axolotl version: 0.4.1
base_model: FourOhFour/Vapor_7B
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-org/stheno-filtered-v1.1
type: sharegpt
conversation: chatml
- path: Epiculous/SynthRP-Gens-v1.1-Filtered-n-Cleaned
type: sharegpt
conversation: chatml
- path: ResplendentAI/bluemoon
type: sharegpt
conversation: chatml
- path: openerotica/freedom-rp
type: sharegpt
conversation: chatml
- path: anthracite-org/nopm_claude_writing_fixed
type: sharegpt
conversation: chatml
- path: MinervaAI/Aesir-Preview
type: sharegpt
conversation: chatml
- path: NewEden/c2-prefixed
type: sharegpt
conversation: chatml
chat_template: chatml
val_set_size: 0.01
output_dir: ./outputs/out
adapter:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear:
sequence_len: 8192
# sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true
plugins:
- axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_swiglu: true
liger_fused_linear_cross_entropy: true
wandb_project: smoke7B
wandb_entity:
wandb_watch:
wandb_name: smoke7B
wandb_log_model:
gradient_accumulation_steps: 32
micro_batch_size: 1
num_epochs: 2
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.00001
weight_decay: 0.05
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true
gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint: /workspace/axolotl/outputs/out/checkpoint-137
auto_resume_from_checkpoints: true
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
warmup_ratio: 0.1
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 2
debug:
deepspeed:
fsdp:
fsdp_config:
special_tokens:
pad_token: <pad>
outputs/out
This model is a fine-tuned version of FourOhFour/Vapor_7B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4023
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 32
- total_train_batch_size: 64
- total_eval_batch_size: 2
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 54
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.539 | 0.0037 | 1 | 1.5559 |
| 1.562 | 0.2528 | 69 | 1.4611 |
| 1.4928 | 0.5056 | 138 | 1.4304 |
| 1.4968 | 0.7583 | 207 | 1.4155 |
| 1.4817 | 1.0108 | 276 | 1.4075 |
| 1.4637 | 1.2640 | 345 | 1.4038 |
| 1.4701 | 1.5171 | 414 | 1.4026 |
| 1.4657 | 1.7703 | 483 | 1.4023 |
Framework versions
- Transformers 4.45.0.dev0
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1