pmrster/test-llama3-8b-instruct-qlora-fine-tune-1

README.md

@@ -0,0 +1,79 @@
+---
+license: llama3
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
+model-index:
+- name: llama3-8b-instruct-journal-finetune
+  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. -->
+
+# llama3-8b-instruct-journal-finetune
+
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.0299
+
+## 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: 2.5e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1
+- training_steps: 500
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss |
+|:-------------:|:-------:|:----:|:---------------:|
+| 2.9002        | 2.0833  | 25   | 1.8777          |
+| 1.1645        | 4.1667  | 50   | 1.6214          |
+| 0.4078        | 6.25    | 75   | 1.7856          |
+| 0.2373        | 8.3333  | 100  | 1.8434          |
+| 0.2209        | 10.4167 | 125  | 1.7767          |
+| 0.1953        | 12.5    | 150  | 1.8293          |
+| 0.1755        | 14.5833 | 175  | 1.7663          |
+| 0.1893        | 16.6667 | 200  | 1.8726          |
+| 0.1621        | 18.75   | 225  | 1.9366          |
+| 0.1657        | 20.8333 | 250  | 1.9146          |
+| 0.1593        | 22.9167 | 275  | 1.9225          |
+| 0.156         | 25.0    | 300  | 1.9411          |
+| 0.1549        | 27.0833 | 325  | 1.9504          |
+| 0.1525        | 29.1667 | 350  | 1.9608          |
+| 0.1511        | 31.25   | 375  | 1.9924          |
+| 0.1494        | 33.3333 | 400  | 1.9878          |
+| 0.1488        | 35.4167 | 425  | 2.0089          |
+| 0.1479        | 37.5    | 450  | 2.0089          |
+| 0.1448        | 39.5833 | 475  | 2.0233          |
+| 0.1447        | 41.6667 | 500  | 2.0299          |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.1
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,35 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
+  "bias": "none",
+  "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_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "up_proj",
+    "q_proj",
+    "gate_proj",
+    "lm_head",
+    "k_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:d4b45c8440c55566094fc98c2b3f650c98d9de9d101540006ef842032a9ace5b
+size 2453893592

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6d3334cc95af51b2006bf11de475278997260b3b08a1b6662aaf067f44c15ea
+size 5112