Model save

README.md

@@ -0,0 +1,86 @@
+---
+library_name: transformers
+license: other
+base_model: trl-lib/qwen1.5-0.5b-sft
+tags:
+- trl
+- simpo
+- generated_from_trainer
+model-index:
+- name: qwen_qfUNL_entropy
+  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. -->
+
+# qwen_qfUNL_entropy
+
+This model is a fine-tuned version of [trl-lib/qwen1.5-0.5b-sft](https://huggingface.co/trl-lib/qwen1.5-0.5b-sft) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: nan
+- Rewards/chosen: nan
+- Rewards/rejected: nan
+- Rewards/accuracies: 0.0
+- Rewards/margins: nan
+- Logps/rejected: nan
+- Logps/chosen: nan
+- Logits/rejected: nan
+- Logits/chosen: nan
+- Semantic Entropy: nan
+
+## 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: 1e-06
+- train_batch_size: 2
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen | Semantic Entropy |
+|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|:----------------:|
+| 0.0           | 0.2141 | 400  | nan             | nan            | nan              | 0.0                | nan             | nan            | nan          | nan             | nan           | nan              |
+| 0.0           | 0.4282 | 800  | nan             | nan            | nan              | 0.0                | nan             | nan            | nan          | nan             | nan           | nan              |
+| 0.0           | 0.6422 | 1200 | nan             | nan            | nan              | 0.0                | nan             | nan            | nan          | nan             | nan           | nan              |
+| 0.0           | 0.8563 | 1600 | nan             | nan            | nan              | 0.0                | nan             | nan            | nan          | nan             | nan           | nan              |
+| 0.0           | 1.0704 | 2000 | nan             | nan            | nan              | 0.0                | nan             | nan            | nan          | nan             | nan           | nan              |
+| 0.0           | 1.2845 | 2400 | nan             | nan            | nan              | 0.0                | nan             | nan            | nan          | nan             | nan           | nan              |
+| 0.0           | 1.4986 | 2800 | nan             | nan            | nan              | 0.0                | nan             | nan            | nan          | nan             | nan           | nan              |
+| 0.0           | 1.7127 | 3200 | nan             | nan            | nan              | 0.0                | nan             | nan            | nan          | nan             | nan           | nan              |
+| 0.0           | 1.9267 | 3600 | nan             | nan            | nan              | 0.0                | nan             | nan            | nan          | nan             | nan           | nan              |
+| 0.0           | 2.1408 | 4000 | nan             | nan            | nan              | 0.0                | nan             | nan            | nan          | nan             | nan           | nan              |
+| 0.0           | 2.3549 | 4400 | nan             | nan            | nan              | 0.0                | nan             | nan            | nan          | nan             | nan           | nan              |
+| 0.0           | 2.5690 | 4800 | nan             | nan            | nan              | 0.0                | nan             | nan            | nan          | nan             | nan           | nan              |
+| 0.0           | 2.7831 | 5200 | nan             | nan            | nan              | 0.0                | nan             | nan            | nan          | nan             | nan           | nan              |
+| 0.0           | 2.9972 | 5600 | nan             | nan            | nan              | 0.0                | nan             | nan            | nan          | nan             | nan           | nan              |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.2.2+cu121
+- Datasets 2.18.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.999297541394882,
+    "total_flos": 0.0,
+    "train_loss": 0.4331439037054118,
+    "train_runtime": 28837.4505,
+    "train_samples": 59790,
+    "train_samples_per_second": 6.22,
+    "train_steps_per_second": 0.194
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.44.2"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.999297541394882,
+    "total_flos": 0.0,
+    "train_loss": 0.4331439037054118,
+    "train_runtime": 28837.4505,
+    "train_samples": 59790,
+    "train_samples_per_second": 6.22,
+    "train_steps_per_second": 0.194
+}