Upload LoRA adapter files

README.md

@@ -0,0 +1,135 @@
+---
+library_name: peft
+license: other
+base_model: mistralai/Ministral-8B-Instruct-2410
+tags:
+- generated_from_trainer
+model-index:
+- name: workspace/FinLoRA/lora/axolotl-output/formula_mistral_8b_8bits_r8
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.10.0`
+```yaml
+base_model: mistralai/Ministral-8B-Instruct-2410
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+gradient_accumulation_steps: 2
+micro_batch_size: 4
+num_epochs: 1
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 0.0001
+load_in_8bit: true
+load_in_4bit: false
+bnb_4bit_use_double_quant: false
+bnb_4bit_quant_type: null
+bnb_4bit_compute_dtype: null
+adapter: lora
+lora_model_dir: null
+lora_r: 8
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_modules:
+- q_proj
+- v_proj
+- k_proj
+- path: /workspace/FinLoRA/data/train/formula_train.jsonl
+  type:
+    system_prompt: ''
+    field_system: system
+    field_instruction: context
+    field_output: target
+    format: '[INST] {instruction} [/INST]'
+    no_input_format: '[INST] {instruction} [/INST]'
+dataset_prepared_path: null
+val_set_size: 0.02
+output_dir: /workspace/FinLoRA/lora/axolotl-output/formula_mistral_8b_8bits_r8
+peft_use_dora: false
+peft_use_rslora: false
+sequence_len: 4096
+sample_packing: false
+pad_to_sequence_len: false
+wandb_project: finlora_models
+wandb_entity: null
+wandb_watch: gradients
+wandb_name: formula_mistral_8b_8bits_r8
+wandb_log_model: 'false'
+bf16: auto
+tf32: false
+gradient_checkpointing: true
+resume_from_checkpoint: null
+logging_steps: 500
+flash_attention: false
+deepspeed: deepspeed_configs/zero1.json
+warmup_steps: 10
+evals_per_epoch: 4
+saves_per_epoch: 1
+weight_decay: 0.0
+special_tokens:
+  pad_token: <|end_of_text|>
+
+```
+
+</details><br>
+
+# workspace/FinLoRA/lora/axolotl-output/formula_mistral_8b_8bits_r8
+
+This model is a fine-tuned version of [mistralai/Ministral-8B-Instruct-2410](https://huggingface.co/mistralai/Ministral-8B-Instruct-2410) on the /workspace/FinLoRA/data/train/formula_train.jsonl dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6196
+
+## 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: 0.0001
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- total_eval_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- training_steps: 25
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| No log        | 0      | 0    | 0.9518          |
+| No log        | 0.2857 | 7    | 0.7872          |
+| No log        | 0.5714 | 14   | 0.6417          |
+| No log        | 0.8571 | 21   | 0.6196          |
+
+
+### Framework versions
+
+- PEFT 0.15.2
+- Transformers 4.52.3
+- Pytorch 2.8.0.dev20250319+cu128
+- Datasets 3.6.0
+- Tokenizers 0.21.2

adapter_config.json

@@ -0,0 +1,35 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Ministral-8B-Instruct-2410",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39ad3e365f1055f81141d9f44465a99de82aff31b77dd26046abfc079bb3e4e8
+size 2158147096