Hamanasu-4B-Instruct

1
2
llama
by
Delta-Vector
Other
OTHER
4B params
New
1 downloads
Early-stage
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
9GB+ RAM
Mobile
Laptop
Server
Quick Summary

html, body { background: black; color: #c9d1d9 !

Device Compatibility

Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
4GB+ RAM

Code Examples

Axolotl Config ꒰(˶• ᴗ •˶)꒱yaml
base_model: NewEden_4B-PT
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

  #hub_model_id: NewEden/4B-Inst
  #hub_strategy: "all_checkpoints"
  #push_dataset_to_hub:
  #hf_use_auth_token: true

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/Helpsteer-3-Filtered
    type: dan-chat-advanced
  - path: NewEden/GSM8K-R1-filtered
    type: dan-chat-advanced
  - path: NewEden/Hydrus-R1-Thinking-Sharegpt
    type: dan-chat-advanced
  - path: NewEden/Hydrus-SonnetOrca
    type: dan-chat-advanced
  - path: NewEden/Hydrus-HelpSteer2
    type: dan-chat-advanced
  - path: NewEden/Claude-Instruct-5K
    type: dan-chat-advanced
  - path: PocketDoc/Dans-MemoryCore-CoreCurriculum-Small
    type: dan-chat-advanced
  - path: Nitral-AI/ARES-ShareGPT
    type: dan-chat-advanced 
  - path: NewEden/Hydrus-Instruct-SmolTalk
    type: dan-chat-advanced
  - path: NewEden/Hydrus-Chat_error-Pure-Dove-sharegpt
    type: dan-chat-advanced  
  - path: NewEden/Claude-Instruct-2.7K
    type: dan-chat-advanced 
  - path: PocketDoc/Dans-Assistantmaxx-Tulu3-IF
    type: dan-chat-advanced  
dataset_prepared_path: prepared_data
val_set_size: 0.0
output_dir: ./4b-inst-r2

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true


wandb_project: 4B-mng
wandb_entity:
wandb_watch:
wandb_name: attempt-2
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 1
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 5e-6
max_grad_norm: 0.2

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 40
saves_per_epoch: 2
debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.02
fsdp:
fsdp_config:
special_tokens:
  pad_token: <|finetune_right_pad_id|>
Axolotl Config ꒰(˶• ᴗ •˶)꒱yaml
base_model: NewEden_4B-PT
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

  #hub_model_id: NewEden/4B-Inst
  #hub_strategy: "all_checkpoints"
  #push_dataset_to_hub:
  #hf_use_auth_token: true

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/Helpsteer-3-Filtered
    type: dan-chat-advanced
  - path: NewEden/GSM8K-R1-filtered
    type: dan-chat-advanced
  - path: NewEden/Hydrus-R1-Thinking-Sharegpt
    type: dan-chat-advanced
  - path: NewEden/Hydrus-SonnetOrca
    type: dan-chat-advanced
  - path: NewEden/Hydrus-HelpSteer2
    type: dan-chat-advanced
  - path: NewEden/Claude-Instruct-5K
    type: dan-chat-advanced
  - path: PocketDoc/Dans-MemoryCore-CoreCurriculum-Small
    type: dan-chat-advanced
  - path: Nitral-AI/ARES-ShareGPT
    type: dan-chat-advanced 
  - path: NewEden/Hydrus-Instruct-SmolTalk
    type: dan-chat-advanced
  - path: NewEden/Hydrus-Chat_error-Pure-Dove-sharegpt
    type: dan-chat-advanced  
  - path: NewEden/Claude-Instruct-2.7K
    type: dan-chat-advanced 
  - path: PocketDoc/Dans-Assistantmaxx-Tulu3-IF
    type: dan-chat-advanced  
dataset_prepared_path: prepared_data
val_set_size: 0.0
output_dir: ./4b-inst-r2

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true


wandb_project: 4B-mng
wandb_entity:
wandb_watch:
wandb_name: attempt-2
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 1
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 5e-6
max_grad_norm: 0.2

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 40
saves_per_epoch: 2
debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.02
fsdp:
fsdp_config:
special_tokens:
  pad_token: <|finetune_right_pad_id|>
Axolotl Config ꒰(˶• ᴗ •˶)꒱yaml
base_model: NewEden_4B-PT
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

  #hub_model_id: NewEden/4B-Inst
  #hub_strategy: "all_checkpoints"
  #push_dataset_to_hub:
  #hf_use_auth_token: true

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/Helpsteer-3-Filtered
    type: dan-chat-advanced
  - path: NewEden/GSM8K-R1-filtered
    type: dan-chat-advanced
  - path: NewEden/Hydrus-R1-Thinking-Sharegpt
    type: dan-chat-advanced
  - path: NewEden/Hydrus-SonnetOrca
    type: dan-chat-advanced
  - path: NewEden/Hydrus-HelpSteer2
    type: dan-chat-advanced
  - path: NewEden/Claude-Instruct-5K
    type: dan-chat-advanced
  - path: PocketDoc/Dans-MemoryCore-CoreCurriculum-Small
    type: dan-chat-advanced
  - path: Nitral-AI/ARES-ShareGPT
    type: dan-chat-advanced 
  - path: NewEden/Hydrus-Instruct-SmolTalk
    type: dan-chat-advanced
  - path: NewEden/Hydrus-Chat_error-Pure-Dove-sharegpt
    type: dan-chat-advanced  
  - path: NewEden/Claude-Instruct-2.7K
    type: dan-chat-advanced 
  - path: PocketDoc/Dans-Assistantmaxx-Tulu3-IF
    type: dan-chat-advanced  
dataset_prepared_path: prepared_data
val_set_size: 0.0
output_dir: ./4b-inst-r2

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true


wandb_project: 4B-mng
wandb_entity:
wandb_watch:
wandb_name: attempt-2
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 1
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 5e-6
max_grad_norm: 0.2

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 40
saves_per_epoch: 2
debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.02
fsdp:
fsdp_config:
special_tokens:
  pad_token: <|finetune_right_pad_id|>
Axolotl Config ꒰(˶• ᴗ •˶)꒱yaml
base_model: NewEden_4B-PT
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

  #hub_model_id: NewEden/4B-Inst
  #hub_strategy: "all_checkpoints"
  #push_dataset_to_hub:
  #hf_use_auth_token: true

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/Helpsteer-3-Filtered
    type: dan-chat-advanced
  - path: NewEden/GSM8K-R1-filtered
    type: dan-chat-advanced
  - path: NewEden/Hydrus-R1-Thinking-Sharegpt
    type: dan-chat-advanced
  - path: NewEden/Hydrus-SonnetOrca
    type: dan-chat-advanced
  - path: NewEden/Hydrus-HelpSteer2
    type: dan-chat-advanced
  - path: NewEden/Claude-Instruct-5K
    type: dan-chat-advanced
  - path: PocketDoc/Dans-MemoryCore-CoreCurriculum-Small
    type: dan-chat-advanced
  - path: Nitral-AI/ARES-ShareGPT
    type: dan-chat-advanced 
  - path: NewEden/Hydrus-Instruct-SmolTalk
    type: dan-chat-advanced
  - path: NewEden/Hydrus-Chat_error-Pure-Dove-sharegpt
    type: dan-chat-advanced  
  - path: NewEden/Claude-Instruct-2.7K
    type: dan-chat-advanced 
  - path: PocketDoc/Dans-Assistantmaxx-Tulu3-IF
    type: dan-chat-advanced  
dataset_prepared_path: prepared_data
val_set_size: 0.0
output_dir: ./4b-inst-r2

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true


wandb_project: 4B-mng
wandb_entity:
wandb_watch:
wandb_name: attempt-2
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 1
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 5e-6
max_grad_norm: 0.2

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 40
saves_per_epoch: 2
debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.02
fsdp:
fsdp_config:
special_tokens:
  pad_token: <|finetune_right_pad_id|>
Axolotl Config ꒰(˶• ᴗ •˶)꒱yaml
base_model: NewEden_4B-PT
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

  #hub_model_id: NewEden/4B-Inst
  #hub_strategy: "all_checkpoints"
  #push_dataset_to_hub:
  #hf_use_auth_token: true

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/Helpsteer-3-Filtered
    type: dan-chat-advanced
  - path: NewEden/GSM8K-R1-filtered
    type: dan-chat-advanced
  - path: NewEden/Hydrus-R1-Thinking-Sharegpt
    type: dan-chat-advanced
  - path: NewEden/Hydrus-SonnetOrca
    type: dan-chat-advanced
  - path: NewEden/Hydrus-HelpSteer2
    type: dan-chat-advanced
  - path: NewEden/Claude-Instruct-5K
    type: dan-chat-advanced
  - path: PocketDoc/Dans-MemoryCore-CoreCurriculum-Small
    type: dan-chat-advanced
  - path: Nitral-AI/ARES-ShareGPT
    type: dan-chat-advanced 
  - path: NewEden/Hydrus-Instruct-SmolTalk
    type: dan-chat-advanced
  - path: NewEden/Hydrus-Chat_error-Pure-Dove-sharegpt
    type: dan-chat-advanced  
  - path: NewEden/Claude-Instruct-2.7K
    type: dan-chat-advanced 
  - path: PocketDoc/Dans-Assistantmaxx-Tulu3-IF
    type: dan-chat-advanced  
dataset_prepared_path: prepared_data
val_set_size: 0.0
output_dir: ./4b-inst-r2

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true


wandb_project: 4B-mng
wandb_entity:
wandb_watch:
wandb_name: attempt-2
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 1
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 5e-6
max_grad_norm: 0.2

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 40
saves_per_epoch: 2
debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.02
fsdp:
fsdp_config:
special_tokens:
  pad_token: <|finetune_right_pad_id|>
Axolotl Config ꒰(˶• ᴗ •˶)꒱yaml
base_model: NewEden_4B-PT
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

  #hub_model_id: NewEden/4B-Inst
  #hub_strategy: "all_checkpoints"
  #push_dataset_to_hub:
  #hf_use_auth_token: true

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/Helpsteer-3-Filtered
    type: dan-chat-advanced
  - path: NewEden/GSM8K-R1-filtered
    type: dan-chat-advanced
  - path: NewEden/Hydrus-R1-Thinking-Sharegpt
    type: dan-chat-advanced
  - path: NewEden/Hydrus-SonnetOrca
    type: dan-chat-advanced
  - path: NewEden/Hydrus-HelpSteer2
    type: dan-chat-advanced
  - path: NewEden/Claude-Instruct-5K
    type: dan-chat-advanced
  - path: PocketDoc/Dans-MemoryCore-CoreCurriculum-Small
    type: dan-chat-advanced
  - path: Nitral-AI/ARES-ShareGPT
    type: dan-chat-advanced 
  - path: NewEden/Hydrus-Instruct-SmolTalk
    type: dan-chat-advanced
  - path: NewEden/Hydrus-Chat_error-Pure-Dove-sharegpt
    type: dan-chat-advanced  
  - path: NewEden/Claude-Instruct-2.7K
    type: dan-chat-advanced 
  - path: PocketDoc/Dans-Assistantmaxx-Tulu3-IF
    type: dan-chat-advanced  
dataset_prepared_path: prepared_data
val_set_size: 0.0
output_dir: ./4b-inst-r2

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true


wandb_project: 4B-mng
wandb_entity:
wandb_watch:
wandb_name: attempt-2
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 1
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 5e-6
max_grad_norm: 0.2

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 40
saves_per_epoch: 2
debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.02
fsdp:
fsdp_config:
special_tokens:
  pad_token: <|finetune_right_pad_id|>
Axolotl Config ꒰(˶• ᴗ •˶)꒱yaml
base_model: NewEden_4B-PT
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

  #hub_model_id: NewEden/4B-Inst
  #hub_strategy: "all_checkpoints"
  #push_dataset_to_hub:
  #hf_use_auth_token: true

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/Helpsteer-3-Filtered
    type: dan-chat-advanced
  - path: NewEden/GSM8K-R1-filtered
    type: dan-chat-advanced
  - path: NewEden/Hydrus-R1-Thinking-Sharegpt
    type: dan-chat-advanced
  - path: NewEden/Hydrus-SonnetOrca
    type: dan-chat-advanced
  - path: NewEden/Hydrus-HelpSteer2
    type: dan-chat-advanced
  - path: NewEden/Claude-Instruct-5K
    type: dan-chat-advanced
  - path: PocketDoc/Dans-MemoryCore-CoreCurriculum-Small
    type: dan-chat-advanced
  - path: Nitral-AI/ARES-ShareGPT
    type: dan-chat-advanced 
  - path: NewEden/Hydrus-Instruct-SmolTalk
    type: dan-chat-advanced
  - path: NewEden/Hydrus-Chat_error-Pure-Dove-sharegpt
    type: dan-chat-advanced  
  - path: NewEden/Claude-Instruct-2.7K
    type: dan-chat-advanced 
  - path: PocketDoc/Dans-Assistantmaxx-Tulu3-IF
    type: dan-chat-advanced  
dataset_prepared_path: prepared_data
val_set_size: 0.0
output_dir: ./4b-inst-r2

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true


wandb_project: 4B-mng
wandb_entity:
wandb_watch:
wandb_name: attempt-2
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 1
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 5e-6
max_grad_norm: 0.2

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 40
saves_per_epoch: 2
debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.02
fsdp:
fsdp_config:
special_tokens:
  pad_token: <|finetune_right_pad_id|>
Axolotl Config ꒰(˶• ᴗ •˶)꒱yaml
base_model: NewEden_4B-PT
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

  #hub_model_id: NewEden/4B-Inst
  #hub_strategy: "all_checkpoints"
  #push_dataset_to_hub:
  #hf_use_auth_token: true

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/Helpsteer-3-Filtered
    type: dan-chat-advanced
  - path: NewEden/GSM8K-R1-filtered
    type: dan-chat-advanced
  - path: NewEden/Hydrus-R1-Thinking-Sharegpt
    type: dan-chat-advanced
  - path: NewEden/Hydrus-SonnetOrca
    type: dan-chat-advanced
  - path: NewEden/Hydrus-HelpSteer2
    type: dan-chat-advanced
  - path: NewEden/Claude-Instruct-5K
    type: dan-chat-advanced
  - path: PocketDoc/Dans-MemoryCore-CoreCurriculum-Small
    type: dan-chat-advanced
  - path: Nitral-AI/ARES-ShareGPT
    type: dan-chat-advanced 
  - path: NewEden/Hydrus-Instruct-SmolTalk
    type: dan-chat-advanced
  - path: NewEden/Hydrus-Chat_error-Pure-Dove-sharegpt
    type: dan-chat-advanced  
  - path: NewEden/Claude-Instruct-2.7K
    type: dan-chat-advanced 
  - path: PocketDoc/Dans-Assistantmaxx-Tulu3-IF
    type: dan-chat-advanced  
dataset_prepared_path: prepared_data
val_set_size: 0.0
output_dir: ./4b-inst-r2

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true


wandb_project: 4B-mng
wandb_entity:
wandb_watch:
wandb_name: attempt-2
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 1
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 5e-6
max_grad_norm: 0.2

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 40
saves_per_epoch: 2
debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.02
fsdp:
fsdp_config:
special_tokens:
  pad_token: <|finetune_right_pad_id|>
Axolotl Config ꒰(˶• ᴗ •˶)꒱yaml
base_model: NewEden_4B-PT
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

  #hub_model_id: NewEden/4B-Inst
  #hub_strategy: "all_checkpoints"
  #push_dataset_to_hub:
  #hf_use_auth_token: true

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/Helpsteer-3-Filtered
    type: dan-chat-advanced
  - path: NewEden/GSM8K-R1-filtered
    type: dan-chat-advanced
  - path: NewEden/Hydrus-R1-Thinking-Sharegpt
    type: dan-chat-advanced
  - path: NewEden/Hydrus-SonnetOrca
    type: dan-chat-advanced
  - path: NewEden/Hydrus-HelpSteer2
    type: dan-chat-advanced
  - path: NewEden/Claude-Instruct-5K
    type: dan-chat-advanced
  - path: PocketDoc/Dans-MemoryCore-CoreCurriculum-Small
    type: dan-chat-advanced
  - path: Nitral-AI/ARES-ShareGPT
    type: dan-chat-advanced 
  - path: NewEden/Hydrus-Instruct-SmolTalk
    type: dan-chat-advanced
  - path: NewEden/Hydrus-Chat_error-Pure-Dove-sharegpt
    type: dan-chat-advanced  
  - path: NewEden/Claude-Instruct-2.7K
    type: dan-chat-advanced 
  - path: PocketDoc/Dans-Assistantmaxx-Tulu3-IF
    type: dan-chat-advanced  
dataset_prepared_path: prepared_data
val_set_size: 0.0
output_dir: ./4b-inst-r2

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true


wandb_project: 4B-mng
wandb_entity:
wandb_watch:
wandb_name: attempt-2
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 1
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 5e-6
max_grad_norm: 0.2

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 40
saves_per_epoch: 2
debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.02
fsdp:
fsdp_config:
special_tokens:
  pad_token: <|finetune_right_pad_id|>
Axolotl Config ꒰(˶• ᴗ •˶)꒱yaml
base_model: NewEden_4B-PT
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

  #hub_model_id: NewEden/4B-Inst
  #hub_strategy: "all_checkpoints"
  #push_dataset_to_hub:
  #hf_use_auth_token: true

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/Helpsteer-3-Filtered
    type: dan-chat-advanced
  - path: NewEden/GSM8K-R1-filtered
    type: dan-chat-advanced
  - path: NewEden/Hydrus-R1-Thinking-Sharegpt
    type: dan-chat-advanced
  - path: NewEden/Hydrus-SonnetOrca
    type: dan-chat-advanced
  - path: NewEden/Hydrus-HelpSteer2
    type: dan-chat-advanced
  - path: NewEden/Claude-Instruct-5K
    type: dan-chat-advanced
  - path: PocketDoc/Dans-MemoryCore-CoreCurriculum-Small
    type: dan-chat-advanced
  - path: Nitral-AI/ARES-ShareGPT
    type: dan-chat-advanced 
  - path: NewEden/Hydrus-Instruct-SmolTalk
    type: dan-chat-advanced
  - path: NewEden/Hydrus-Chat_error-Pure-Dove-sharegpt
    type: dan-chat-advanced  
  - path: NewEden/Claude-Instruct-2.7K
    type: dan-chat-advanced 
  - path: PocketDoc/Dans-Assistantmaxx-Tulu3-IF
    type: dan-chat-advanced  
dataset_prepared_path: prepared_data
val_set_size: 0.0
output_dir: ./4b-inst-r2

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true


wandb_project: 4B-mng
wandb_entity:
wandb_watch:
wandb_name: attempt-2
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 1
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 5e-6
max_grad_norm: 0.2

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 40
saves_per_epoch: 2
debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.02
fsdp:
fsdp_config:
special_tokens:
  pad_token: <|finetune_right_pad_id|>
Axolotl Config ꒰(˶• ᴗ •˶)꒱yaml
base_model: NewEden_4B-PT
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

  #hub_model_id: NewEden/4B-Inst
  #hub_strategy: "all_checkpoints"
  #push_dataset_to_hub:
  #hf_use_auth_token: true

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/Helpsteer-3-Filtered
    type: dan-chat-advanced
  - path: NewEden/GSM8K-R1-filtered
    type: dan-chat-advanced
  - path: NewEden/Hydrus-R1-Thinking-Sharegpt
    type: dan-chat-advanced
  - path: NewEden/Hydrus-SonnetOrca
    type: dan-chat-advanced
  - path: NewEden/Hydrus-HelpSteer2
    type: dan-chat-advanced
  - path: NewEden/Claude-Instruct-5K
    type: dan-chat-advanced
  - path: PocketDoc/Dans-MemoryCore-CoreCurriculum-Small
    type: dan-chat-advanced
  - path: Nitral-AI/ARES-ShareGPT
    type: dan-chat-advanced 
  - path: NewEden/Hydrus-Instruct-SmolTalk
    type: dan-chat-advanced
  - path: NewEden/Hydrus-Chat_error-Pure-Dove-sharegpt
    type: dan-chat-advanced  
  - path: NewEden/Claude-Instruct-2.7K
    type: dan-chat-advanced 
  - path: PocketDoc/Dans-Assistantmaxx-Tulu3-IF
    type: dan-chat-advanced  
dataset_prepared_path: prepared_data
val_set_size: 0.0
output_dir: ./4b-inst-r2

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true


wandb_project: 4B-mng
wandb_entity:
wandb_watch:
wandb_name: attempt-2
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 1
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 5e-6
max_grad_norm: 0.2

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 40
saves_per_epoch: 2
debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.02
fsdp:
fsdp_config:
special_tokens:
  pad_token: <|finetune_right_pad_id|>
Axolotl Config ꒰(˶• ᴗ •˶)꒱yaml
base_model: NewEden_4B-PT
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

  #hub_model_id: NewEden/4B-Inst
  #hub_strategy: "all_checkpoints"
  #push_dataset_to_hub:
  #hf_use_auth_token: true

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/Helpsteer-3-Filtered
    type: dan-chat-advanced
  - path: NewEden/GSM8K-R1-filtered
    type: dan-chat-advanced
  - path: NewEden/Hydrus-R1-Thinking-Sharegpt
    type: dan-chat-advanced
  - path: NewEden/Hydrus-SonnetOrca
    type: dan-chat-advanced
  - path: NewEden/Hydrus-HelpSteer2
    type: dan-chat-advanced
  - path: NewEden/Claude-Instruct-5K
    type: dan-chat-advanced
  - path: PocketDoc/Dans-MemoryCore-CoreCurriculum-Small
    type: dan-chat-advanced
  - path: Nitral-AI/ARES-ShareGPT
    type: dan-chat-advanced 
  - path: NewEden/Hydrus-Instruct-SmolTalk
    type: dan-chat-advanced
  - path: NewEden/Hydrus-Chat_error-Pure-Dove-sharegpt
    type: dan-chat-advanced  
  - path: NewEden/Claude-Instruct-2.7K
    type: dan-chat-advanced 
  - path: PocketDoc/Dans-Assistantmaxx-Tulu3-IF
    type: dan-chat-advanced  
dataset_prepared_path: prepared_data
val_set_size: 0.0
output_dir: ./4b-inst-r2

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true


wandb_project: 4B-mng
wandb_entity:
wandb_watch:
wandb_name: attempt-2
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 1
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 5e-6
max_grad_norm: 0.2

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 40
saves_per_epoch: 2
debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.02
fsdp:
fsdp_config:
special_tokens:
  pad_token: <|finetune_right_pad_id|>
Axolotl Config ꒰(˶• ᴗ •˶)꒱yaml
base_model: NewEden_4B-PT
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

  #hub_model_id: NewEden/4B-Inst
  #hub_strategy: "all_checkpoints"
  #push_dataset_to_hub:
  #hf_use_auth_token: true

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/Helpsteer-3-Filtered
    type: dan-chat-advanced
  - path: NewEden/GSM8K-R1-filtered
    type: dan-chat-advanced
  - path: NewEden/Hydrus-R1-Thinking-Sharegpt
    type: dan-chat-advanced
  - path: NewEden/Hydrus-SonnetOrca
    type: dan-chat-advanced
  - path: NewEden/Hydrus-HelpSteer2
    type: dan-chat-advanced
  - path: NewEden/Claude-Instruct-5K
    type: dan-chat-advanced
  - path: PocketDoc/Dans-MemoryCore-CoreCurriculum-Small
    type: dan-chat-advanced
  - path: Nitral-AI/ARES-ShareGPT
    type: dan-chat-advanced 
  - path: NewEden/Hydrus-Instruct-SmolTalk
    type: dan-chat-advanced
  - path: NewEden/Hydrus-Chat_error-Pure-Dove-sharegpt
    type: dan-chat-advanced  
  - path: NewEden/Claude-Instruct-2.7K
    type: dan-chat-advanced 
  - path: PocketDoc/Dans-Assistantmaxx-Tulu3-IF
    type: dan-chat-advanced  
dataset_prepared_path: prepared_data
val_set_size: 0.0
output_dir: ./4b-inst-r2

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true


wandb_project: 4B-mng
wandb_entity:
wandb_watch:
wandb_name: attempt-2
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 1
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 5e-6
max_grad_norm: 0.2

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 40
saves_per_epoch: 2
debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.02
fsdp:
fsdp_config:
special_tokens:
  pad_token: <|finetune_right_pad_id|>
Axolotl Config ꒰(˶• ᴗ •˶)꒱yaml
base_model: NewEden_4B-PT
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

  #hub_model_id: NewEden/4B-Inst
  #hub_strategy: "all_checkpoints"
  #push_dataset_to_hub:
  #hf_use_auth_token: true

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/Helpsteer-3-Filtered
    type: dan-chat-advanced
  - path: NewEden/GSM8K-R1-filtered
    type: dan-chat-advanced
  - path: NewEden/Hydrus-R1-Thinking-Sharegpt
    type: dan-chat-advanced
  - path: NewEden/Hydrus-SonnetOrca
    type: dan-chat-advanced
  - path: NewEden/Hydrus-HelpSteer2
    type: dan-chat-advanced
  - path: NewEden/Claude-Instruct-5K
    type: dan-chat-advanced
  - path: PocketDoc/Dans-MemoryCore-CoreCurriculum-Small
    type: dan-chat-advanced
  - path: Nitral-AI/ARES-ShareGPT
    type: dan-chat-advanced 
  - path: NewEden/Hydrus-Instruct-SmolTalk
    type: dan-chat-advanced
  - path: NewEden/Hydrus-Chat_error-Pure-Dove-sharegpt
    type: dan-chat-advanced  
  - path: NewEden/Claude-Instruct-2.7K
    type: dan-chat-advanced 
  - path: PocketDoc/Dans-Assistantmaxx-Tulu3-IF
    type: dan-chat-advanced  
dataset_prepared_path: prepared_data
val_set_size: 0.0
output_dir: ./4b-inst-r2

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true


wandb_project: 4B-mng
wandb_entity:
wandb_watch:
wandb_name: attempt-2
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 1
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 5e-6
max_grad_norm: 0.2

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 40
saves_per_epoch: 2
debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.02
fsdp:
fsdp_config:
special_tokens:
  pad_token: <|finetune_right_pad_id|>
Axolotl Config ꒰(˶• ᴗ •˶)꒱yaml
base_model: NewEden_4B-PT
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

  #hub_model_id: NewEden/4B-Inst
  #hub_strategy: "all_checkpoints"
  #push_dataset_to_hub:
  #hf_use_auth_token: true

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/Helpsteer-3-Filtered
    type: dan-chat-advanced
  - path: NewEden/GSM8K-R1-filtered
    type: dan-chat-advanced
  - path: NewEden/Hydrus-R1-Thinking-Sharegpt
    type: dan-chat-advanced
  - path: NewEden/Hydrus-SonnetOrca
    type: dan-chat-advanced
  - path: NewEden/Hydrus-HelpSteer2
    type: dan-chat-advanced
  - path: NewEden/Claude-Instruct-5K
    type: dan-chat-advanced
  - path: PocketDoc/Dans-MemoryCore-CoreCurriculum-Small
    type: dan-chat-advanced
  - path: Nitral-AI/ARES-ShareGPT
    type: dan-chat-advanced 
  - path: NewEden/Hydrus-Instruct-SmolTalk
    type: dan-chat-advanced
  - path: NewEden/Hydrus-Chat_error-Pure-Dove-sharegpt
    type: dan-chat-advanced  
  - path: NewEden/Claude-Instruct-2.7K
    type: dan-chat-advanced 
  - path: PocketDoc/Dans-Assistantmaxx-Tulu3-IF
    type: dan-chat-advanced  
dataset_prepared_path: prepared_data
val_set_size: 0.0
output_dir: ./4b-inst-r2

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true


wandb_project: 4B-mng
wandb_entity:
wandb_watch:
wandb_name: attempt-2
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 1
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 5e-6
max_grad_norm: 0.2

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 40
saves_per_epoch: 2
debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.02
fsdp:
fsdp_config:
special_tokens:
  pad_token: <|finetune_right_pad_id|>
Axolotl Config ꒰(˶• ᴗ •˶)꒱yaml
base_model: NewEden_4B-PT
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

  #hub_model_id: NewEden/4B-Inst
  #hub_strategy: "all_checkpoints"
  #push_dataset_to_hub:
  #hf_use_auth_token: true

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/Helpsteer-3-Filtered
    type: dan-chat-advanced
  - path: NewEden/GSM8K-R1-filtered
    type: dan-chat-advanced
  - path: NewEden/Hydrus-R1-Thinking-Sharegpt
    type: dan-chat-advanced
  - path: NewEden/Hydrus-SonnetOrca
    type: dan-chat-advanced
  - path: NewEden/Hydrus-HelpSteer2
    type: dan-chat-advanced
  - path: NewEden/Claude-Instruct-5K
    type: dan-chat-advanced
  - path: PocketDoc/Dans-MemoryCore-CoreCurriculum-Small
    type: dan-chat-advanced
  - path: Nitral-AI/ARES-ShareGPT
    type: dan-chat-advanced 
  - path: NewEden/Hydrus-Instruct-SmolTalk
    type: dan-chat-advanced
  - path: NewEden/Hydrus-Chat_error-Pure-Dove-sharegpt
    type: dan-chat-advanced  
  - path: NewEden/Claude-Instruct-2.7K
    type: dan-chat-advanced 
  - path: PocketDoc/Dans-Assistantmaxx-Tulu3-IF
    type: dan-chat-advanced  
dataset_prepared_path: prepared_data
val_set_size: 0.0
output_dir: ./4b-inst-r2

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true


wandb_project: 4B-mng
wandb_entity:
wandb_watch:
wandb_name: attempt-2
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 1
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 5e-6
max_grad_norm: 0.2

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 40
saves_per_epoch: 2
debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.02
fsdp:
fsdp_config:
special_tokens:
  pad_token: <|finetune_right_pad_id|>
Axolotl Config ꒰(˶• ᴗ •˶)꒱yaml
base_model: NewEden_4B-PT
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

  #hub_model_id: NewEden/4B-Inst
  #hub_strategy: "all_checkpoints"
  #push_dataset_to_hub:
  #hf_use_auth_token: true

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/Helpsteer-3-Filtered
    type: dan-chat-advanced
  - path: NewEden/GSM8K-R1-filtered
    type: dan-chat-advanced
  - path: NewEden/Hydrus-R1-Thinking-Sharegpt
    type: dan-chat-advanced
  - path: NewEden/Hydrus-SonnetOrca
    type: dan-chat-advanced
  - path: NewEden/Hydrus-HelpSteer2
    type: dan-chat-advanced
  - path: NewEden/Claude-Instruct-5K
    type: dan-chat-advanced
  - path: PocketDoc/Dans-MemoryCore-CoreCurriculum-Small
    type: dan-chat-advanced
  - path: Nitral-AI/ARES-ShareGPT
    type: dan-chat-advanced 
  - path: NewEden/Hydrus-Instruct-SmolTalk
    type: dan-chat-advanced
  - path: NewEden/Hydrus-Chat_error-Pure-Dove-sharegpt
    type: dan-chat-advanced  
  - path: NewEden/Claude-Instruct-2.7K
    type: dan-chat-advanced 
  - path: PocketDoc/Dans-Assistantmaxx-Tulu3-IF
    type: dan-chat-advanced  
dataset_prepared_path: prepared_data
val_set_size: 0.0
output_dir: ./4b-inst-r2

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true


wandb_project: 4B-mng
wandb_entity:
wandb_watch:
wandb_name: attempt-2
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 1
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 5e-6
max_grad_norm: 0.2

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 40
saves_per_epoch: 2
debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.02
fsdp:
fsdp_config:
special_tokens:
  pad_token: <|finetune_right_pad_id|>

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.