EshAhm/Llama-3-8b-LoRA-Medical2

README.md

@@ -0,0 +1,75 @@
+---
+library_name: peft
+license: llama3
+base_model: meta-llama/Meta-Llama-3-8B
+tags:
+- base_model:adapter:meta-llama/Meta-Llama-3-8B
+- lora
+- transformers
+pipeline_tag: text-generation
+model-index:
+- name: Llama-3-8bLoRA-Medical2
+  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. -->
+
+# Llama-3-8bLoRA-Medical2
+
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4624
+
+## 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: 0.0002
+- train_batch_size: 2
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 50
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.4736        | 0.2667 | 100  | 0.4776          |
+| 0.4546        | 0.5333 | 200  | 0.4697          |
+| 0.4659        | 0.8    | 300  | 0.4645          |
+| 0.4357        | 1.0667 | 400  | 0.4637          |
+| 0.4163        | 1.3333 | 500  | 0.4643          |
+| 0.4228        | 1.6    | 600  | 0.4624          |
+| 0.4096        | 1.8667 | 700  | 0.4608          |
+| 0.3708        | 2.1333 | 800  | 0.4737          |
+| 0.355         | 2.4    | 900  | 0.4737          |
+| 0.3693        | 2.6667 | 1000 | 0.4733          |
+| 0.3642        | 2.9333 | 1100 | 0.4726          |
+
+
+### Framework versions
+
+- PEFT 0.17.1
+- Transformers 4.56.1
+- Pytorch 2.8.0+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.0

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a872f85f7a0e5d7da6216cf55139e9400942acc738a1b8703e7d1a7dcc038887
+size 109086416

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e343ff6c4477a8ad24cc8b8202a363a1980994fd3a972ca8b75fc53d282fa49
+size 5777