Model save

README.md

@@ -0,0 +1,69 @@
+---
+library_name: peft
+license: mit
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: models-p10-limit-data-step1
+  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. -->
+
+# models-p10-limit-data-step1
+
+This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-32B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1200
+
+## 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: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 32
+- total_eval_batch_size: 8
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.1928        | 1.0   | 7    | 0.1710          |
+| 0.1516        | 2.0   | 14   | 0.1407          |
+| 0.1408        | 3.0   | 21   | 0.1239          |
+| 0.1367        | 4.0   | 28   | 0.1200          |
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.47.0.dev0
+- Pytorch 2.4.0+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 4.0,
+    "total_flos": 613369774080000.0,
+    "train_loss": 0.1637916559619563,
+    "train_runtime": 908.7009,
+    "train_samples": 200,
+    "train_samples_per_second": 0.88,
+    "train_steps_per_second": 0.031
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 4.0,
+    "total_flos": 613369774080000.0,
+    "train_loss": 0.1637916559619563,
+    "train_runtime": 908.7009,
+    "train_samples": 200,
+    "train_samples_per_second": 0.88,
+    "train_steps_per_second": 0.031
+}