Model save

README.md

@@ -0,0 +1,62 @@
+---
+license: llama3.1
+base_model: NousResearch/Meta-Llama-3.1-8B-Instruct
+tags:
+- generated_from_trainer
+model-index:
+- name: Llama-3.1-8B-Instruct-EI1-120K-fix-32gpus-04
+  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-EI1-120K-fix-32gpus-04
+
+This model is a fine-tuned version of [NousResearch/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3.1-8B-Instruct) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4876
+
+## 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: 6e-06
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 32
+- total_train_batch_size: 64
+- total_eval_batch_size: 256
+- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 2.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| No log        | 0.7299 | 100  | 0.5306          |
+| No log        | 1.4599 | 200  | 0.4876          |
+
+
+### Framework versions
+
+- Transformers 4.43.4
+- Pytorch 2.4.0+cu121
+- Datasets 3.0.1
+- Tokenizers 0.19.1

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.43.4"
+}