jellywibble-lora-120k-p_2801

submission_id: jellywibble-lora-120k-p_2801_v11

developer_uid: Jellywibble

alignment_samples: 0

best_of: 2

celo_rating: 1212.11

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': 2, '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: 91203

num_wins: 47391

propriety_score: 0.7256912891081397

propriety_total_count: 7703.0

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: 2024-07-14T03:51:54+00:00

us_pacific_date: 2024-07-13

win_ratio: 0.5196210650965428

Resubmit model

Reference Models

Running pipeline stage MKMLizer
Starting job with name jellywibble-lora-120k-p-2801-v11-mkmlizer
Waiting for job on jellywibble-lora-120k-p-2801-v11-mkmlizer to finish
jellywibble-lora-120k-p-2801-v11-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jellywibble-lora-120k-p-2801-v11-mkmlizer: ║     _____            __           __                                ║
jellywibble-lora-120k-p-2801-v11-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jellywibble-lora-120k-p-2801-v11-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jellywibble-lora-120k-p-2801-v11-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jellywibble-lora-120k-p-2801-v11-mkmlizer: ║       /___/                                                         ║
jellywibble-lora-120k-p-2801-v11-mkmlizer: ║                                                                     ║
jellywibble-lora-120k-p-2801-v11-mkmlizer: ║  Version: 0.9.5.post2                                               ║
jellywibble-lora-120k-p-2801-v11-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jellywibble-lora-120k-p-2801-v11-mkmlizer: ║  https://mk1.ai                                                     ║
jellywibble-lora-120k-p-2801-v11-mkmlizer: ║                                                                     ║
jellywibble-lora-120k-p-2801-v11-mkmlizer: ║  The license key for the current software has been verified as      ║
jellywibble-lora-120k-p-2801-v11-mkmlizer: ║  belonging to:                                                      ║
jellywibble-lora-120k-p-2801-v11-mkmlizer: ║                                                                     ║
jellywibble-lora-120k-p-2801-v11-mkmlizer: ║  Chai Research Corp.                                                ║
jellywibble-lora-120k-p-2801-v11-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jellywibble-lora-120k-p-2801-v11-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
jellywibble-lora-120k-p-2801-v11-mkmlizer: ║                                                                     ║
jellywibble-lora-120k-p-2801-v11-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jellywibble-lora-120k-p-2801-v11-mkmlizer: Downloaded to shared memory in 55.065s
jellywibble-lora-120k-p-2801-v11-mkmlizer: quantizing model to /dev/shm/model_cache
jellywibble-lora-120k-p-2801-v11-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.embed_tokens.weight torch.Size([139542528])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.0.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.0.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.0.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.0.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.0.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.0.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.1.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.1.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.1.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.1.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.1.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.1.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.2.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.2.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.2.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.2.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.2.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.2.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.3.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.3.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.3.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.3.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.4.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.4.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.4.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.4.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.4.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.4.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.5.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.5.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.5.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.5.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.5.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.5.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.6.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.6.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.6.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.6.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.6.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.6.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.7.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.7.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.7.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.7.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.7.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.7.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.8.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.8.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.8.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.10.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.10.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.10.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.10.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.10.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.10.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.11.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.11.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.11.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.11.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.11.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.11.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.12.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.12.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.12.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.12.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.12.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.12.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.13.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.13.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.13.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.13.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.13.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.13.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.14.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.14.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.8.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.8.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.8.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.9.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.9.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.9.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.9.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.9.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.9.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.14.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.14.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.14.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.14.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.15.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.15.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.15.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.15.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.15.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.15.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.16.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.16.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.16.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.16.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.16.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.16.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.17.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.17.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.17.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.17.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.17.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.17.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.18.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.18.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.18.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.18.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.18.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.18.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.19.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.19.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.19.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.19.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.19.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.19.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.20.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.20.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.20.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.20.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.20.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.20.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.21.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.21.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.21.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.21.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.21.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.21.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.22.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.22.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.22.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.22.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.22.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v11-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
                                                  

Loading 0:   0%|          | 1/291 [00:00<00:00, 295.89it/s]
                                                           

Loading 0:   1%|          | 2/291 [00:00<00:07, 38.07it/s]
                                                          

Loading 0:   1%|▏         | 4/291 [00:00<00:10, 28.10it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:08, 35.08it/s]
                                                          

Loading 0:   2%|▏         | 5/291 [00:00<00:08, 35.08it/s]
                                                          

Loading 0:   2%|▏         | 7/291 [00:00<00:08, 35.08it/s]
                                                          

Loading 0:   3%|▎         | 9/291 [00:00<00:08, 35.08it/s]
                                                          

Loading 0:   3%|▎         | 10/291 [00:00<00:08, 35.08it/s]
                                                           

Loading 0:   4%|▍         | 11/291 [00:00<00:07, 35.08it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:09, 30.97it/s]
                                                           

Loading 0:   4%|▍         | 13/291 [00:01<00:08, 30.97it/s]
                                                           

Loading 0:   5%|▍         | 14/291 [00:01<00:08, 30.97it/s]
Loading 0:   5%|▌         | 16/291 [00:01<00:25, 10.61it/s]
                                                           

Loading 0:   5%|▌         | 16/291 [00:01<00:25, 10.61it/s]
Loading 0:   6%|▌         | 18/291 [00:01<00:23, 11.51it/s]
                                                           

Loading 0:   6%|▌         | 18/291 [00:01<00:23, 11.51it/s]
                                                           

Loading 0:   7%|▋         | 19/291 [00:01<00:23, 11.51it/s]
                                                           

Loading 0:   7%|▋         | 20/291 [00:01<00:23, 11.51it/s]
Loading 0:   7%|▋         | 21/291 [00:01<00:22, 12.09it/s]
                                                           

Loading 0:   8%|▊         | 22/291 [00:02<00:22, 12.09it/s]
Loading 0:   8%|▊         | 23/291 [00:02<00:35,  7.62it/s]
                                                           

Loading 0:   8%|▊         | 23/291 [00:02<00:35,  7.62it/s]
                                                           

Loading 0:   9%|▊         | 25/291 [00:02<00:34,  7.62it/s]
Loading 0:   9%|▉         | 27/291 [00:02<00:24, 10.73it/s]
                                                           

Loading 0:   9%|▉         | 27/291 [00:02<00:24, 10.73it/s]
                                                           

Loading 0:  10%|▉         | 29/291 [00:02<00:24, 10.73it/s]
Loading 0:  10%|█         | 30/291 [00:02<00:27,  9.39it/s]
                                                           

Loading 0:  11%|█         | 31/291 [00:02<00:27,  9.39it/s]
Loading 0:  11%|█         | 32/291 [00:02<00:24, 10.55it/s]
                                                           

Loading 0:  11%|█         | 32/291 [00:03<00:24, 10.55it/s]
                                                           

Loading 0:  11%|█▏        | 33/291 [00:03<00:24, 10.55it/s]
Loading 0:  12%|█▏        | 34/291 [00:03<00:40,  6.29it/s]
                                                           

Loading 0:  12%|█▏        | 35/291 [00:05<00:40,  6.29it/s]
Loading 0:  12%|█▏        | 36/291 [00:05<01:21,  3.13it/s]
                                                           

Loading 0:  12%|█▏        | 36/291 [00:05<01:21,  3.13it/s]
                                                           

Loading 0:  13%|█▎        | 37/291 [00:05<01:21,  3.13it/s]
                                                           

Loading 0:  13%|█▎        | 38/291 [00:05<01:20,  3.13it/s]
Loading 0:  13%|█▎        | 39/291 [00:05<01:10,  3.58it/s]
Loading 0:  14%|█▎        | 40/291 [00:06<01:22,  3.04it/s]
                                                           

Loading 0:  14%|█▎        | 40/291 [00:06<01:22,  3.04it/s]
Loading 0:  14%|█▍        | 41/291 [00:06<01:33,  2.67it/s]
                                                           

Loading 0:  14%|█▍        | 41/291 [00:06<01:33,  2.67it/s]
                                                           

Loading 0:  15%|█▍        | 43/291 [00:07<01:32,  2.67it/s]
Loading 0:  15%|█▌        | 44/291 [00:07<00:58,  4.25it/s]
                                                           

Loading 0:  15%|█▌        | 45/291 [00:07<00:57,  4.25it/s]
                                                           

Loading 0:  16%|█▌        | 46/291 [00:07<00:57,  4.25it/s]
                                                           

Loading 0:  16%|█▌        | 47/291 [00:07<00:57,  4.25it/s]
Loading 0:  16%|█▋        | 48/291 [00:07<00:39,  6.09it/s]
                                                           

Loading 0:  17%|█▋        | 49/291 [00:08<00:39,  6.09it/s]
Loading 0:  17%|█▋        | 50/291 [00:08<00:48,  4.95it/s]
                                                           

Loading 0:  17%|█▋        | 50/291 [00:08<00:48,  4.95it/s]
                                                           

Loading 0:  18%|█▊        | 52/291 [00:08<00:48,  4.95it/s]
                                                           

Loading 0:  19%|█▊        | 54/291 [00:08<00:47,  4.95it/s]
                                                           

Loading 0:  19%|█▉        | 55/291 [00:08<00:47,  4.95it/s]
                                                           

Loading 0:  19%|█▉        | 56/291 [00:08<00:47,  4.95it/s]
Loading 0:  20%|█▉        | 57/291 [00:08<00:24,  9.71it/s]
                                                           

Loading 0:  20%|█▉        | 58/291 [00:08<00:23,  9.71it/s]
                                                           

Loading 0:  20%|██        | 59/291 [00:08<00:23,  9.71it/s]
                                                           

Loading 0:  21%|██        | 61/291 [00:08<00:23,  9.71it/s]
Loading 0:  22%|██▏       | 63/291 [00:08<00:15, 14.62it/s]
                                                           

Loading 0:  22%|██▏       | 63/291 [00:08<00:15, 14.62it/s]
                                                           

Loading 0:  22%|██▏       | 64/291 [00:08<00:15, 14.62it/s]
                                                           

Loading 0:  22%|██▏       | 65/291 [00:08<00:15, 14.62it/s]
                                                           

Loading 0:  23%|██▎       | 67/291 [00:08<00:15, 14.62it/s]
Loading 0:  23%|██▎       | 68/291 [00:08<00:12, 18.39it/s]
                                                           

Loading 0:  23%|██▎       | 68/291 [00:08<00:12, 18.39it/s]
                                                           

Loading 0:  24%|██▍       | 70/291 [00:08<00:12, 18.39it/s]
                                                           

Loading 0:  25%|██▍       | 72/291 [00:08<00:11, 18.39it/s]
                                                           

Loading 0:  25%|██▌       | 74/291 [00:08<00:11, 18.39it/s]
Loading 0:  26%|██▌       | 75/291 [00:08<00:08, 25.41it/s]
                                                           

Loading 0:  26%|██▌       | 76/291 [00:08<00:08, 25.41it/s]
                                                           

Loading 0:  27%|██▋       | 78/291 [00:08<00:08, 25.41it/s]
                                                           

Loading 0:  27%|██▋       | 79/291 [00:08<00:08, 25.41it/s]
Loading 0:  27%|██▋       | 80/291 [00:08<00:11, 19.13it/s]
                                                           

Loading 0:  27%|██▋       | 80/291 [00:08<00:11, 19.13it/s]
                                                           

Loading 0:  28%|██▊       | 82/291 [00:09<00:10, 19.13it/s]
                                                           

Loading 0:  29%|██▊       | 83/291 [00:09<00:10, 19.13it/s]
Loading 0:  29%|██▉       | 84/291 [00:09<00:09, 21.12it/s]
                                                           

Loading 0:  29%|██▉       | 85/291 [00:09<00:09, 21.12it/s]
                                                           

Loading 0:  30%|██▉       | 87/291 [00:09<00:09, 21.12it/s]
                                                           

Loading 0:  30%|███       | 88/291 [00:09<00:09, 21.12it/s]
                                                           

Loading 0:  31%|███       | 89/291 [00:09<00:09, 21.12it/s]
Loading 0:  31%|███▏      | 91/291 [00:09<00:07, 28.37it/s]
                                                           

Loading 0:  31%|███▏      | 91/291 [00:09<00:07, 28.37it/s]
                                                           

Loading 0:  32%|███▏      | 92/291 [00:09<00:07, 28.37it/s]
                                                           

Loading 0:  32%|███▏      | 94/291 [00:09<00:06, 28.37it/s]
                                                           

Loading 0:  33%|███▎      | 96/291 [00:09<00:06, 28.37it/s]
                                                           

Loading 0:  33%|███▎      | 97/291 [00:09<00:06, 28.37it/s]
                                                           

Loading 0:  34%|███▎      | 98/291 [00:09<00:06, 28.37it/s]
Loading 0:  34%|███▍      | 99/291 [00:09<00:05, 36.98it/s]
                                                           

Loading 0:  34%|███▍      | 100/291 [00:09<00:05, 36.98it/s]
                                                            

Loading 0:  35%|███▍      | 101/291 [00:09<00:05, 36.98it/s]
                                                            

Loading 0:  35%|███▌      | 103/291 [00:09<00:05, 36.98it/s]
Loading 0:  36%|███▌      | 105/291 [00:09<00:04, 40.38it/s]
                                                            

Loading 0:  36%|███▌      | 105/291 [00:09<00:04, 40.38it/s]
                                                            

Loading 0:  36%|███▋      | 106/291 [00:09<00:04, 40.38it/s]
                                                            

Loading 0:  37%|███▋      | 107/291 [00:09<00:04, 40.38it/s]
                                                            

Loading 0:  37%|███▋      | 109/291 [00:09<00:04, 40.38it/s]
                                                            

Loading 0:  38%|███▊      | 110/291 [00:09<00:04, 40.38it/s]
Loading 0:  38%|███▊      | 111/291 [00:09<00:04, 42.66it/s]
                                                            

Loading 0:  38%|███▊      | 112/291 [00:09<00:04, 42.66it/s]
                                                            

Loading 0:  39%|███▉      | 114/291 [00:09<00:04, 42.66it/s]
                                                            

Loading 0:  40%|████      | 117/291 [00:09<00:04, 42.66it/s]
                                                            

Loading 0:  41%|████      | 119/291 [00:09<00:04, 42.66it/s]
Loading 0:  41%|████      | 120/291 [00:09<00:03, 53.07it/s]
                                                            

Loading 0:  41%|████      | 120/291 [00:09<00:03, 53.07it/s]
                                                            

Loading 0:  42%|████▏     | 121/291 [00:09<00:03, 53.07it/s]
                                                            

Loading 0:  42%|████▏     | 122/291 [00:09<00:03, 53.07it/s]
                                                            

Loading 0:  42%|████▏     | 123/291 [00:09<00:03, 53.07it/s]
                                                            

Loading 0:  43%|████▎     | 124/291 [00:09<00:03, 53.07it/s]
                                                            

Loading 0:  43%|████▎     | 126/291 [00:09<00:03, 53.07it/s]
Loading 0:  44%|████▎     | 127/291 [00:09<00:03, 47.70it/s]
                                                            

Loading 0:  44%|████▎     | 127/291 [00:09<00:03, 47.70it/s]
                                                            

Loading 0:  44%|████▍     | 129/291 [00:09<00:03, 47.70it/s]
                                                            

Loading 0:  45%|████▌     | 131/291 [00:09<00:03, 47.70it/s]
                                                            

Loading 0:  45%|████▌     | 132/291 [00:10<00:03, 47.70it/s]
Loading 0:  46%|████▌     | 133/291 [00:10<00:05, 27.90it/s]
                                                            

Loading 0:  46%|████▌     | 133/291 [00:10<00:05, 27.90it/s]
                                                            

Loading 0:  46%|████▌     | 134/291 [00:10<00:05, 27.90it/s]
                                                            

Loading 0:  46%|████▋     | 135/291 [00:10<00:05, 27.90it/s]
                                                            

Loading 0:  47%|████▋     | 136/291 [00:10<00:05, 27.90it/s]
                                                            

Loading 0:  47%|████▋     | 137/291 [00:10<00:05, 27.90it/s]
Loading 0:  47%|████▋     | 138/291 [00:10<00:05, 29.62it/s]
                                                            

Loading 0:  48%|████▊     | 139/291 [00:10<00:05, 29.62it/s]
                                                            

Loading 0:  48%|████▊     | 140/291 [00:10<00:05, 29.62it/s]
                                                            

Loading 0:  49%|████▉     | 142/291 [00:10<00:05, 29.62it/s]
Loading 0:  49%|████▉     | 144/291 [00:10<00:04, 34.09it/s]
                                                            

Loading 0:  49%|████▉     | 144/291 [00:10<00:04, 34.09it/s]
                                                            

Loading 0:  50%|████▉     | 145/291 [00:10<00:04, 34.09it/s]
                                                            

Loading 0:  50%|█████     | 146/291 [00:10<00:04, 34.09it/s]
                                                            

Loading 0:  51%|█████     | 148/291 [00:10<00:04, 34.09it/s]
Loading 0:  51%|█████     | 149/291 [00:10<00:04, 35.38it/s]
                                                            

Loading 0:  51%|█████     | 149/291 [00:10<00:04, 35.38it/s]
                                                            

Loading 0:  52%|█████▏    | 151/291 [00:10<00:03, 35.38it/s]
                                                            

Loading 0:  53%|█████▎    | 153/291 [00:10<00:03, 35.38it/s]
                                                            

Loading 0:  53%|█████▎    | 154/291 [00:10<00:03, 35.38it/s]
                                                            

Loading 0:  53%|█████▎    | 155/291 [00:10<00:03, 35.38it/s]
Loading 0:  54%|█████▍    | 157/291 [00:10<00:03, 43.84it/s]
                                                            

Loading 0:  54%|█████▍    | 157/291 [00:10<00:03, 43.84it/s]
                                                            

Loading 0:  54%|█████▍    | 158/291 [00:10<00:03, 43.84it/s]
                                                            

Loading 0:  55%|█████▍    | 160/291 [00:10<00:02, 43.84it/s]
                                                            

Loading 0:  56%|█████▌    | 162/291 [00:10<00:02, 43.84it/s]
                                                            

Loading 0:  56%|█████▌    | 163/291 [00:10<00:02, 43.84it/s]
                                                            

Loading 0:  56%|█████▋    | 164/291 [00:10<00:02, 43.84it/s]
model.layers.22.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.23.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.23.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.23.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.23.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.23.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.23.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.24.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.24.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.24.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.24.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.24.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.24.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.25.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.25.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.25.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.25.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.25.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.25.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.26.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.26.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.26.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.26.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.26.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.26.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.27.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.27.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.27.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.27.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.27.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.27.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.28.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.28.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.28.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.28.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.28.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.28.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.29.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.29.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.29.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.29.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.29.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.29.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.30.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.30.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.30.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.30.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.30.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.30.self_attn.qkv_proj.weight torch.Size([5111808])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.31.self_attn.o_proj.weight torch.Size([3407872])
jellywibble-lora-120k-p-2801-v11-mkmlizer: lm_head.weight torch.Size([139542528])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.31.input_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.31.mlp.down_proj.weight torch.Size([11927552])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.31.mlp.up_gate_proj.weight torch.Size([23855104])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.layers.31.post_attention_layernorm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: model.norm.weight torch.Size([4096])
jellywibble-lora-120k-p-2801-v11-mkmlizer: Loading 0:  57%|█████▋    | 165/291 [00:10<00:02, 50.20it/s]
                                                            

Loading 0:  57%|█████▋    | 166/291 [00:10<00:02, 50.20it/s]
                                                            

Loading 0:  57%|█████▋    | 167/291 [00:10<00:02, 50.20it/s]
                                                            

Loading 0:  58%|█████▊    | 169/291 [00:10<00:02, 50.20it/s]
Loading 0:  59%|█████▉    | 171/291 [00:10<00:02, 49.88it/s]
                                                            

Loading 0:  59%|█████▉    | 171/291 [00:10<00:02, 49.88it/s]
                                                            

Loading 0:  59%|█████▉    | 172/291 [00:10<00:02, 49.88it/s]
                                                            

Loading 0:  59%|█████▉    | 173/291 [00:11<00:02, 49.88it/s]
                                                            

Loading 0:  60%|██████    | 175/291 [00:11<00:02, 49.88it/s]
                                                            

Loading 0:  60%|██████    | 176/291 [00:11<00:02, 49.88it/s]
Loading 0:  61%|██████    | 177/291 [00:11<00:02, 46.24it/s]
                                                            

Loading 0:  61%|██████    | 178/291 [00:11<00:02, 46.24it/s]
                                                            

Loading 0:  62%|██████▏   | 180/291 [00:11<00:02, 46.24it/s]
                                                            

Loading 0:  63%|██████▎   | 182/291 [00:11<00:02, 46.24it/s]
                                                            

Loading 0:  63%|██████▎   | 184/291 [00:11<00:02, 46.24it/s]
                                                            

Loading 0:  64%|██████▎   | 185/291 [00:11<00:02, 46.24it/s]
Loading 0:  64%|██████▍   | 186/291 [00:11<00:03, 28.90it/s]
                                                            

Loading 0:  64%|██████▍   | 186/291 [00:11<00:03, 28.90it/s]
                                                            

Loading 0:  65%|██████▍   | 188/291 [00:11<00:03, 28.90it/s]
                                                            

Loading 0:  65%|██████▍   | 189/291 [00:11<00:03, 28.90it/s]
                                                            

Loading 0:  65%|██████▌   | 190/291 [00:11<00:03, 28.90it/s]
Loading 0:  66%|██████▌   | 191/291 [00:11<00:03, 31.19it/s]
                                                            

Loading 0:  66%|██████▌   | 191/291 [00:11<00:03, 31.19it/s]
                                                            

Loading 0:  66%|██████▋   | 193/291 [00:11<00:03, 31.19it/s]
                                                            

Loading 0:  67%|██████▋   | 194/291 [00:11<00:03, 31.19it/s]
Loading 0:  67%|██████▋   | 196/291 [00:11<00:02, 33.09it/s]
                                                            

Loading 0:  67%|██████▋   | 196/291 [00:11<00:02, 33.09it/s]
                                                            

Loading 0:  68%|██████▊   | 198/291 [00:11<00:02, 33.09it/s]
                                                            

Loading 0:  68%|██████▊   | 199/291 [00:11<00:02, 33.09it/s]
                                                            

Loading 0:  69%|██████▊   | 200/291 [00:11<00:02, 33.09it/s]
Loading 0:  69%|██████▉   | 202/291 [00:11<00:02, 37.73it/s]
                                                            

Loading 0:  69%|██████▉   | 202/291 [00:12<00:02, 37.73it/s]
                                                            

Loading 0:  70%|██████▉   | 203/291 [00:12<00:02, 37.73it/s]
                                                            

Loading 0:  70%|███████   | 205/291 [00:12<00:02, 37.73it/s]
                                                            

Loading 0:  71%|███████   | 207/291 [00:12<00:02, 37.73it/s]
                                                            

Loading 0:  71%|███████▏  | 208/291 [00:12<00:02, 37.73it/s]
                                                            

Loading 0:  72%|███████▏  | 209/291 [00:12<00:02, 37.73it/s]
Loading 0:  72%|███████▏  | 210/291 [00:12<00:01, 45.02it/s]
                                                            

Loading 0:  73%|███████▎  | 211/291 [00:12<00:01, 45.02it/s]
                                                            

Loading 0:  73%|███████▎  | 212/291 [00:12<00:01, 45.02it/s]
                                                            

Loading 0:  74%|███████▎  | 214/291 [00:12<00:01, 45.02it/s]
Loading 0:  74%|███████▍  | 216/291 [00:12<00:01, 45.35it/s]
                                                            

Loading 0:  74%|███████▍  | 216/291 [00:12<00:01, 45.35it/s]
                                                            

Loading 0:  75%|███████▍  | 217/291 [00:12<00:01, 45.35it/s]
                                                            

Loading 0:  75%|███████▍  | 218/291 [00:12<00:01, 45.35it/s]
                                                            

Loading 0:  76%|███████▌  | 220/291 [00:12<00:01, 45.35it/s]
                                                            

Loading 0:  76%|███████▌  | 221/291 [00:12<00:01, 45.35it/s]
Loading 0:  76%|███████▋  | 222/291 [00:12<00:01, 45.17it/s]
                                                            

Loading 0:  77%|███████▋  | 223/291 [00:12<00:01, 45.17it/s]
                                                            

Loading 0:  77%|███████▋  | 225/291 [00:12<00:01, 45.17it/s]
                                                            

Loading 0:  78%|███████▊  | 227/291 [00:12<00:01, 45.17it/s]
Loading 0:  78%|███████▊  | 228/291 [00:12<00:01, 46.90it/s]
                                                            

Loading 0:  79%|███████▊  | 229/291 [00:12<00:01, 46.90it/s]
                                                            

Loading 0:  79%|███████▉  | 231/291 [00:12<00:01, 46.90it/s]
                                                            

Loading 0:  80%|███████▉  | 232/291 [00:12<00:01, 46.90it/s]
Loading 0:  80%|████████  | 233/291 [00:12<00:02, 25.72it/s]
                                                            

Loading 0:  80%|████████  | 233/291 [00:12<00:02, 25.72it/s]
                                                            

Loading 0:  80%|████████  | 234/291 [00:12<00:02, 25.72it/s]
                                                            

Loading 0:  81%|████████  | 235/291 [00:12<00:02, 25.72it/s]
                                                            

Loading 0:  81%|████████  | 236/291 [00:13<00:02, 25.72it/s]
Loading 0:  82%|████████▏ | 238/291 [00:13<00:01, 28.66it/s]
                                                            

Loading 0:  82%|████████▏ | 238/291 [00:13<00:01, 28.66it/s]
                                                            

Loading 0:  82%|████████▏ | 239/291 [00:13<00:01, 28.66it/s]
                                                            

Loading 0:  83%|████████▎ | 241/291 [00:13<00:01, 28.66it/s]
                                                            

Loading 0:  84%|████████▎ | 243/291 [00:13<00:01, 28.66it/s]
                                                            

Loading 0:  84%|████████▍ | 244/291 [00:13<00:01, 28.66it/s]
                                                            

Loading 0:  84%|████████▍ | 245/291 [00:13<00:01, 28.66it/s]
Loading 0:  85%|████████▍ | 246/291 [00:13<00:01, 36.75it/s]
                                                            

Loading 0:  85%|████████▍ | 247/291 [00:13<00:01, 36.75it/s]
                                                            

Loading 0:  85%|████████▌ | 248/291 [00:13<00:01, 36.75it/s]
                                                            

Loading 0:  86%|████████▌ | 250/291 [00:13<00:01, 36.75it/s]
Loading 0:  86%|████████▋ | 251/291 [00:13<00:01, 39.33it/s]
                                                            

Loading 0:  87%|████████▋ | 252/291 [00:13<00:00, 39.33it/s]
                                                            

Loading 0:  87%|████████▋ | 253/291 [00:13<00:00, 39.33it/s]
                                                            

Loading 0:  87%|████████▋ | 254/291 [00:13<00:00, 39.33it/s]
                                                            

Loading 0:  88%|████████▊ | 256/291 [00:13<00:00, 39.33it/s]
Loading 0:  88%|████████▊ | 257/291 [00:13<00:00, 40.46it/s]
                                                            

Loading 0:  88%|████████▊ | 257/291 [00:13<00:00, 40.46it/s]
                                                            

Loading 0:  89%|████████▉ | 259/291 [00:13<00:00, 40.46it/s]
                                                            

Loading 0:  90%|████████▉ | 261/291 [00:13<00:00, 40.46it/s]
                                                            

Loading 0:  90%|█████████ | 262/291 [00:13<00:00, 40.46it/s]
                                                            

Loading 0:  90%|█████████ | 263/291 [00:13<00:00, 40.46it/s]
Loading 0:  91%|█████████ | 265/291 [00:13<00:00, 48.04it/s]
                                                            

Loading 0:  91%|█████████ | 265/291 [00:13<00:00, 48.04it/s]
                                                            

Loading 0:  91%|█████████▏| 266/291 [00:13<00:00, 48.04it/s]
                                                            

Loading 0:  92%|█████████▏| 268/291 [00:13<00:00, 48.04it/s]
                                                            

Loading 0:  93%|█████████▎| 270/291 [00:13<00:00, 48.04it/s]
                                                            

Loading 0:  93%|█████████▎| 271/291 [00:13<00:00, 48.04it/s]
                                                            

Loading 0:  93%|█████████▎| 272/291 [00:13<00:00, 48.04it/s]
Loading 0:  94%|█████████▍| 273/291 [00:13<00:00, 52.70it/s]
                                                            

Loading 0:  94%|█████████▍| 274/291 [00:13<00:00, 52.70it/s]
                                                            

Loading 0:  95%|█████████▍| 275/291 [00:13<00:00, 52.70it/s]
                                                            

Loading 0:  95%|█████████▌| 277/291 [00:13<00:00, 52.70it/s]
Loading 0:  96%|█████████▌| 279/291 [00:13<00:00, 50.91it/s]
                                                            

Loading 0:  96%|█████████▌| 279/291 [00:13<00:00, 50.91it/s]
                                                            

Loading 0:  97%|█████████▋| 282/291 [00:13<00:00, 50.91it/s]
                                                            

Loading 0:  98%|█████████▊| 284/291 [00:13<00:00, 50.91it/s]
                                                            

Loading 0:  98%|█████████▊| 285/291 [00:21<00:00, 50.91it/s]
Loading 0:  98%|█████████▊| 286/291 [00:21<00:01,  2.83it/s]
                                                            

Loading 0:  98%|█████████▊| 286/291 [00:21<00:01,  2.83it/s]
                                                            

Loading 0:  99%|█████████▊| 287/291 [00:21<00:01,  2.83it/s]
                                                            

Loading 0:  99%|█████████▉| 288/291 [00:21<00:01,  2.83it/s]
                                                            

Loading 0:  99%|█████████▉| 289/291 [00:21<00:00,  2.83it/s]
                                                            

Loading 0: 100%|█████████▉| 290/291 [00:21<00:00,  2.83it/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-v11-mkmlizer: quantized model in 43.948s
jellywibble-lora-120k-p-2801-v11-mkmlizer: Processed model Jellywibble/lora_120k_pref_data_ep3_stacked_elo_alignment in 99.013s
jellywibble-lora-120k-p-2801-v11-mkmlizer: creating bucket guanaco-mkml-models
jellywibble-lora-120k-p-2801-v11-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jellywibble-lora-120k-p-2801-v11-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jellywibble-lora-120k-p-2801-v11
jellywibble-lora-120k-p-2801-v11-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jellywibble-lora-120k-p-2801-v11/special_tokens_map.json
jellywibble-lora-120k-p-2801-v11-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jellywibble-lora-120k-p-2801-v11/config.json
jellywibble-lora-120k-p-2801-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jellywibble-lora-120k-p-2801-v11/tokenizer_config.json
jellywibble-lora-120k-p-2801-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jellywibble-lora-120k-p-2801-v11/tokenizer.json
jellywibble-lora-120k-p-2801-v11-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
jellywibble-lora-120k-p-2801-v11-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-v11-mkmlizer:   warnings.warn(
jellywibble-lora-120k-p-2801-v11-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-v11-mkmlizer:   warnings.warn(
jellywibble-lora-120k-p-2801-v11-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-v11-mkmlizer:   warnings.warn(
jellywibble-lora-120k-p-2801-v11-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:08<00:08,  8.39s/it]
Downloading shards: 100%|██████████| 2/2 [00:10<00:00,  4.94s/it]
Downloading shards: 100%|██████████| 2/2 [00:10<00:00,  5.46s/it]
jellywibble-lora-120k-p-2801-v11-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  1.30it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:01<00:00,  2.20it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:01<00:00,  1.99it/s]
jellywibble-lora-120k-p-2801-v11-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jellywibble-lora-120k-p-2801-v11-mkmlizer: Saving duration: 3.105s
jellywibble-lora-120k-p-2801-v11-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 16.678s
jellywibble-lora-120k-p-2801-v11-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/jellywibble-lora-120k-p-2801-v11_reward/reward.tensors
Job jellywibble-lora-120k-p-2801-v11-mkmlizer completed after 213.04s with status: succeeded
Stopping job with name jellywibble-lora-120k-p-2801-v11-mkmlizer
Pipeline stage MKMLizer completed in 213.99s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.14s
Running pipeline stage ISVCDeployer
Creating inference service jellywibble-lora-120k-p-2801-v11
Waiting for inference service jellywibble-lora-120k-p-2801-v11 to be ready
Inference service jellywibble-lora-120k-p-2801-v11 ready after 50.2209255695343s
Pipeline stage ISVCDeployer completed in 56.88s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.23925518989563s
Received healthy response to inference request in 1.1102869510650635s
Received healthy response to inference request in 1.1102674007415771s
Received healthy response to inference request in 1.1016948223114014s
Received healthy response to inference request in 1.1020264625549316s
5 requests
0 failed requests
5th percentile: 1.1017611503601075
10th percentile: 1.1018274784088136
20th percentile: 1.1019601345062255
30th percentile: 1.1036746501922607
40th percentile: 1.106971025466919
50th percentile: 1.1102674007415771
60th percentile: 1.1102752208709716
70th percentile: 1.1102830410003661
80th percentile: 1.336080598831177
90th percentile: 1.7876678943634035
95th percentile: 2.0134615421295163
99th percentile: 2.1940964603424074
mean time: 1.3327061653137207
Pipeline stage StressChecker completed in 7.78s
jellywibble-lora-120k-p_2801_v11 status is now deployed due to DeploymentManager action
jellywibble-lora-120k-p_2801_v11 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of jellywibble-lora-120k-p_2801_v11
Running pipeline stage ISVCDeleter
Checking if service jellywibble-lora-120k-p-2801-v11 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 5.22s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key jellywibble-lora-120k-p-2801-v11/config.json from bucket guanaco-mkml-models
Deleting key jellywibble-lora-120k-p-2801-v11/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key jellywibble-lora-120k-p-2801-v11/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key jellywibble-lora-120k-p-2801-v11/tokenizer.json from bucket guanaco-mkml-models
Deleting key jellywibble-lora-120k-p-2801-v11/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key jellywibble-lora-120k-p-2801-v11_reward/config.json from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-p-2801-v11_reward/merges.txt from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-p-2801-v11_reward/reward.tensors from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-p-2801-v11_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-p-2801-v11_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-p-2801-v11_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-p-2801-v11_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.90s
jellywibble-lora-120k-p_2801_v11 status is now torndown due to DeploymentManager action

Start Time:

End Time:

Step (in hours or minutes, e.g. 1h, 10m):

Usage Metrics

Latency Metrics

Model Developer	Developer Rank	Model Rank	Model Rank By Developer	Elo Rating	Elo Rating By Developer	Alignment Score	Alignment Samples	User Alignment Score	User Alignment Question Responses	Submission ID	Parameters	Huggingface Repository	Variant	Number of Battles	Number of Battles By Developer	Win Ratio	Win Ratio By Developer	Type	Best of	Max Input Tokens	Max Output Tokens	Model Architecture	Model Group	Date	Overall Norm	Elo Norm	Alignment Norm	User Alignment Norm	Alt Ranking	Alt Ranking By Developer	Elo Rank	Alignment Rank	Ranking Group	Thoughput	GPU Counts
zonemercy	1	1.0	1.0	1301.46	1301.46	4.3	30214	0.71	3122.0	zonemercy-graft-cogent-v_7573_v6	13B	zonemercy/Graft-Cogent-v1-Acute-Nemo-v0-5e6ep1	0815v1-7	30214	49287869	0.58	0.64	basic	16.0	512.0	64.0	MistralForCausalLM	zonemercy/Graft-Cogent-v	2024-08-15	2.01	2.29	1.5	0.24	2.0	1.0	2.0	41.0	single	0.94	{'NVIDIA RTX A5000': 1}
zonemercy	1	2.0	1.0	1292.84	1301.46	4.33	30926	0.73	3160.0	zonemercy-cogent-nemo-v1_3266_v8	13B	zonemercy/Cogent-Nemo-v1-1k1e5	0815v1-3	30926	49287869	0.56	0.64	basic	16.0	512.0	64.0	MistralForCausalLM	zonemercy/Cogent-Nemo-v1	2024-08-15	1.89	2.1	1.51	0.34	1.0	1.0	4.0	38.0	single	0.95	{'NVIDIA RTX A5000': 1}
zonemercy	1	3.0	1.0	1294.81	1301.46	4.09	11643	0.75	1177.0	zonemercy-cogent-nemo-v2-5e6_v13	13B	zonemercy/Cogent-Nemo-v2-5e6	0815v1-0	11643	49287869	0.57	0.64	basic	16.0	512.0	64.0	MistralForCausalLM	zonemercy/Cogent-Nemo-v2	2024-08-15	1.89	2.14	1.42	0.43	5.0	1.0	3.0	46.0	single
zonemercy	1	4.0	1.0	1273.7	1301.46	6.07	12026	0.67	1150.0	zonemercy-graft-cogent-v_7573_v2	13B	zonemercy/Graft-Cogent-v1-Acute-Nemo-v0-5e6ep1	zonemercy-graft-cogent-v_7573_v2	12026	49287869	0.58	0.64	basic	16.0	512.0	64.0	MistralForCausalLM	zonemercy/Graft-Cogent-v	2024-08-14	1.85	1.67	2.19	0.02	4.0	1.0	36.5	10.0	single
zonemercy	1	5.0	1.0	1270.85	1301.46	6.18	12379	0.68	1334.0	zonemercy-graft-cogent-v_7573_v5	13B	zonemercy/Graft-Cogent-v1-Acute-Nemo-v0-5e6ep1	zonemercy-graft-cogent-v_7573_v5	12379	49287869	0.56	0.64	basic	8.0	1024.0	64.0	MistralForCausalLM	zonemercy/Graft-Cogent-v	2024-08-14	1.83	1.61	2.23	0.06	11.0	1.0	54.0	8.0	single
zonemercy	1	6.0	1.0	1285.61	1301.46	4.44	30852	0.72	3156.0	zonemercy-graft-cogent-n_9815_v2	13B	zonemercy/Graft-Cogent-Nemo-v2.1-5e6	0815v1-8	30852	49287869	0.55	0.64	basic	16.0	512.0	64.0	MistralForCausalLM	zonemercy/Graft-Cogent-N	2024-08-15	1.8	1.94	1.56	0.28	3.0	1.0	12.0	33.0	single
zonemercy	1	7.0	1.0	1284.56	1301.46	4.42	28821	0.71	2895.0	zonemercy-graft-cogent-n_9815_v5	13B	zonemercy/Graft-Cogent-Nemo-v2.1-5e6	0815v1-3	28821	49287869	0.55	0.64	basic	16.0	512.0	64.0	MistralForCausalLM	zonemercy/Graft-Cogent-N	2024-08-15	1.79	1.91	1.55	0.25	6.0	1.0	15.0	36.0	single
zonemercy	1	8.0	1.0	1290.49	1301.46	3.68	10195	0.7	912.0	zonemercy-graft-cogent-v_7573_v7	13B	zonemercy/Graft-Cogent-v1-Acute-Nemo-v0-5e6ep1	0815v1-7	10195	49287869	0.57	0.64	basic	16.0	512.0	64.0	MistralForCausalLM	zonemercy/Graft-Cogent-v	2024-08-21	1.77	2.04	1.26	0.18	13.0	1.0	7.0	60.0	single
zonemercy	1	9.0	1.0	1269.88	1301.46	5.73	10662	0.68	1236.0	zonemercy-graft-cogent-v_7573_v4	13B	zonemercy/Graft-Cogent-v1-Acute-Nemo-v0-5e6ep1	zonemercy-graft-cogent-v_7573_v4	10662	49287869	0.56	0.64	basic	16.0	512.0	64.0	MistralForCausalLM	zonemercy/Graft-Cogent-v	2024-08-14	1.75	1.59	2.06	0.07	17.0	1.0	66.0	15.0	single
zonemercy	1	10.0	1.0	1284.52	1301.46	4.17	9822	0.72	899.0	zonemercy-cogent-nemo-v2-5e6_v14	13B	zonemercy/Cogent-Nemo-v2-5e6	0815v1-1	9822	49287869	0.56	0.64	basic	16.0	512.0	64.0	MistralForCausalLM	zonemercy/Cogent-Nemo-v2	2024-08-15	1.75	1.91	1.45	0.29	8.0	1.0	16.0	43.0	single
zonemercy	1	11.0	1.0	1269.02	1301.46	5.73	11079	0.7	1211.0	zonemercy-graft-cogent-v_7573_v3	13B	zonemercy/Graft-Cogent-v1-Acute-Nemo-v0-5e6ep1	zonemercy-graft-cogent-v_7573_v3	11079	49287869	0.56	0.64	basic	16.0	512.0	64.0	MistralForCausalLM	zonemercy/Graft-Cogent-v	2024-08-14	1.74	1.57	2.06	0.21	19.0	1.0	70.0	14.0	single
zonemercy	1	12.0	1.0	1278.53	1301.46	4.58	9715	0.68	893.0	zonemercy-lexical-nemo-_1518_v20	13B	zonemercy/Lexical-Nemo-v4-1k1e5	0815v2-0	9715	49287869	0.56	0.64	basic	16.0	512.0	64.0	MistralForCausalLM	zonemercy/Lexical-Nemo-v	2024-08-15	1.72	1.78	1.61	0.09	7.0	1.0	27.0	28.0	single
zonemercy	1	13.0	1.0	1280.15	1301.46	4.34	16560	0.7	1711.0	zonemercy-cogent-nemo-v2-5e6_v15	13B	zonemercy/Cogent-Nemo-v2-5e6	0815v1-2	16560	49287869	0.55	0.64	basic	8.0	1024.0	64.0	MistralForCausalLM	zonemercy/Cogent-Nemo-v2	2024-08-15	1.71	1.81	1.52	0.19	11.0	1.0	25.0	37.0	single
zonemercy	1	14.0	1.0	1277.75	1301.46	4.44	9736	0.71	904.0	zonemercy-acute-nemo-v1-_4488_v7	13B	zonemercy/Acute-Nemo-v1-1e5ep1	0815v1-2	9736	49287869	0.56	0.64	basic	16.0	512.0	64.0	MistralForCausalLM	zonemercy/Acute-Nemo-v1-	2024-08-15	1.69	1.76	1.56	0.24	11.0	1.0	28.0	34.0	single
zonemercy	1	15.0	1.0	1276.0	1301.46	4.51	9384	0.73	953.0	zonemercy-lexical-nemov8_5966_v4	13B	zonemercy/Lexical-Nemov8-1k1e5	0815v2-1	9384	49287869	0.56	0.64	basic	16.0	512.0	64.0	MistralForCausalLM	zonemercy/Lexical-Nemov8	2024-08-15	1.67	1.72	1.59	0.34	9.0	1.0	31.0	30.0	single
zonemercy	1	16.0	1.0	1280.76	1301.46	3.94	10939	0.75	985.0	zonemercy-lexical-nemov8_5966_v6	13B	zonemercy/Lexical-Nemov8-1k1e5	0815v2-3	10939	49287869	0.57	0.64	basic	16.0	512.0	64.0	MistralForCausalLM	zonemercy/Lexical-Nemov8	2024-08-16	1.66	1.83	1.36	0.44	15.0	1.0	22.0	54.0	single
zonemercy	1	17.0	1.0	1264.13	1301.46	5.71	13378	0.72	1224.0	zonemercy-cogent-nemo-v1_3266_v6	13B	zonemercy/Cogent-Nemo-v1-1k1e5	zonemercy-cogent-nemo-v1_3266_v6	13378	49287869	0.56	0.64	basic	8.0	1024.0	64.0	MistralForCausalLM	zonemercy/Cogent-Nemo-v1	2024-08-14	1.66	1.46	2.05	0.32	25.0	1.0	121.0	16.0	single
zonemercy	1	18.0	1.0	1271.01	1301.46	4.88	11842	0.67	1121.0	zonemercy-graft-cogent-v_7573_v1	13B	zonemercy/Graft-Cogent-v1-Acute-Nemo-v0-5e6ep1	0814v1-5	11842	49287869	0.56	0.64	basic	16.0	512.0	64.0	MistralForCausalLM	zonemercy/Graft-Cogent-v	2024-08-14	1.65	1.61	1.73	0.04	14.0	1.0	51.0	24.0	single
zonemercy	1	19.0	1.0	1256.9	1301.46	6.24	11538	0.7	1049.0	zonemercy-cogent-nemo-v1_4327_v4	13B	zonemercy/Cogent-Nemo-v1-1k1e5-ep1	zonemercy-cogent-nemo-v1_4327_v4	11538	49287869	0.54	0.64	basic	8.0	1024.0	64.0	MistralForCausalLM	zonemercy/Cogent-Nemo-v1	2024-08-10	1.63	1.3	2.25	0.17	39.0	1.0	240.0	7.0	single
zonemercy	1	20.0	1.0	1261.43	1301.46	5.68	13593	0.74	1206.0	zonemercy-cogent-nemo-v1_4327_v5	13B	zonemercy/Cogent-Nemo-v1-1k1e5-ep1	zonemercy-cogent-nemo-v1_4327_v5	13593	49287869	0.55	0.64	basic	8.0	1024.0	64.0	MistralForCausalLM	zonemercy/Cogent-Nemo-v1	2024-08-14	1.62	1.4	2.04	0.39	34.0	1.0	161.0	17.0	single
zonemercy	1	21.0	1.0	1272.13	1301.46	4.46	16913	0.73	1699.0	zonemercy-graft-cogent-n_9815_v9	13B	zonemercy/Graft-Cogent-Nemo-v2.1-5e6	0815v1-3	16913	49287869	0.54	0.64	basic	8.0	1024.0	64.0	MistralForCausalLM	zonemercy/Graft-Cogent-N	2024-08-15	1.61	1.64	1.56	0.36	16.0	1.0	45.5	32.0	single
zonemercy	1	22.0	1.0	1277.43	1301.46	3.74	10445	0.76	907.0	zonemercy-lexical-nemo-_1518_v22	13B	zonemercy/Lexical-Nemo-v4-1k1e5	0815v2-2	10445	49287869	0.56	0.64	basic	16.0	512.0	64.0	MistralForCausalLM	zonemercy/Lexical-Nemo-v	2024-08-16	1.59	1.75	1.28	0.49	20.0	1.0	29.0	58.0	single
zonemercy	1	23.0	1.0	1273.46	1301.46	4.12	10476	0.7	958.0	zonemercy-lexical-nemo-_1518_v21	13B	zonemercy/Lexical-Nemo-v4-1k1e5	0815v2-0	10476	49287869	0.55	0.64	basic	8.0	1024.0	64.0	MistralForCausalLM	zonemercy/Lexical-Nemo-v	2024-08-16	1.58	1.67	1.43	0.17	18.0	1.0	38.0	45.0	single
zonemercy	1	24.0	1.0	1270.37	1301.46	4.44	9935	0.72	1002.0	zonemercy-acute-nemo-v1-_4488_v6	13B	zonemercy/Acute-Nemo-v1-1e5ep1	0815v1-1	9935	49287869	0.55	0.64	basic	16.0	512.0	64.0	MistralForCausalLM	zonemercy/Acute-Nemo-v1-	2024-08-15	1.58	1.6	1.56	0.31	21.0	1.0	59.0	35.0	single
zonemercy	1	25.0	1.0	1268.9	1301.46	4.47	9890	0.73	1015.0	zonemercy-lexical-nemov8_5966_v8	13B	zonemercy/Lexical-Nemov8-1k1e5	0815v2-1	9890	49287869	0.55	0.64	basic	8.0	1024.0	64.0	MistralForCausalLM	zonemercy/Lexical-Nemov8	2024-08-21	1.57	1.56	1.57	0.34	22.0	1.0	72.5	31.0	single
zonemercy	1	26.0	1.0	1253.1	1301.46	6.09	9499	0.71	1087.0	zonemercy-acute-nemo-v1-_4488_v3	13B	zonemercy/Acute-Nemo-v1-1e5ep1	zonemercy-acute-nemo-v1-_4488_v3	9499	49287869	0.54	0.64	basic	16.0	512.0	64.0	MistralForCausalLM	zonemercy/Acute-Nemo-v1-	2024-08-14	1.56	1.21	2.2	0.26	48.0	1.0	308.0	9.0	single
zonemercy	1	27.0	1.0	1269.68	1301.46	4.31	10233	0.73	960.0	zonemercy-graft-virgo-v1_3528_v1	13B	zonemercy/Graft-Virgo-v1-Acute-v1	zonemercy-graft-virgo-v1_3528_v1	10233	49287869	0.55	0.64	basic	8.0	1024.0	64.0	MistralForCausalLM	zonemercy/Graft-Virgo-v1	2024-08-21	1.56	1.58	1.51	0.34	23.5	1.0	67.0	40.0	single
zonemercy	1	28.0	1.0	1270.72	1301.46	4.03	10540	0.74	966.0	zonemercy-lexical-nemov8_5966_v5	13B	zonemercy/Lexical-Nemov8-1k1e5	0815v2-1	10540	49287869	0.55	0.64	basic	8.0	1024.0	64.0	MistralForCausalLM	zonemercy/Lexical-Nemov8	2024-08-16	1.53	1.61	1.4	0.41	23.5	1.0	55.0	52.0	single
zonemercy	1	29.0	1.0	1256.33	1301.46	5.55	9360	0.69	891.0	zonemercy-cogent-nemo-v1_3266_v7	13B	zonemercy/Cogent-Nemo-v1-1k1e5	0814v1-7	9360	49287869	0.54	0.64	basic	16.0	512.0	64.0	MistralForCausalLM	zonemercy/Cogent-Nemo-v1	2024-08-14	1.53	1.29	1.99	0.13	42.0	1.0	250.0	20.0	single
zonemercy	1	30.0	1.0	1292.06	1301.46	1.72	106640	0.71	11368.0	zonemercy-cogent-nemo-v2-5e6_v18	13B	zonemercy/Cogent-Nemo-v2-5e6	0815v3-2	106640	49287869	0.5	0.64	basic	16.0	1024.0	64.0	MistralForCausalLM	zonemercy/Cogent-Nemo-v2	2024-08-16	1.53	2.08	0.5	0.26	31.0	1.0	5.0	161.0	single
zonemercy	1	31.0	1.0	1291.25	1301.46	1.77	108706	0.71	10227.0	zonemercy-cogent-nemo-v2-5e6_v17	13B	zonemercy/Cogent-Nemo-v2-5e6	0815v3-2	108706	49287869	0.5	0.64	basic	16.0	1024.0	64.0	MistralForCausalLM	zonemercy/Cogent-Nemo-v2	2024-08-16	1.52	2.06	0.52	0.23	30.0	1.0	6.0	156.0	single
zonemercy	1	32.0	1.0	1248.17	1301.46	6.26	165840	0.73	16061.0	zonemercy-lexical-nemov8_5966_v1	13B	zonemercy/Lexical-Nemov8-1k1e5	0805v2-4	175556	49287869	0.54	0.64	basic	4.0	1024.0	64.0	MistralForCausalLM	zonemercy/Lexical-Nemov8	2024-08-05	1.51	1.11	2.26	0.33	62.0	1.0	397.5	6.0	single
chai_backend_admin	2	33.0	33.0	1303.02	1303.02	0.01	5613	0.72	1655.0	blend_porer_2024-07-23	n/a		fourier-routed_blend	18746	210525784	0.63	1.0	routed_blend						2024-07-23	1.45	2.32	-0.16	0.29	57.0	28.0	1.0	389.0	blended
chai_backend_admin	2	34.0	33.0	1266.28	1303.02	3.88	10609	0.74	984.0	blend_domul_2024-08-22	n/a		blend_domul_2024-08-22	10609	210525784	0.54	1.0	blend						2024-08-21	1.45	1.51	1.34	0.38	28.0	28.0	96.0	55.0	blended
zonemercy	1	35.0	1.0	1256.36	1301.46	4.81	9553	0.71	830.0	zonemercy-lexical-nemov8_5966_v7	13B	zonemercy/Lexical-Nemov8-1k1e5	0815v2-1	9553	49287869	0.53	0.64	basic	8.0	1024.0	64.0	MistralForCausalLM	zonemercy/Lexical-Nemov8	2024-08-20	1.43	1.29	1.7	0.23	43.0	1.0	248.0	26.0	single
zonemercy	1	36.0	1.0	1248.17	1301.46	5.59	12094	0.68	1111.0	zonemercy-graft-cogent-v_3240_v1	13B	zonemercy/Graft-Cogent-v1-Acute-Nemo-v1-1e5ep1	0814v1-6	12094	49287869	0.53	0.64	basic	16.0	512.0	64.0	MistralForCausalLM	zonemercy/Graft-Cogent-v	2024-08-14	1.42	1.11	2.0	0.07	64.0	1.0	397.5	18.0	single
zonemercy	1	37.0	1.0	1268.95	1301.46	3.31	10529	0.73	1021.0	zonemercy-graft-virgo-v1_16_v1	13B	zonemercy/Graft-Virgo-v1-base-v1	zonemercy-graft-virgo-v1_16_v1	10529	49287869	0.55	0.64	basic	8.0	1024.0	64.0	MistralForCausalLM	zonemercy/Graft-Virgo-v1	2024-08-22	1.41	1.57	1.12	0.34	26.0	1.0	71.0	72.0	single
zonemercy	1	38.0	1.0	1280.35	1301.46	2.08	153293	0.72	14605.0	zonemercy-acute-nemo-v1-_4488_v4	13B	zonemercy/Acute-Nemo-v1-1e5ep1	0815v1-1	153293	49287869	0.51	0.64	basic	16.0	512.0	64.0	MistralForCausalLM	zonemercy/Acute-Nemo-v1-	2024-08-15	1.41	1.82	0.64	0.28	27.0	1.0	23.0	127.0	single
zonemercy	1	39.0	1.0	1248.93	1301.46	5.38	12373	0.71	1412.0	zonemercy-acute-nemo-v1-_4488_v1	13B	zonemercy/Acute-Nemo-v1-1e5ep1	0814v1-2	12373	49287869	0.53	0.64	basic	16.0	512.0	64.0	MistralForCausalLM	zonemercy/Acute-Nemo-v1-	2024-08-14	1.4	1.12	1.92	0.26	60.0	1.0	378.0	21.0	single
zonemercy	1	40.0	1.0	1279.87	1301.46	2.07	152943	0.72	14466.0	zonemercy-acute-nemo-v1-_4488_v5	13B	zonemercy/Acute-Nemo-v1-1e5ep1	0815v1-2	152943	49287869	0.51	0.64	basic	16.0	512.0	64.0	MistralForCausalLM	zonemercy/Acute-Nemo-v1-	2024-08-15	1.4	1.81	0.64	0.27	29.0	1.0	26.0	131.0	single