Model save

README.md

@@ -0,0 +1,57 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+- trl
+- sft
+base_model: Dynosaur/llama3-8b-math-sft
+model_name: llama3-8b-math-sft-mix-2-0
+licence: license
+---
+
+# Model Card for llama3-8b-math-sft-mix-2-0
+
+This model is a fine-tuned version of [Dynosaur/llama3-8b-math-sft](https://huggingface.co/Dynosaur/llama3-8b-math-sft).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="Dynosaur/llama3-8b-math-sft-mix-2-0", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.12.1
+- Transformers: 4.46.3
+- Pytorch: 2.5.1
+- Datasets: 3.1.0
+- Tokenizers: 0.20.3
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.9994890883877088,
+    "total_flos": 311934616780800.0,
+    "train_loss": 0.38544139599375354,
+    "train_runtime": 12440.8908,
+    "train_samples": 109602,
+    "train_samples_per_second": 17.62,
+    "train_steps_per_second": 0.275
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.46.3"
+}

runs/Nov25_04-12-50_34bc63e25d0b/events.out.tfevents.1732508512.34bc63e25d0b.2840.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4381e11c45f5ecf3c1135a4e35e0a16a25cb8bf6888a4042dbe73f77ca1fdabe
-size 727682
+oid sha256:17c1dd2cd9424542ba51ae6899dc242fd7085630cbdc4f3699d954edfeddd3ed
+size 728036

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.9994890883877088,
+    "total_flos": 311934616780800.0,
+    "train_loss": 0.38544139599375354,
+    "train_runtime": 12440.8908,
+    "train_samples": 109602,
+    "train_samples_per_second": 17.62,
+    "train_steps_per_second": 0.275
+}