developer_uid: robert_irvine
submission_id: nitral-ai-hathor-l3-8b-v-01_v42
model_name: nitral-ai-hathor-l3-8b-v-01_v42
model_group: Nitral-AI/Hathor-L3-8B-v
status: torndown
timestamp: 2024-07-06T21:17:36+00:00
num_battles: 69144
num_wins: 35659
celo_rating: 1236.12
family_friendly_score: 0.0
submission_type: basic
model_repo: Nitral-AI/Hathor-L3-8B-v.01
model_architecture: LlamaForCausalLM
reward_repo: Jellywibble/CHAI_alignment_reward_model
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: nitral-ai-hathor-l3-8b-v-01_v42
is_internal_developer: True
language_model: Nitral-AI/Hathor-L3-8B-v.01
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-06
win_ratio: 0.5157208145319913
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
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}
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': '', 'prompt_template': '', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nitral-ai-hathor-l3-8b-v-01-v42-mkmlizer
Waiting for job on nitral-ai-hathor-l3-8b-v-01-v42-mkmlizer to finish
nitral-ai-hathor-l3-8b-v-01-v42-mkmlizer: Downloaded to shared memory in 53.027s
nitral-ai-hathor-l3-8b-v-01-v42-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-01-v42-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-01-v42-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:07<17:04,  3.55s/it]
Loading 0:   4%|▍         | 13/291 [00:07<01:53,  2.44it/s]
Loading 0:   8%|▊         | 23/291 [00:07<00:52,  5.10it/s]
Loading 0:  11%|█▏        | 33/291 [00:07<00:29,  8.65it/s]
Loading 0:  15%|█▌        | 44/291 [00:07<00:17, 13.80it/s]
Loading 0:  20%|█▉        | 58/291 [00:07<00:10, 22.08it/s]
Loading 0:  24%|██▎       | 69/291 [00:08<00:09, 23.04it/s]
Loading 0:  29%|██▉       | 85/291 [00:08<00:05, 34.63it/s]
Loading 0:  33%|███▎      | 95/291 [00:08<00:04, 41.52it/s]
Loading 0:  36%|███▌      | 105/291 [00:08<00:03, 48.82it/s]
Loading 0:  41%|████      | 119/291 [00:08<00:02, 63.42it/s]
Loading 0:  45%|████▌     | 131/291 [00:08<00:02, 71.31it/s]
Loading 0:  49%|████▉     | 142/291 [00:08<00:01, 78.59it/s]
Loading 0:  54%|█████▍    | 157/291 [00:08<00:01, 91.04it/s]
Loading 0:  58%|█████▊    | 169/291 [00:09<00:02, 58.31it/s]
Loading 0:  62%|██████▏   | 181/291 [00:09<00:01, 68.17it/s]
Loading 0:  66%|██████▌   | 191/291 [00:09<00:01, 74.02it/s]
Loading 0:  69%|██████▉   | 202/291 [00:09<00:01, 81.35it/s]
Loading 0:  73%|███████▎  | 213/291 [00:09<00:00, 84.36it/s]
Loading 0:  77%|███████▋  | 225/291 [00:09<00:00, 91.95it/s]
Loading 0:  82%|████████▏ | 238/291 [00:09<00:00, 98.76it/s]
Loading 0:  86%|████████▌ | 249/291 [00:10<00:00, 89.44it/s]
Loading 0:  90%|████████▉ | 261/291 [00:10<00:00, 95.73it/s]
Loading 0:  93%|█████████▎| 272/291 [00:10<00:00, 58.62it/s]
Loading 0:  98%|█████████▊| 284/291 [00:10<00:00, 67.16it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
nitral-ai-hathor-l3-8b-v-01-v42-mkmlizer: quantized model in 27.376s
nitral-ai-hathor-l3-8b-v-01-v42-mkmlizer: Processed model Nitral-AI/Hathor-L3-8B-v.01 in 80.403s
nitral-ai-hathor-l3-8b-v-01-v42-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-hathor-l3-8b-v-01-v42-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-hathor-l3-8b-v-01-v42-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v42
nitral-ai-hathor-l3-8b-v-01-v42-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v42/config.json
nitral-ai-hathor-l3-8b-v-01-v42-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v42/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v42-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v42/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v42-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v42/tokenizer.json
nitral-ai-hathor-l3-8b-v-01-v42-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v42/flywheel_model.0.safetensors
nitral-ai-hathor-l3-8b-v-01-v42-mkmlizer: loading reward model from Jellywibble/CHAI_alignment_reward_model
nitral-ai-hathor-l3-8b-v-01-v42-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.
nitral-ai-hathor-l3-8b-v-01-v42-mkmlizer:   warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v42-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.
nitral-ai-hathor-l3-8b-v-01-v42-mkmlizer:   warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v42-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.
nitral-ai-hathor-l3-8b-v-01-v42-mkmlizer:   warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v42-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-hathor-l3-8b-v-01-v42-mkmlizer: Saving duration: 0.167s
nitral-ai-hathor-l3-8b-v-01-v42-mkmlizer: Processed model Jellywibble/CHAI_alignment_reward_model in 22.272s
nitral-ai-hathor-l3-8b-v-01-v42-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-hathor-l3-8b-v-01-v42-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-hathor-l3-8b-v-01-v42-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v42_reward
nitral-ai-hathor-l3-8b-v-01-v42-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v42_reward/config.json
nitral-ai-hathor-l3-8b-v-01-v42-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v42_reward/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v42-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v42_reward/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v42-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v42_reward/merges.txt
nitral-ai-hathor-l3-8b-v-01-v42-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v42_reward/vocab.json
nitral-ai-hathor-l3-8b-v-01-v42-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v42_reward/tokenizer.json
nitral-ai-hathor-l3-8b-v-01-v42-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v42_reward/reward.tensors
Job nitral-ai-hathor-l3-8b-v-01-v42-mkmlizer completed after 266.26s with status: succeeded
Stopping job with name nitral-ai-hathor-l3-8b-v-01-v42-mkmlizer
Pipeline stage MKMLizer completed in 268.35s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.27s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-hathor-l3-8b-v-01-v42
Waiting for inference service nitral-ai-hathor-l3-8b-v-01-v42 to be ready
Inference service nitral-ai-hathor-l3-8b-v-01-v42 ready after 80.91779327392578s
Pipeline stage ISVCDeployer completed in 87.43s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9072060585021973s
Received healthy response to inference request in 1.4221932888031006s
Received healthy response to inference request in 1.516796588897705s
Received healthy response to inference request in 1.4048492908477783s
Received healthy response to inference request in 1.406707525253296s
5 requests
0 failed requests
5th percentile: 1.4052209377288818
10th percentile: 1.4055925846099853
20th percentile: 1.4063358783721924
30th percentile: 1.409804677963257
40th percentile: 1.4159989833831788
50th percentile: 1.4221932888031006
60th percentile: 1.4600346088409424
70th percentile: 1.4978759288787842
80th percentile: 1.5948784828186036
90th percentile: 1.7510422706604003
95th percentile: 1.8291241645812988
99th percentile: 1.8915896797180176
mean time: 1.5315505504608153
Pipeline stage StressChecker completed in 10.07s
nitral-ai-hathor-l3-8b-v-01_v42 status is now deployed due to DeploymentManager action
nitral-ai-hathor-l3-8b-v-01_v42 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of nitral-ai-hathor-l3-8b-v-01_v42
Running pipeline stage ISVCDeleter
Checking if service nitral-ai-hathor-l3-8b-v-01-v42 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 5.18s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key nitral-ai-hathor-l3-8b-v-01-v42/config.json from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v42/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v42/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v42/tokenizer.json from bucket guanaco-mkml-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v42/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key nitral-ai-hathor-l3-8b-v-01-v42_reward/config.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v42_reward/merges.txt from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v42_reward/reward.tensors from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v42_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v42_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v42_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key nitral-ai-hathor-l3-8b-v-01-v42_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.45s
nitral-ai-hathor-l3-8b-v-01_v42 status is now torndown due to DeploymentManager action