See axolotl config

axolotl version: 0.13.0.dev0

base_model: alpindale/Mistral-7B-v0.2-hf
tokenizer_type: AutoTokenizer
model_type: AutoModelForCausalLM
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: representation_variation_storeflow.jsonl
  type: completion
- path: text_chunks_storeflow.jsonl
  type: completion
- path: inferred_facts_storeflow.jsonl
  type: completion
dataset_prepared_path: last_run_prepared
output_dir: ./model-output
seed: 1337
sequence_len: 5000
sample_packing: true
pad_to_sequence_len: false
shuffle_merged_datasets: true
gradient_accumulation_steps: 8
micro_batch_size: 1
eval_batch_size: 4
num_epochs: 5
optimizer: paged_adamw_8bit
lr_scheduler: constant
learning_rate: 2.0e-05
noisy_embedding_alpha: 5
weight_decay: 0
train_on_inputs: false
group_by_length: false
bf16: true
fp16: false
tf32: false
gradient_checkpointing: true
logging_steps: 1
xformers_attention: false
flash_attention: true
chat_template: chatml
auto_resume_from_checkpoints: false
warmup_ratio: 0.1
evals_per_epoch: 1
val_set_size: 0.04
saves_per_epoch: 1
eval_sample_packing: false
save_total_limit: 2
special_tokens:
  pad_token: <unk>
use_liger_kernel: true
plugins:
- axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_glu_activation: true
liger_layer_norm: true
liger_fused_linear_cross_entropy: true
sequence_length: 10000
wandb_project: test-project
wandb_entity: ''
wandb_watch: ''
wandb_run_id: ''
wandb_log_model: ''
hub_model_id: SaurabhJ20/deva1-pretrain
hub_strategy: end

deva1-pretrain

This model is a fine-tuned version of alpindale/Mistral-7B-v0.2-hf on the representation_variation_storeflow.jsonl, the text_chunks_storeflow.jsonl and the inferred_facts_storeflow.jsonl datasets.

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: 4
• seed: 1337
• gradient_accumulation_steps: 8
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: constant
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 5.0

Training results

Framework versions

• Transformers 4.55.0
• Pytorch 2.7.1+cu128
• Datasets 4.0.0
• Tokenizers 0.21.4