submission_id: nitral-ai-hathor-l3-8b-v-01_v4
developer_uid: Nitral-AI
status: inactive
model_repo: Nitral-AI/Hathor-L3-8B-v.01
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.25, 'top_p': 1.0, 'min_p': 0.03, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>', '<|end_header_id|>', '\n\n{user_name}'], '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: {'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: 2024-06-07T17:12:21+00:00
model_name: nitral-ai-hathor-l3-8b-v-01_v1
model_eval_status: success
model_group: Nitral-AI/Hathor-L3-8B-v
num_battles: 12746
num_wins: 6847
celo_rating: 1216.02
safety_score: 0.96
propriety_score: 0.6542491268917345
propriety_total_count: 859.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: nitral-ai-hathor-l3-8b-v-01_v1
ineligible_reason: propriety_total_count < 5000
language_model: Nitral-AI/Hathor-L3-8B-v.01
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-07
win_ratio: 0.5371881374548878
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer
Waiting for job on nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer to finish
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: ║ _____ __ __ ║
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: ║ /___/ ║
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: ║ Version: 0.8.14 ║
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: ║ https://mk1.ai ║
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: ║ belonging to: ║
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: warnings.warn(warning_message, FutureWarning)
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: Downloaded to shared memory in 21.777s
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<09:55, 2.06s/it] Loading 0: 5%|▌ | 15/291 [00:04<00:57, 4.82it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:20, 12.73it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:10, 22.73it/s] Loading 0: 22%|██▏ | 65/291 [00:04<00:08, 26.50it/s] Loading 0: 28%|██▊ | 81/291 [00:04<00:05, 37.90it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:03, 50.06it/s] Loading 0: 39%|███▉ | 114/291 [00:05<00:02, 66.79it/s] Loading 0: 45%|████▌ | 132/291 [00:05<00:01, 83.95it/s] Loading 0: 52%|█████▏ | 150/291 [00:05<00:01, 99.97it/s] Loading 0: 57%|█████▋ | 166/291 [00:05<00:01, 73.81it/s] Loading 0: 63%|██████▎ | 184/291 [00:05<00:01, 89.12it/s] Loading 0: 69%|██████▉ | 202/291 [00:05<00:00, 103.41it/s] Loading 0: 76%|███████▌ | 220/291 [00:06<00:00, 115.87it/s] Loading 0: 81%|████████ | 236/291 [00:06<00:00, 125.42it/s] Loading 0: 86%|████████▋ | 251/291 [00:06<00:00, 129.39it/s] Loading 0: 91%|█████████▏| 266/291 [00:06<00:00, 78.82it/s] Loading 0: 97%|█████████▋| 283/291 [00:06<00:00, 94.03it/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-v4-mkmlizer: quantized model in 19.053s
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: Processed model Nitral-AI/Hathor-L3-8B-v.01 in 41.878s
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v4
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v4/config.json
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v4/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v4/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v4/tokenizer.json
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v4/flywheel_model.0.safetensors
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:913: 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-v4-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:757: 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-v4-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v4-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.
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: /opt/conda/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: return self.fget.__get__(instance, owner)()
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: Saving duration: 0.288s
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.754s
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v4_reward
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v4_reward/config.json
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v4_reward/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v4_reward/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v4_reward/merges.txt
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v4_reward/vocab.json
nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v4_reward/tokenizer.json
Job nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer completed after 77.41s with status: succeeded
Stopping job with name nitral-ai-hathor-l3-8b-v-01-v4-mkmlizer
Pipeline stage MKMLizer completed in 81.68s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-hathor-l3-8b-v-01-v4
Waiting for inference service nitral-ai-hathor-l3-8b-v-01-v4 to be ready
Failed to get response for submission blend_kefet_2024-05-01: ('http://mistralai-mixtral-8x7b-3473-v33-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'upstream connect error or disconnect/reset before headers. reset reason: overflow')
Tearing down inference service nitral-ai-hathor-l3-8b-v-01-v4
%s, retrying in %s seconds...
Creating inference service nitral-ai-hathor-l3-8b-v-01-v4
Waiting for inference service nitral-ai-hathor-l3-8b-v-01-v4 to be ready
Inference service nitral-ai-hathor-l3-8b-v-01-v4 ready after 40.22934627532959s
Pipeline stage ISVCDeployer completed in 657.25s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1458568572998047s
Received healthy response to inference request in 4.599895477294922s
Received healthy response to inference request in 1.2862401008605957s
Received healthy response to inference request in 1.3039731979370117s
Received healthy response to inference request in 1.3361682891845703s
5 requests
0 failed requests
5th percentile: 1.2897867202758788
10th percentile: 1.2933333396911622
20th percentile: 1.3004265785217286
30th percentile: 1.3104122161865235
40th percentile: 1.3232902526855468
50th percentile: 1.3361682891845703
60th percentile: 1.660043716430664
70th percentile: 1.9839191436767576
80th percentile: 2.6366645812988287
90th percentile: 3.618280029296875
95th percentile: 4.109087753295898
99th percentile: 4.501733932495117
mean time: 2.134426784515381
Pipeline stage StressChecker completed in 11.30s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.04s
M-Eval Dataset for topic stay_in_character is loaded
nitral-ai-hathor-l3-8b-v-01_v4 status is now deployed due to DeploymentManager action
nitral-ai-hathor-l3-8b-v-01_v4 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics