submission_id: jellywibble-lora-120k-pr_7199_v3
developer_uid: Jellywibble
status: inactive
model_repo: Jellywibble/lora_120k_pref_data_ep3_stacked_elo_only
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
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: {'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: 2024-07-09T07:16:42+00:00
model_name: nitral-ai-hathor-l3-8b-v-01_v1
model_group: Jellywibble/lora_120k_pr
num_battles: 30416
num_wins: 18393
celo_rating: 1271.14
alignment_score: None
alignment_samples: 0
propriety_score: 0.7097400077609624
propriety_total_count: 5154.0
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: None
language_model: Jellywibble/lora_120k_pref_data_ep3_stacked_elo_only
model_size: 8B
reward_model: ChaiML/gpt2_xl_pairwise_89m_step_347634
us_pacific_date: 2024-07-09
win_ratio: 0.6047146238821672
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name jellywibble-lora-120k-pr-7199-v3-mkmlizer
Waiting for job on jellywibble-lora-120k-pr-7199-v3-mkmlizer to finish
jellywibble-lora-120k-pr-7199-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jellywibble-lora-120k-pr-7199-v3-mkmlizer: ║ _____ __ __ ║
jellywibble-lora-120k-pr-7199-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
jellywibble-lora-120k-pr-7199-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
jellywibble-lora-120k-pr-7199-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
jellywibble-lora-120k-pr-7199-v3-mkmlizer: ║ /___/ ║
jellywibble-lora-120k-pr-7199-v3-mkmlizer: ║ ║
jellywibble-lora-120k-pr-7199-v3-mkmlizer: ║ Version: 0.8.14 ║
jellywibble-lora-120k-pr-7199-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
jellywibble-lora-120k-pr-7199-v3-mkmlizer: ║ https://mk1.ai ║
jellywibble-lora-120k-pr-7199-v3-mkmlizer: ║ ║
jellywibble-lora-120k-pr-7199-v3-mkmlizer: ║ The license key for the current software has been verified as ║
jellywibble-lora-120k-pr-7199-v3-mkmlizer: ║ belonging to: ║
jellywibble-lora-120k-pr-7199-v3-mkmlizer: ║ ║
jellywibble-lora-120k-pr-7199-v3-mkmlizer: ║ Chai Research Corp. ║
jellywibble-lora-120k-pr-7199-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
jellywibble-lora-120k-pr-7199-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
jellywibble-lora-120k-pr-7199-v3-mkmlizer: ║ ║
jellywibble-lora-120k-pr-7199-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jellywibble-lora-120k-pr-7199-v3-mkmlizer: Downloaded to shared memory in 49.776s
jellywibble-lora-120k-pr-7199-v3-mkmlizer: quantizing model to /dev/shm/model_cache
jellywibble-lora-120k-pr-7199-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jellywibble-lora-120k-pr-7199-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:06, 44.40it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:04, 64.21it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:03, 70.94it/s] Loading 0: 10%|▉ | 29/291 [00:00<00:03, 73.40it/s] Loading 0: 13%|█▎ | 37/291 [00:00<00:08, 30.29it/s] Loading 0: 15%|█▍ | 43/291 [00:01<00:07, 34.53it/s] Loading 0: 17%|█▋ | 50/291 [00:01<00:06, 38.79it/s] Loading 0: 20%|█▉ | 58/291 [00:01<00:04, 47.06it/s] Loading 0: 23%|██▎ | 66/291 [00:01<00:04, 54.40it/s] Loading 0: 25%|██▌ | 73/291 [00:01<00:03, 57.58it/s] Loading 0: 27%|██▋ | 80/291 [00:01<00:06, 31.21it/s] Loading 0: 30%|██▉ | 86/291 [00:02<00:05, 34.53it/s] Loading 0: 32%|███▏ | 92/291 [00:02<00:05, 37.69it/s] Loading 0: 35%|███▍ | 101/291 [00:02<00:04, 44.69it/s] Loading 0: 37%|███▋ | 109/291 [00:02<00:03, 51.91it/s] Loading 0: 40%|███▉ | 116/291 [00:02<00:03, 56.01it/s] Loading 0: 43%|████▎ | 125/291 [00:02<00:02, 64.26it/s] Loading 0: 46%|████▌ | 133/291 [00:03<00:04, 35.06it/s] Loading 0: 48%|████▊ | 139/291 [00:03<00:04, 35.52it/s] Loading 0: 51%|█████ | 147/291 [00:03<00:03, 42.14it/s] Loading 0: 53%|█████▎ | 153/291 [00:03<00:03, 44.91it/s] Loading 0: 55%|█████▍ | 159/291 [00:03<00:03, 37.76it/s] Loading 0: 57%|█████▋ | 166/291 [00:03<00:02, 43.74it/s] Loading 0: 60%|█████▉ | 174/291 [00:03<00:02, 50.98it/s] Loading 0: 62%|██████▏ | 181/291 [00:04<00:02, 54.89it/s] Loading 0: 65%|██████▍ | 188/291 [00:04<00:03, 29.64it/s] Loading 0: 66%|██████▋ | 193/291 [00:04<00:03, 32.00it/s] Loading 0: 69%|██████▉ | 202/291 [00:04<00:02, 39.82it/s] Loading 0: 73%|███████▎ | 211/291 [00:04<00:01, 46.39it/s] Loading 0: 76%|███████▌ | 220/291 [00:05<00:01, 51.60it/s] Loading 0: 78%|███████▊ | 227/291 [00:05<00:01, 55.45it/s] Loading 0: 80%|████████ | 234/291 [00:05<00:01, 32.40it/s] Loading 0: 82%|████████▏ | 239/291 [00:05<00:01, 34.76it/s] Loading 0: 85%|████████▌ | 248/291 [00:05<00:01, 42.28it/s] Loading 0: 88%|████████▊ | 256/291 [00:05<00:00, 49.48it/s] Loading 0: 91%|█████████ | 265/291 [00:06<00:00, 54.56it/s] Loading 0: 94%|█████████▍| 274/291 [00:06<00:00, 58.21it/s] Loading 0: 97%|█████████▋| 282/291 [00:06<00:00, 62.81it/s] Loading 0: 99%|█████████▉| 289/291 [00:13<00:00, 3.54it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
jellywibble-lora-120k-pr-7199-v3-mkmlizer: quantized model in 32.160s
jellywibble-lora-120k-pr-7199-v3-mkmlizer: Processed model Jellywibble/lora_120k_pref_data_ep3_stacked_elo_only in 81.936s
jellywibble-lora-120k-pr-7199-v3-mkmlizer: creating bucket guanaco-mkml-models
jellywibble-lora-120k-pr-7199-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jellywibble-lora-120k-pr-7199-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jellywibble-lora-120k-pr-7199-v3
jellywibble-lora-120k-pr-7199-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jellywibble-lora-120k-pr-7199-v3/tokenizer_config.json
jellywibble-lora-120k-pr-7199-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jellywibble-lora-120k-pr-7199-v3/config.json
jellywibble-lora-120k-pr-7199-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jellywibble-lora-120k-pr-7199-v3/special_tokens_map.json
jellywibble-lora-120k-pr-7199-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jellywibble-lora-120k-pr-7199-v3/tokenizer.json
jellywibble-lora-120k-pr-7199-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jellywibble-lora-120k-pr-7199-v3/flywheel_model.0.safetensors
jellywibble-lora-120k-pr-7199-v3-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
jellywibble-lora-120k-pr-7199-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
jellywibble-lora-120k-pr-7199-v3-mkmlizer: warnings.warn(
jellywibble-lora-120k-pr-7199-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
jellywibble-lora-120k-pr-7199-v3-mkmlizer: warnings.warn(
jellywibble-lora-120k-pr-7199-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
jellywibble-lora-120k-pr-7199-v3-mkmlizer: warnings.warn(
jellywibble-lora-120k-pr-7199-v3-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.
jellywibble-lora-120k-pr-7199-v3-mkmlizer: warnings.warn(
jellywibble-lora-120k-pr-7199-v3-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:06<00:06, 6.67s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 3.92s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.33s/it]
jellywibble-lora-120k-pr-7199-v3-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 1.61it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.64it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.41it/s]
jellywibble-lora-120k-pr-7199-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jellywibble-lora-120k-pr-7199-v3-mkmlizer: Saving duration: 2.153s
jellywibble-lora-120k-pr-7199-v3-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.316s
jellywibble-lora-120k-pr-7199-v3-mkmlizer: creating bucket guanaco-reward-models
jellywibble-lora-120k-pr-7199-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jellywibble-lora-120k-pr-7199-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jellywibble-lora-120k-pr-7199-v3_reward
jellywibble-lora-120k-pr-7199-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jellywibble-lora-120k-pr-7199-v3_reward/config.json
jellywibble-lora-120k-pr-7199-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jellywibble-lora-120k-pr-7199-v3_reward/special_tokens_map.json
jellywibble-lora-120k-pr-7199-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jellywibble-lora-120k-pr-7199-v3_reward/tokenizer_config.json
jellywibble-lora-120k-pr-7199-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jellywibble-lora-120k-pr-7199-v3_reward/vocab.json
jellywibble-lora-120k-pr-7199-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jellywibble-lora-120k-pr-7199-v3_reward/merges.txt
jellywibble-lora-120k-pr-7199-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jellywibble-lora-120k-pr-7199-v3_reward/tokenizer.json
Job jellywibble-lora-120k-pr-7199-v3-mkmlizer completed after 124.49s with status: succeeded
Stopping job with name jellywibble-lora-120k-pr-7199-v3-mkmlizer
Pipeline stage MKMLizer completed in 125.37s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service jellywibble-lora-120k-pr-7199-v3
Waiting for inference service jellywibble-lora-120k-pr-7199-v3 to be ready
Inference service jellywibble-lora-120k-pr-7199-v3 ready after 50.226728439331055s
Pipeline stage ISVCDeployer completed in 57.37s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3680076599121094s
Received healthy response to inference request in 1.5917487144470215s
Received healthy response to inference request in 1.5465309619903564s
Received healthy response to inference request in 1.5170373916625977s
Received healthy response to inference request in 1.6171984672546387s
5 requests
0 failed requests
5th percentile: 1.5229361057281494
10th percentile: 1.5288348197937012
20th percentile: 1.5406322479248047
30th percentile: 1.5555745124816895
40th percentile: 1.5736616134643555
50th percentile: 1.5917487144470215
60th percentile: 1.6019286155700683
70th percentile: 1.6121085166931153
80th percentile: 1.767360305786133
90th percentile: 2.067683982849121
95th percentile: 2.217845821380615
99th percentile: 2.3379752922058104
mean time: 1.7281046390533448
Pipeline stage StressChecker completed in 9.32s
jellywibble-lora-120k-pr_7199_v3 status is now deployed due to DeploymentManager action
jellywibble-lora-120k-pr_7199_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics