Model save

README.md

@@ -0,0 +1,67 @@
+---
+base_model: meta-llama/Llama-3.1-8B-Instruct
+library_name: peft
+license: llama3.1
+tags:
+- llama-factory
+- generated_from_trainer
+model-index:
+- name: Llama-3.1-8B-Instruct-SFT-400
+  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-3.1-8B-Instruct-SFT-400
+
+This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0645
+
+## 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-06
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 10.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.8183        | 2.2222 | 50   | 0.6115          |
+| 0.1498        | 4.4444 | 100  | 0.0840          |
+| 0.0829        | 6.6667 | 150  | 0.0651          |
+| 0.0952        | 8.8889 | 200  | 0.0645          |
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.45.2
+- Pytorch 2.3.0
+- Datasets 2.19.0
+- Tokenizers 0.20.0

trainer_log.jsonl

@@ -22,3 +22,6 @@
 {"current_steps": 190, "total_steps": 220, "loss": 0.0952, "learning_rate": 2.963665913810451e-07, "epoch": 8.444444444444445, "percentage": 86.36, "elapsed_time": "0:04:26", "remaining_time": "0:00:42"}
 {"current_steps": 200, "total_steps": 220, "loss": 0.0952, "learning_rate": 1.3749795321332887e-07, "epoch": 8.88888888888889, "percentage": 90.91, "elapsed_time": "0:04:39", "remaining_time": "0:00:27"}
 {"current_steps": 200, "total_steps": 220, "eval_loss": 0.06450273841619492, "epoch": 8.88888888888889, "percentage": 90.91, "elapsed_time": "0:04:40", "remaining_time": "0:00:28"}
+{"current_steps": 210, "total_steps": 220, "loss": 0.0727, "learning_rate": 3.798061746947995e-08, "epoch": 9.333333333333334, "percentage": 95.45, "elapsed_time": "0:04:55", "remaining_time": "0:00:14"}
+{"current_steps": 220, "total_steps": 220, "loss": 0.1111, "learning_rate": 3.146808153123293e-10, "epoch": 9.777777777777779, "percentage": 100.0, "elapsed_time": "0:05:08", "remaining_time": "0:00:00"}
+{"current_steps": 220, "total_steps": 220, "epoch": 9.777777777777779, "percentage": 100.0, "elapsed_time": "0:05:10", "remaining_time": "0:00:00"}