base_model: unsloth/mistral-7b-v0.3-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- trl
- sft
license: apache-2.0
language:
- fr
datasets:
- KasparZ/mtext-071024
Uploaded model
Developed by: KasparZ
License: apache-2.0
Finetuned from model : unsloth/mistral-7b-v0.3-bnb-4bit
- max_seq_length = 4096
tokenizer.pad_token = tokenizer.eos_token
model.config.pad_token_id = tokenizer.pad_token_id
new_tokens = ["<|s|>", "<|e|>"]
LoRA
r = 128,
target_modules = ["q_proj", "k_proj", "v_proj", "o_proj","gate_proj", "up_proj", "down_proj","embed_tokens", "lm_head"]
lora_alpha = 32,
lora_dropout = 0,
bias = "none",
use_gradient_checkpointing = "unsloth",
random_state = 3407,
use_rslora = True,
loftq_config = None,
Training
per_device_train_batch_size = 1,
gradient_accumulation_steps = 8,
warmup_ratio = 0.1,
num_train_epochs = 2,
learning_rate = 1e-4,
embedding_learning_rate = 5e-5,
fp16 = True,
bf16 = False,
logging_steps = 1,
optim = "adamw_8bit",
weight_decay = 0.01,
lr_scheduler_type = "cosine",
seed = 3407,
output_dir = "outputs",
save_strategy = "steps",
save_steps = 50,
report_to = "none",
This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.
