Idowenst/finetuned-llama3-mental-health-chatbot

README.md

@@ -0,0 +1,74 @@
+---
+library_name: peft
+base_model: unsloth/llama-3.2-1b-unsloth-bnb-4bit
+tags:
+- unsloth
+- generated_from_trainer
+model-index:
+- name: results
+  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. -->
+
+# results
+
+This model is a fine-tuned version of [unsloth/llama-3.2-1b-unsloth-bnb-4bit](https://huggingface.co/unsloth/llama-3.2-1b-unsloth-bnb-4bit) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 7.2083
+
+## 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: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 15
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 13.3929       | 1.0   | 43   | 7.2656          |
+| 11.4271       | 2.0   | 86   | 7.2669          |
+| 11.0609       | 3.0   | 129  | 7.3441          |
+| 10.097        | 4.0   | 172  | 7.6927          |
+| 8.2179        | 5.0   | 215  | 7.7197          |
+| 7.1093        | 6.0   | 258  | 7.6223          |
+| 6.3082        | 7.0   | 301  | 7.5638          |
+| 5.8958        | 8.0   | 344  | 7.4709          |
+| 5.7789        | 9.0   | 387  | 7.3977          |
+| 5.5157        | 10.0  | 430  | 7.3469          |
+| 5.3691        | 11.0  | 473  | 7.3023          |
+| 5.4559        | 12.0  | 516  | 7.2700          |
+| 5.3126        | 13.0  | 559  | 7.2285          |
+| 5.2435        | 14.0  | 602  | 7.2138          |
+| 5.3684        | 15.0  | 645  | 7.2083          |
+
+
+### Framework versions
+
+- PEFT 0.14.0
+- Transformers 4.48.3
+- Pytorch 2.6.0+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/llama-3.2-1b-unsloth-bnb-4bit",
+  "bias": "none",
+  "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": 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"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30de0d6429681369c8c5b34b8f2584fed046cc2099c55de70929639976bfc5f3
+size 3416264

runs/Feb13_01-41-26_69ed60e663c1/events.out.tfevents.1739410888.69ed60e663c1.31.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11e3dcfeb1effcfb48e7e00af7769298b814a9584db718b940c8007c4052ab8f
+size 5758

runs/Feb13_01-51-33_69ed60e663c1/events.out.tfevents.1739411494.69ed60e663c1.31.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7701b68bc5a1f117b5ec37e496bb03ee2fe39990e82bdf61301d7e0388a21e19
+size 5797

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3485a7194793c8926f5deb2e2a7272c9ef1058871bc62579a1bddf6018434bce
+size 5304