submission_id: jellywibble-lora-120k-p_2801_v14
developer_uid: Jellywibble
alignment_samples: 0
best_of: 8
celo_rating: 1248.15
display_name: nitral-ai-hathor-l3-8b-v-01_v1
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}
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': 8, 'max_output_tokens': 64}
is_internal_developer: True
language_model: Jellywibble/lora_120k_pref_data_ep3_stacked_elo_alignment
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: Jellywibble/lora_120k_pr
model_name: nitral-ai-hathor-l3-8b-v-01_v1
model_num_parameters: 8030261248.0
model_repo: Jellywibble/lora_120k_pref_data_ep3_stacked_elo_alignment
model_size: 8B
num_battles: 90984
num_wins: 52075
propriety_score: 0.7337512794268168
propriety_total_count: 7816.0
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: 2024-07-14T03:52:27+00:00
us_pacific_date: 2024-07-13
win_ratio: 0.5723533808142091
Resubmit model
Running pipeline stage MKMLizer
Starting job with name jellywibble-lora-120k-p-2801-v14-mkmlizer
Waiting for job on jellywibble-lora-120k-p-2801-v14-mkmlizer to finish
jellywibble-lora-120k-p-2801-v14-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jellywibble-lora-120k-p-2801-v14-mkmlizer: ║     _____            __           __                                ║
jellywibble-lora-120k-p-2801-v14-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jellywibble-lora-120k-p-2801-v14-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jellywibble-lora-120k-p-2801-v14-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jellywibble-lora-120k-p-2801-v14-mkmlizer: ║       /___/                                                         ║
jellywibble-lora-120k-p-2801-v14-mkmlizer: ║                                                                     ║
jellywibble-lora-120k-p-2801-v14-mkmlizer: ║  Version: 0.9.5.post2                                               ║
jellywibble-lora-120k-p-2801-v14-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jellywibble-lora-120k-p-2801-v14-mkmlizer: ║  https://mk1.ai                                                     ║
jellywibble-lora-120k-p-2801-v14-mkmlizer: ║                                                                     ║
jellywibble-lora-120k-p-2801-v14-mkmlizer: ║  The license key for the current software has been verified as      ║
jellywibble-lora-120k-p-2801-v14-mkmlizer: ║  belonging to:                                                      ║
jellywibble-lora-120k-p-2801-v14-mkmlizer: ║                                                                     ║
jellywibble-lora-120k-p-2801-v14-mkmlizer: ║  Chai Research Corp.                                                ║
jellywibble-lora-120k-p-2801-v14-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jellywibble-lora-120k-p-2801-v14-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
jellywibble-lora-120k-p-2801-v14-mkmlizer: ║                                                                     ║
jellywibble-lora-120k-p-2801-v14-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jellywibble-lora-120k-p-2801-v14-mkmlizer: Downloaded to shared memory in 51.070s
jellywibble-lora-120k-p-2801-v14-mkmlizer: quantizing model to /dev/shm/model_cache
jellywibble-lora-120k-p-2801-v14-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.embed_tokens.weight torch.Size([139542528])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.0.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.0.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.0.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.0.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.0.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.0.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.1.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.1.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.1.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.1.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.1.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.1.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.2.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.2.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.2.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.2.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.2.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.2.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.3.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.3.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.3.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.3.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.3.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.3.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.4.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.4.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.4.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.4.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.4.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.4.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.5.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.5.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.5.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.5.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.5.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.5.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.6.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.6.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.6.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.6.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.6.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.6.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.7.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.7.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.7.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.7.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.7.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.7.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.8.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.8.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.8.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.10.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.10.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.10.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.10.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.10.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.10.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.11.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.11.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.11.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.11.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.11.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.11.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.12.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.12.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.12.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.12.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.12.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.12.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.13.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.13.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.13.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.13.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.13.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.13.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.14.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.14.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.8.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.8.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.8.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.9.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.9.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.9.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.9.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.9.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.9.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.14.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.14.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.14.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.14.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.15.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.15.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.15.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.15.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.15.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.15.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.16.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.16.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.16.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.16.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.16.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.16.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.17.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.17.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.17.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.17.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.17.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.17.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.18.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.18.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.18.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.18.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.18.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.18.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.19.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.19.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.19.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.19.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.19.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.19.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.20.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.20.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.20.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.20.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.20.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.20.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.21.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.21.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.21.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.21.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.21.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.21.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.22.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.22.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.22.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.22.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.22.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.22.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v14-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
                                                  

Loading 0:   0%|          | 1/291 [00:00<00:00, 471.22it/s]
                                                           

Loading 0:   1%|          | 2/291 [00:01<03:22,  1.43it/s]
Loading 0:   1%|          | 3/291 [00:01<02:14,  2.14it/s]
Loading 0:   1%|▏         | 4/291 [00:01<01:47,  2.67it/s]
                                                          

Loading 0:   1%|▏         | 4/291 [00:01<01:47,  2.67it/s]
                                                          

Loading 0:   2%|▏         | 5/291 [00:01<01:47,  2.67it/s]
                                                          

Loading 0:   2%|▏         | 7/291 [00:01<01:46,  2.67it/s]
Loading 0:   3%|▎         | 9/291 [00:01<00:36,  7.81it/s]
                                                          

Loading 0:   3%|▎         | 9/291 [00:01<00:36,  7.81it/s]
                                                          

Loading 0:   3%|▎         | 10/291 [00:01<00:35,  7.81it/s]
                                                           

Loading 0:   4%|▍         | 11/291 [00:01<00:35,  7.81it/s]
                                                           

Loading 0:   4%|▍         | 13/291 [00:01<00:35,  7.81it/s]
Loading 0:   5%|▍         | 14/291 [00:01<00:21, 12.90it/s]
                                                           

Loading 0:   5%|▍         | 14/291 [00:01<00:21, 12.90it/s]
                                                           

Loading 0:   5%|▌         | 16/291 [00:01<00:21, 12.90it/s]
                                                           

Loading 0:   6%|▌         | 18/291 [00:01<00:21, 12.90it/s]
                                                           

Loading 0:   7%|▋         | 19/291 [00:01<00:21, 12.90it/s]
                                                           

Loading 0:   7%|▋         | 20/291 [00:01<00:21, 12.90it/s]
Loading 0:   8%|▊         | 22/291 [00:01<00:11, 22.56it/s]
                                                           

Loading 0:   8%|▊         | 22/291 [00:02<00:11, 22.56it/s]
                                                           

Loading 0:   8%|▊         | 23/291 [00:02<00:11, 22.56it/s]
                                                           

Loading 0:   9%|▊         | 25/291 [00:02<00:11, 22.56it/s]
Loading 0:   9%|▉         | 27/291 [00:02<00:24, 10.67it/s]
                                                           

Loading 0:   9%|▉         | 27/291 [00:03<00:24, 10.67it/s]
                                                           

Loading 0:  10%|▉         | 29/291 [00:03<00:24, 10.67it/s]
Loading 0:  10%|█         | 30/291 [00:03<00:35,  7.36it/s]
                                                           

Loading 0:  11%|█         | 31/291 [00:04<00:35,  7.36it/s]
                                                           

Loading 0:  11%|█         | 32/291 [00:04<00:35,  7.36it/s]
Loading 0:  11%|█▏        | 33/291 [00:04<00:50,  5.11it/s]
                                                           

Loading 0:  11%|█▏        | 33/291 [00:05<00:50,  5.11it/s]
Loading 0:  12%|█▏        | 35/291 [00:06<01:20,  3.18it/s]
                                                           

Loading 0:  12%|█▏        | 35/291 [00:07<01:20,  3.18it/s]
                                                           

Loading 0:  12%|█▏        | 36/291 [00:07<01:20,  3.18it/s]
Loading 0:  13%|█▎        | 37/291 [00:07<01:22,  3.09it/s]
                                                           

Loading 0:  13%|█▎        | 37/291 [00:07<01:22,  3.09it/s]
                                                           

Loading 0:  13%|█▎        | 38/291 [00:08<01:21,  3.09it/s]
Loading 0:  13%|█▎        | 39/291 [00:08<01:36,  2.60it/s]
Loading 0:  14%|█▎        | 40/291 [00:08<01:38,  2.54it/s]
                                                           

Loading 0:  14%|█▎        | 40/291 [00:09<01:38,  2.54it/s]
                                                           

Loading 0:  14%|█▍        | 41/291 [00:09<01:38,  2.54it/s]
                                                           

Loading 0:  15%|█▍        | 43/291 [00:09<01:37,  2.54it/s]
                                                           

Loading 0:  15%|█▌        | 45/291 [00:09<01:36,  2.54it/s]
                                                           

Loading 0:  16%|█▌        | 46/291 [00:09<01:36,  2.54it/s]
                                                           

Loading 0:  16%|█▌        | 47/291 [00:09<01:35,  2.54it/s]
Loading 0:  16%|█▋        | 48/291 [00:09<00:38,  6.24it/s]
                                                           

Loading 0:  17%|█▋        | 49/291 [00:09<00:38,  6.24it/s]
                                                           

Loading 0:  17%|█▋        | 50/291 [00:09<00:38,  6.24it/s]
                                                           

Loading 0:  18%|█▊        | 52/291 [00:09<00:38,  6.24it/s]
Loading 0:  18%|█▊        | 53/291 [00:09<00:26,  9.04it/s]
                                                           

Loading 0:  19%|█▊        | 54/291 [00:09<00:26,  9.04it/s]
                                                           

Loading 0:  19%|█▉        | 55/291 [00:09<00:26,  9.04it/s]
                                                           

Loading 0:  19%|█▉        | 56/291 [00:09<00:26,  9.04it/s]
Loading 0:  20%|█▉        | 58/291 [00:09<00:18, 12.46it/s]
                                                           

Loading 0:  20%|█▉        | 58/291 [00:09<00:18, 12.46it/s]
                                                           

Loading 0:  20%|██        | 59/291 [00:09<00:18, 12.46it/s]
                                                           

Loading 0:  21%|██        | 61/291 [00:09<00:18, 12.46it/s]
                                                           

Loading 0:  22%|██▏       | 63/291 [00:09<00:18, 12.46it/s]
                                                           

Loading 0:  22%|██▏       | 64/291 [00:09<00:18, 12.46it/s]
                                                           

Loading 0:  22%|██▏       | 65/291 [00:09<00:18, 12.46it/s]
Loading 0:  23%|██▎       | 66/291 [00:09<00:11, 19.27it/s]
                                                           

Loading 0:  23%|██▎       | 67/291 [00:09<00:11, 19.27it/s]
                                                           

Loading 0:  23%|██▎       | 68/291 [00:09<00:11, 19.27it/s]
                                                           

Loading 0:  24%|██▍       | 70/291 [00:09<00:11, 19.27it/s]
Loading 0:  24%|██▍       | 71/291 [00:09<00:09, 23.14it/s]
                                                           

Loading 0:  25%|██▍       | 72/291 [00:09<00:09, 23.14it/s]
                                                           

Loading 0:  25%|██▌       | 74/291 [00:09<00:09, 23.14it/s]
Loading 0:  26%|██▌       | 76/291 [00:09<00:07, 27.07it/s]
                                                           

Loading 0:  26%|██▌       | 76/291 [00:09<00:07, 27.07it/s]
                                                           

Loading 0:  27%|██▋       | 78/291 [00:09<00:07, 27.07it/s]
                                                           

Loading 0:  27%|██▋       | 79/291 [00:09<00:07, 27.07it/s]
                                                           

Loading 0:  27%|██▋       | 80/291 [00:10<00:07, 27.07it/s]
Loading 0:  28%|██▊       | 81/291 [00:10<00:11, 19.07it/s]
                                                           

Loading 0:  28%|██▊       | 82/291 [00:10<00:10, 19.07it/s]
                                                           

Loading 0:  29%|██▊       | 83/291 [00:10<00:10, 19.07it/s]
Loading 0:  29%|██▉       | 85/291 [00:10<00:13, 15.73it/s]
                                                           

Loading 0:  29%|██▉       | 85/291 [00:10<00:13, 15.73it/s]
                                                           

Loading 0:  30%|██▉       | 87/291 [00:10<00:12, 15.73it/s]
                                                           

Loading 0:  30%|███       | 88/291 [00:10<00:12, 15.73it/s]
                                                           

Loading 0:  31%|███       | 89/291 [00:10<00:12, 15.73it/s]
Loading 0:  31%|███▏      | 91/291 [00:10<00:09, 20.51it/s]
                                                           

Loading 0:  31%|███▏      | 91/291 [00:10<00:09, 20.51it/s]
                                                           

Loading 0:  32%|███▏      | 92/291 [00:10<00:09, 20.51it/s]
                                                           

Loading 0:  32%|███▏      | 94/291 [00:10<00:09, 20.51it/s]
                                                           

Loading 0:  33%|███▎      | 96/291 [00:10<00:09, 20.51it/s]
                                                           

Loading 0:  33%|███▎      | 97/291 [00:10<00:09, 20.51it/s]
                                                           

Loading 0:  34%|███▎      | 98/291 [00:10<00:09, 20.51it/s]
Loading 0:  34%|███▍      | 99/291 [00:10<00:06, 28.24it/s]
                                                           

Loading 0:  34%|███▍      | 100/291 [00:10<00:06, 28.24it/s]
                                                            

Loading 0:  35%|███▍      | 101/291 [00:10<00:06, 28.24it/s]
                                                            

Loading 0:  35%|███▌      | 103/291 [00:10<00:06, 28.24it/s]
Loading 0:  36%|███▌      | 104/291 [00:10<00:05, 31.59it/s]
                                                            

Loading 0:  36%|███▌      | 105/291 [00:10<00:05, 31.59it/s]
                                                            

Loading 0:  36%|███▋      | 106/291 [00:10<00:05, 31.59it/s]
                                                            

Loading 0:  37%|███▋      | 107/291 [00:10<00:05, 31.59it/s]
                                                            

Loading 0:  37%|███▋      | 109/291 [00:10<00:05, 31.59it/s]
Loading 0:  38%|███▊      | 110/291 [00:10<00:05, 35.05it/s]
                                                            

Loading 0:  38%|███▊      | 110/291 [00:10<00:05, 35.05it/s]
                                                            

Loading 0:  38%|███▊      | 112/291 [00:10<00:05, 35.05it/s]
                                                            

Loading 0:  39%|███▉      | 114/291 [00:10<00:05, 35.05it/s]
                                                            

Loading 0:  40%|████      | 117/291 [00:11<00:04, 35.05it/s]
Loading 0:  41%|████      | 119/291 [00:11<00:03, 46.24it/s]
                                                            

Loading 0:  41%|████      | 119/291 [00:11<00:03, 46.24it/s]
                                                            

Loading 0:  41%|████      | 120/291 [00:11<00:03, 46.24it/s]
                                                            

Loading 0:  42%|████▏     | 121/291 [00:11<00:03, 46.24it/s]
                                                            

Loading 0:  42%|████▏     | 122/291 [00:11<00:03, 46.24it/s]
                                                            

Loading 0:  42%|████▏     | 123/291 [00:11<00:03, 46.24it/s]
                                                            

Loading 0:  43%|████▎     | 124/291 [00:11<00:03, 46.24it/s]
Loading 0:  43%|████▎     | 126/291 [00:11<00:03, 47.91it/s]
                                                            

Loading 0:  43%|████▎     | 126/291 [00:11<00:03, 47.91it/s]
                                                            

Loading 0:  44%|████▎     | 127/291 [00:11<00:03, 47.91it/s]
                                                            

Loading 0:  44%|████▍     | 129/291 [00:11<00:03, 47.91it/s]
                                                            

Loading 0:  45%|████▌     | 131/291 [00:11<00:03, 47.91it/s]
Loading 0:  45%|████▌     | 132/291 [00:11<00:03, 49.12it/s]
                                                            

Loading 0:  45%|████▌     | 132/291 [00:11<00:03, 49.12it/s]
                                                            

Loading 0:  46%|████▌     | 133/291 [00:11<00:03, 49.12it/s]
                                                            

Loading 0:  46%|████▌     | 134/291 [00:11<00:03, 49.12it/s]
                                                            

Loading 0:  46%|████▋     | 135/291 [00:11<00:03, 49.12it/s]
                                                            

Loading 0:  47%|████▋     | 136/291 [00:11<00:03, 49.12it/s]
                                                            

Loading 0:  47%|████▋     | 137/291 [00:11<00:03, 49.12it/s]
Loading 0:  47%|████▋     | 138/291 [00:11<00:05, 29.01it/s]
                                                            

Loading 0:  48%|████▊     | 139/291 [00:11<00:05, 29.01it/s]
                                                            

Loading 0:  48%|████▊     | 140/291 [00:11<00:05, 29.01it/s]
                                                            

Loading 0:  49%|████▉     | 142/291 [00:11<00:05, 29.01it/s]
Loading 0:  49%|████▉     | 144/291 [00:11<00:04, 33.93it/s]
                                                            

Loading 0:  49%|████▉     | 144/291 [00:11<00:04, 33.93it/s]
                                                            

Loading 0:  50%|████▉     | 145/291 [00:11<00:04, 33.93it/s]
                                                            

Loading 0:  50%|█████     | 146/291 [00:11<00:04, 33.93it/s]
                                                            

Loading 0:  51%|█████     | 148/291 [00:11<00:04, 33.93it/s]
Loading 0:  51%|█████     | 149/291 [00:11<00:04, 35.27it/s]
                                                            

Loading 0:  51%|█████     | 149/291 [00:11<00:04, 35.27it/s]
                                                            

Loading 0:  52%|█████▏    | 151/291 [00:11<00:03, 35.27it/s]
                                                            

Loading 0:  53%|█████▎    | 153/291 [00:12<00:03, 35.27it/s]
                                                            

Loading 0:  53%|█████▎    | 154/291 [00:12<00:03, 35.27it/s]
                                                            

Loading 0:  53%|█████▎    | 155/291 [00:12<00:03, 35.27it/s]
Loading 0:  54%|█████▍    | 157/291 [00:12<00:03, 42.59it/s]
                                                            

Loading 0:  54%|█████▍    | 157/291 [00:12<00:03, 42.59it/s]
                                                            

Loading 0:  54%|█████▍    | 158/291 [00:12<00:03, 42.59it/s]
                                                            

Loading 0:  55%|█████▍    | 160/291 [00:12<00:03, 42.59it/s]
                                                            

Loading 0:  56%|█████▌    | 162/291 [00:12<00:03, 42.59it/s]
                                                            

Loading 0:  56%|█████▌    | 163/291 [00:12<00:03, 42.59it/s]
                                                            

Loading 0:  56%|█████▋    | 164/291 [00:12<00:02, 42.59it/s]
Loading 0:  57%|█████▋    | 165/291 [00:12<00:02, 47.75it/s]
                                                            

Loading 0:  57%|█████▋    | 166/291 [00:12<00model.layers.23.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.23.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.23.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.23.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.23.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.23.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.24.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.24.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.24.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.24.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.24.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.24.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.25.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.25.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.25.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.25.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.25.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.25.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.26.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.26.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.26.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.26.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.26.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.26.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.27.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.27.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.27.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.27.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.27.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.27.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.28.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.28.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.28.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.28.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.28.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.28.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.29.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.29.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.29.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.29.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.29.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.29.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.30.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.30.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.30.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.30.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.30.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.30.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.31.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v14-mkmlizer: model.layers.31.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v14-mkmlizer: :02, 47.75it/s]
                                                            

Loading 0:  57%|█████▋    | 167/291 [00:12<00:02, 47.75it/s]
                                                            

Loading 0:  58%|█████▊    | 169/291 [00:12<00:02, 47.75it/s]
Loading 0:  59%|█████▉    | 171/291 [00:12<00:02, 49.13it/s]
                                                            

Loading 0:  59%|█████▉    | 171/291 [00:12<00:02, 49.13it/s]
                                                            

Loading 0:  59%|█████▉    | 172/291 [00:12<00:02, 49.13it/s]
                                                            

Loading 0:  59%|█████▉    | 173/291 [00:12<00:02, 49.13it/s]
                                                            

Loading 0:  60%|██████    | 175/291 [00:12<00:02, 49.13it/s]
                                                            

Loading 0:  60%|██████    | 176/291 [00:12<00:02, 49.13it/s]
Loading 0:  61%|██████    | 177/291 [00:12<00:02, 48.17it/s]
                                                            

Loading 0:  61%|██████    | 178/291 [00:12<00:02, 48.17it/s]
                                                            

Loading 0:  62%|██████▏   | 180/291 [00:12<00:02, 48.17it/s]
                                                            

Loading 0:  63%|██████▎   | 182/291 [00:12<00:02, 48.17it/s]
                                                            

Loading 0:  63%|██████▎   | 184/291 [00:12<00:02, 48.17it/s]
                                                            

Loading 0:  64%|██████▎   | 185/291 [00:12<00:02, 48.17it/s]
Loading 0:  64%|██████▍   | 186/291 [00:12<00:02, 37.02it/s]
                                                            

Loading 0:  64%|██████▍   | 186/291 [00:12<00:02, 37.02it/s]
                                                            

Loading 0:  65%|██████▍   | 188/291 [00:12<00:02, 37.02it/s]
                                                            

Loading 0:  65%|██████▍   | 189/291 [00:12<00:02, 37.02it/s]
                                                            

Loading 0:  65%|██████▌   | 190/291 [00:12<00:02, 37.02it/s]
Loading 0:  66%|██████▌   | 191/291 [00:12<00:02, 36.58it/s]
                                                            

Loading 0:  66%|██████▌   | 191/291 [00:12<00:02, 36.58it/s]
                                                            

Loading 0:  66%|██████▋   | 193/291 [00:13<00:02, 36.58it/s]
                                                            

Loading 0:  67%|██████▋   | 194/291 [00:13<00:02, 36.58it/s]
Loading 0:  67%|██████▋   | 196/291 [00:13<00:02, 35.97it/s]
                                                            

Loading 0:  67%|██████▋   | 196/291 [00:13<00:02, 35.97it/s]
                                                            

Loading 0:  68%|██████▊   | 198/291 [00:13<00:02, 35.97it/s]
                                                            

Loading 0:  68%|██████▊   | 199/291 [00:13<00:02, 35.97it/s]
                                                            

Loading 0:  69%|██████▊   | 200/291 [00:13<00:02, 35.97it/s]
Loading 0:  69%|██████▉   | 201/291 [00:13<00:02, 37.60it/s]
                                                            

Loading 0:  69%|██████▉   | 202/291 [00:13<00:02, 37.60it/s]
                                                            

Loading 0:  70%|██████▉   | 203/291 [00:13<00:02, 37.60it/s]
                                                            

Loading 0:  70%|███████   | 205/291 [00:13<00:02, 37.60it/s]
Loading 0:  71%|███████   | 206/291 [00:13<00:02, 31.32it/s]
                                                            

Loading 0:  71%|███████   | 207/291 [00:13<00:02, 31.32it/s]
                                                            

Loading 0:  71%|███████▏  | 208/291 [00:13<00:02, 31.32it/s]
                                                            

Loading 0:  72%|███████▏  | 209/291 [00:13<00:02, 31.32it/s]
Loading 0:  72%|███████▏  | 210/291 [00:13<00:02, 29.54it/s]
                                                            

Loading 0:  73%|███████▎  | 211/291 [00:13<00:02, 29.54it/s]
                                                            

Loading 0:  73%|███████▎  | 212/291 [00:13<00:02, 29.54it/s]
Loading 0:  74%|███████▎  | 214/291 [00:13<00:03, 24.78it/s]
                                                            

Loading 0:  74%|███████▎  | 214/291 [00:13<00:03, 24.78it/s]
                                                            

Loading 0:  74%|███████▍  | 216/291 [00:13<00:03, 24.78it/s]
                                                            

Loading 0:  75%|███████▍  | 217/291 [00:13<00:02, 24.78it/s]
                                                            

Loading 0:  75%|███████▍  | 218/291 [00:13<00:02, 24.78it/s]
Loading 0:  75%|███████▌  | 219/291 [00:13<00:02, 26.97it/s]
                                                            

Loading 0:  76%|███████▌  | 220/291 [00:14<00:02, 26.97it/s]
                                                            

Loading 0:  76%|███████▌  | 221/291 [00:14<00:02, 26.97it/s]
Loading 0:  76%|███████▋  | 222/291 [00:14<00:02, 25.31it/s]
                                                            

Loading 0:  77%|███████▋  | 223/291 [00:14<00:02, 25.31it/s]
                                                            

Loading 0:  77%|███████▋  | 225/291 [00:14<00:02, 25.31it/s]
                                                            

Loading 0:  78%|███████▊  | 227/291 [00:14<00:02, 25.31it/s]
Loading 0:  78%|███████▊  | 228/291 [00:14<00:02, 30.58it/s]
                                                            

Loading 0:  79%|███████▊  | 229/291 [00:14<00:02, 30.58it/s]
                                                            

Loading 0:  79%|███████▉  | 231/291 [00:14<00:01, 30.58it/s]
                                                            

Loading 0:  80%|███████▉  | 232/291 [00:14<00:01, 30.58it/s]
Loading 0:  80%|████████  | 233/291 [00:14<00:02, 24.00it/s]
                                                            

Loading 0:  80%|████████  | 233/291 [00:14<00:02, 24.00it/s]
                                                            

Loading 0:  80%|████████  | 234/291 [00:14<00:02, 24.00it/s]
                                                            

Loading 0:  81%|████████  | 235/291 [00:14<00:02, 24.00it/s]
                                                            

Loading 0:  81%|████████  | 236/291 [00:14<00:02, 24.00it/s]
Loading 0:  81%|████████▏ | 237/291 [00:14<00:02, 26.16it/s]
                                                            

Loading 0:  82%|████████▏ | 238/291 [00:14<00:02, 26.16it/s]
                                                            

Loading 0:  82%|████████▏ | 239/291 [00:14<00:01, 26.16it/s]
Loading 0:  82%|████████▏ | 240/291 [00:14<00:01, 26.70it/s]
                                                            

Loading 0:  83%|████████▎ | 241/291 [00:14<00:01, 26.70it/s]
                                                            

Loading 0:  84%|████████▎ | 243/291 [00:14<00:01, 26.70it/s]
                                                            

Loading 0:  84%|████████▍ | 244/291 [00:14<00:01, 26.70it/s]
                                                            

Loading 0:  84%|████████▍ | 245/291 [00:14<00:01, 26.70it/s]
Loading 0:  85%|████████▍ | 247/291 [00:14<00:01, 34.60it/s]
                                                            

Loading 0:  85%|████████▍ | 247/291 [00:14<00:01, 34.60it/s]
                                                            

Loading 0:  85%|████████▌ | 248/291 [00:14<00:01, 34.60it/s]
                                                            

Loading 0:  86%|████████▌ | 250/291 [00:14<00:01, 34.60it/s]
                                                            

Loading 0:  87%|████████▋ | 252/291 [00:14<00:01, 34.60it/s]
                                                            

Loading 0:  87%|████████▋ | 253/291 [00:14<00:01, 34.60it/s]
                                                            

Loading 0:  87%|████████▋ | 254/291 [00:15<00:01, 34.60it/s]
Loading 0:  88%|████████▊ | 255/291 [00:15<00:00, 43.34it/s]
                                                            

Loading 0:  88%|████████▊ | 256/291 [00:15<00:00, 43.34it/s]
                                                            

Loading 0:  88%|████████▊ | 257/291 [00:15<00:00, 43.34it/s]
                                                            

Loading 0:  89%|████████▉ | 259/291 [00:15<00:00, 43.34it/s]
Loading 0:  89%|████████▉ | 260/291 [00:15<00:00, 44.61it/s]
                                                            

Loading 0:  90%|████████▉ | 261/291 [00:15<00:00, 44.61it/s]
                                                            

Loading 0:  90%|█████████ | 262/291 [00:15<00:00, 44.61it/s]
                                                            

Loading 0:  90%|█████████ | 263/291 [00:15<00:00, 44.61it/s]
Loading 0:  91%|█████████ | 265/291 [00:15<00:00, 45.71it/s]
                                                            

Loading 0:  91%|█████████ | 265/291 [00:15<00:00, 45.71it/s]
                                                            

Loading 0:  91%|█████████▏| 266/291 [00:15<00:00, 45.71it/s]
                                                            

Loading 0:  92%|█████████▏| 268/291 [00:15<00:00, 45.71it/s]
                                                            

Loading 0:  93%|█████████▎| 270/291 [00:15<00:00, 45.71it/s]
                                                            

Loading 0:  93%|█████████▎| 271/291 [00:15<00:00, 45.71it/s]
                                                            

Loading 0:  93%|█████████▎| 272/291 [00:15<00:00, 45.71it/s]
Loading 0:  94%|█████████▍| 273/291 [00:15<00:00, 52.08it/s]
                                                            

Loading 0:  94%|█████████▍| 274/291 [00:15<00:00, 52.08it/s]
                                                            

Loading 0:  95%|█████████▍| 275/291 [00:15<00:00, 52.08it/s]
                                                            

Loading 0:  95%|█████████▌| 277/291 [00:15<00:00, 52.08it/s]
Loading 0:  96%|█████████▌| 279/291 [00:15<00:00, 51.03it/s]
                                                            

Loading 0:  96%|█████████▌| 279/291 [00:15<00:00, 51.03it/s]
                                                            

Loading 0:  97%|█████████▋| 282/291 [00:15<00:00, 51.03it/s]
                                                            

Loading 0:  98%|█████████▊| 284/291 [00:15<00:00, 51.03it/s]
Loading 0:  98%|█████████▊| 285/291 [00:15<00:00, 50.35it/s]
                                                            

Loading 0:  98%|█████████▊| 285/291 [00:21<00:00, 50.35it/s]
                                                            

Loading 0:  98%|█████████▊| 286/291 [00:21<00:00, 50.35it/s]
                                                            

Loading 0:  99%|█████████▊| 287/291 [00:21<00:00, 50.35it/s]
                                                            

Loading 0:  99%|█████████▉| 288/291 [00:21<00:00, 50.35it/s]
                                                            

Loading 0:  99%|█████████▉| 289/291 [00:21<00:00, 50.35it/s]
                                                            

Loading 0: 100%|█████████▉| 290/291 [00:21<00:00, 50.35it/s]
Loading 0: 100%|██████████| 291/291 [00:21<00:00,  3.06it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
jellywibble-lora-120k-p-2801-v14-mkmlizer: quantized model in 39.876s
jellywibble-lora-120k-p-2801-v14-mkmlizer: Processed model Jellywibble/lora_120k_pref_data_ep3_stacked_elo_alignment in 90.946s
jellywibble-lora-120k-p-2801-v14-mkmlizer: creating bucket guanaco-mkml-models
jellywibble-lora-120k-p-2801-v14-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jellywibble-lora-120k-p-2801-v14-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jellywibble-lora-120k-p-2801-v14
jellywibble-lora-120k-p-2801-v14-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jellywibble-lora-120k-p-2801-v14/config.json
jellywibble-lora-120k-p-2801-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jellywibble-lora-120k-p-2801-v14/tokenizer_config.json
jellywibble-lora-120k-p-2801-v14-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jellywibble-lora-120k-p-2801-v14/special_tokens_map.json
jellywibble-lora-120k-p-2801-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jellywibble-lora-120k-p-2801-v14/tokenizer.json
jellywibble-lora-120k-p-2801-v14-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jellywibble-lora-120k-p-2801-v14/flywheel_model.0.safetensors
jellywibble-lora-120k-p-2801-v14-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
jellywibble-lora-120k-p-2801-v14-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.
jellywibble-lora-120k-p-2801-v14-mkmlizer:   warnings.warn(
jellywibble-lora-120k-p-2801-v14-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.
jellywibble-lora-120k-p-2801-v14-mkmlizer:   warnings.warn(
jellywibble-lora-120k-p-2801-v14-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.
jellywibble-lora-120k-p-2801-v14-mkmlizer:   warnings.warn(
jellywibble-lora-120k-p-2801-v14-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:07<00:07,  7.71s/it]
Downloading shards: 100%|██████████| 2/2 [00:09<00:00,  4.41s/it]
Downloading shards: 100%|██████████| 2/2 [00:09<00:00,  4.91s/it]
jellywibble-lora-120k-p-2801-v14-mkmlizer: Saving duration: 2.016s
jellywibble-lora-120k-p-2801-v14-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 14.544s
jellywibble-lora-120k-p-2801-v14-mkmlizer: creating bucket guanaco-reward-models
jellywibble-lora-120k-p-2801-v14-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jellywibble-lora-120k-p-2801-v14-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jellywibble-lora-120k-p-2801-v14_reward
jellywibble-lora-120k-p-2801-v14-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jellywibble-lora-120k-p-2801-v14_reward/config.json
jellywibble-lora-120k-p-2801-v14-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jellywibble-lora-120k-p-2801-v14_reward/tokenizer_config.json
jellywibble-lora-120k-p-2801-v14-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jellywibble-lora-120k-p-2801-v14_reward/special_tokens_map.json
jellywibble-lora-120k-p-2801-v14-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jellywibble-lora-120k-p-2801-v14_reward/merges.txt
jellywibble-lora-120k-p-2801-v14-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jellywibble-lora-120k-p-2801-v14_reward/vocab.json
jellywibble-lora-120k-p-2801-v14-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jellywibble-lora-120k-p-2801-v14_reward/tokenizer.json
jellywibble-lora-120k-p-2801-v14-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/jellywibble-lora-120k-p-2801-v14_reward/reward.tensors
Job jellywibble-lora-120k-p-2801-v14-mkmlizer completed after 206.02s with status: succeeded
Stopping job with name jellywibble-lora-120k-p-2801-v14-mkmlizer
Pipeline stage MKMLizer completed in 206.88s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.14s
Running pipeline stage ISVCDeployer
Creating inference service jellywibble-lora-120k-p-2801-v14
Waiting for inference service jellywibble-lora-120k-p-2801-v14 to be ready
Inference service jellywibble-lora-120k-p-2801-v14 ready after 80.39210224151611s
Pipeline stage ISVCDeployer completed in 86.87s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2026538848876953s
Received healthy response to inference request in 1.2679407596588135s
Received healthy response to inference request in 1.2570905685424805s
Received healthy response to inference request in 1.2475590705871582s
Received healthy response to inference request in 1.271322250366211s
5 requests
0 failed requests
5th percentile: 1.2494653701782226
10th percentile: 1.2513716697692872
20th percentile: 1.255184268951416
30th percentile: 1.259260606765747
40th percentile: 1.2636006832122804
50th percentile: 1.2679407596588135
60th percentile: 1.2692933559417725
70th percentile: 1.2706459522247315
80th percentile: 1.457588577270508
90th percentile: 1.8301212310791017
95th percentile: 2.016387557983398
99th percentile: 2.165400619506836
mean time: 1.4493133068084716
Pipeline stage StressChecker completed in 8.81s
jellywibble-lora-120k-p_2801_v14 status is now deployed due to DeploymentManager action
jellywibble-lora-120k-p_2801_v14 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of jellywibble-lora-120k-p_2801_v14
Running pipeline stage ISVCDeleter
Checking if service jellywibble-lora-120k-p-2801-v14 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.98s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key jellywibble-lora-120k-p-2801-v14/config.json from bucket guanaco-mkml-models
Deleting key jellywibble-lora-120k-p-2801-v14/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key jellywibble-lora-120k-p-2801-v14/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key jellywibble-lora-120k-p-2801-v14/tokenizer.json from bucket guanaco-mkml-models
Deleting key jellywibble-lora-120k-p-2801-v14/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key jellywibble-lora-120k-p-2801-v14_reward/config.json from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-p-2801-v14_reward/merges.txt from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-p-2801-v14_reward/reward.tensors from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-p-2801-v14_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-p-2801-v14_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-p-2801-v14_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-p-2801-v14_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.66s
jellywibble-lora-120k-p_2801_v14 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics