base_model: mistralai/Mistral-7B-v0.3
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer

strict: false

# dataset
datasets:
    - path: BEE-spoke-data/sarcasm-scrolls
      type: completion # format from earlier
      field: text # Optional[str] default: text, field to use for completion data
val_set_size: 0.025

sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# WANDB
wandb_project: sarcasm-scrolls
wandb_entity: pszemraj
wandb_watch: gradients
wandb_name: Mistral-7B-v0.3-sarcasm-scrolls
hub_model_id: pszemraj/Mistral-7B-v0.3-sarcasm-scrolls-2
hub_strategy: every_save

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 2
optimizer: adamw_torch_fused # paged_adamw_32bit
lr_scheduler: cosine
learning_rate: 2e-5

load_in_8bit: false
load_in_4bit: false
bf16: auto
fp16:
tf32: true

torch_compile: true # requires >= torch 2.0, may sometimes cause problems
torch_compile_backend: inductor # Optional[str]
gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
logging_steps: 5
xformers_attention:
flash_attention: true

warmup_steps: 20
# hyperparams for freq of evals, saving, etc
evals_per_epoch: 4
saves_per_epoch: 4
save_safetensors: true
save_total_limit: 1 # Checkpoints saved at a time
output_dir: ./output-axolotl/output-model-theta
resume_from_checkpoint:


deepspeed:
weight_decay: 0.04

special_tokens:

Mistral-7B-v0.3-sarcasm-scrolls @ ctx 4k

This model is a fine-tuned version of mistralai/Mistral-7B-v0.3 on the None dataset. It achieves the following results on the evaluation set:

Loss: 2.2825

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: 2e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 20
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0082	1	2.3959
2.412	0.2544	31	2.3363
2.3866	0.5087	62	2.3277
2.3204	0.7631	93	2.3012
2.2843	1.0174	124	2.2682
2.1748	1.2718	155	2.2425
1.6885	1.2349	186	2.2849
1.6834	1.4892	217	2.2825

Framework versions

Transformers 4.41.1
Pytorch 2.3.0+cu118
Datasets 2.19.1
Tokenizers 0.19.1

pszemraj/Mistral-7B-v0.3-sarcasm-scrolls-4k

Mistral-7B-v0.3-sarcasm-scrolls @ ctx 4k

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

pszemraj/
Mistral-7B-v0.3-sarcasm-scrolls-4k