v62-mkmlizer: quantized model in 23.237s
nousresearch-meta-llama-4941-v62-mkmlizer: Processed model NousResearch/Meta-Llama-3-8B-Instruct in 67.838s
nousresearch-meta-llama-4941-v62-mkmlizer: creating bucket guanaco-mkml-models
nousresearch-meta-llama-4941-v62-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nousresearch-meta-llama-4941-v62-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v62
nousresearch-meta-llama-4941-v62-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v62/config.json
nousresearch-meta-llama-4941-v62-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v62/special_tokens_map.json
nousresearch-meta-llama-4941-v62-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v62/tokenizer_config.json
nousresearch-meta-llama-4941-v62-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v62/tokenizer.json
nousresearch-meta-llama-4941-v62-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v62/flywheel_model.0.safetensors
nousresearch-meta-llama-4941-v62-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:468: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
nousresearch-meta-llama-4941-v62-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v62-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:10<00:10, 10.65s/it] Downloading shards: 100%|██████████| 2/2 [00:21<00:00, 10.59s/it] Downloading shards: 100%|██████████| 2/2 [00:21<00:00, 10.60s/it]
nousresearch-meta-llama-4941-v62-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 1.80it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.07it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.77it/s]
nousresearch-meta-llama-4941-v62-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nousresearch-meta-llama-4941-v62-mkmlizer: Saving duration: 1.706s
nousresearch-meta-llama-4941-v62-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 28.029s
nousresearch-meta-llama-4941-v62-mkmlizer: creating bucket guanaco-reward-models
nousresearch-meta-llama-4941-v62-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nousresearch-meta-llama-4941-v62-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nousresearch-meta-llama-4941-v62_reward
nousresearch-meta-llama-4941-v62-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v62_reward/special_tokens_map.json
nousresearch-meta-llama-4941-v62-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v62_reward/config.json
nousresearch-meta-llama-4941-v62-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v62_reward/tokenizer_config.json
nousresearch-meta-llama-4941-v62-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nousresearch-meta-llama-4941-v62_reward/merges.txt
nousresearch-meta-llama-4941-v62-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v62_reward/vocab.json
nousresearch-meta-llama-4941-v62-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v62_reward/tokenizer.json
Job nousresearch-meta-llama-4941-v62-mkmlizer completed after 473.34s with status: succeeded
Stopping job with name nousresearch-meta-llama-4941-v62-mkmlizer
Pipeline stage MKMLizer completed in 475.76s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.44s
Running pipeline stage ISVCDeployer
Creating inference service nousresearch-meta-llama-4941-v62
Waiting for inference service nousresearch-meta-llama-4941-v62 to be ready
Shutting down server chaiverse_console.server.app.
admin requested tearing down of nousresearch-meta-llama_4941_v62
Running pipeline stage ISVCDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage ISVCDeleter completed in 0.17s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key nousresearch-meta-llama-4941-v62/config.json from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4941-v62/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4941-v62/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4941-v62/tokenizer.json from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4941-v62/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key nousresearch-meta-llama-4941-v62_reward/config.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v62_reward/merges.txt from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v62_reward/reward.tensors from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v62_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v62_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v62_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v62_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.02s
nousresearch-meta-llama_4941_v62 status is now torndown due to DeploymentManager action
nousresearch-meta-llama_4941_v62 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics