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_unl_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_unl_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: 2.0457
+- Rewards/chosen: -1.3358
+- Rewards/rejected: -1.6120
+- Rewards/accuracies: 0.5927
+- Rewards/margins: 0.2762
+- Logps/rejected: -1.6120
+- Logps/chosen: -1.3358
+- Logits/rejected: 0.2351
+- Logits/chosen: 0.1504
+- Semantic Entropy: 0.7755
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|:----------------:|
+| 2.0607        | 0.2141 | 400  | 2.0925          | -1.3454        | -1.4757          | 0.5564             | 0.1303          | -1.4757        | -1.3454      | 0.3297          | 0.2452        | 0.7910           |
+| 2.0818        | 0.4282 | 800  | 2.0714          | -1.3264        | -1.4818          | 0.5586             | 0.1554          | -1.4818        | -1.3264      | 0.3658          | 0.2814        | 0.7938           |
+| 2.0333        | 0.6422 | 1200 | 2.0611          | -1.3249        | -1.5070          | 0.5734             | 0.1821          | -1.5070        | -1.3249      | 0.4174          | 0.3272        | 0.7900           |
+| 2.0467        | 0.8563 | 1600 | 2.0564          | -1.3256        | -1.5170          | 0.5764             | 0.1913          | -1.5170        | -1.3256      | 0.3362          | 0.2519        | 0.7920           |
+| 2.1246        | 1.0704 | 2000 | 2.0505          | -1.3186        | -1.5340          | 0.5772             | 0.2154          | -1.5340        | -1.3186      | 0.4597          | 0.3633        | 0.7884           |
+| 2.0207        | 1.2845 | 2400 | 2.0472          | -1.3301        | -1.5773          | 0.5875             | 0.2473          | -1.5773        | -1.3301      | 0.3860          | 0.2934        | 0.7809           |
+| 2.0557        | 1.4986 | 2800 | 2.0434          | -1.3280        | -1.5872          | 0.5846             | 0.2592          | -1.5872        | -1.3280      | 0.4563          | 0.3580        | 0.7788           |
+| 2.0057        | 1.7127 | 3200 | 2.0460          | -1.3270        | -1.5754          | 0.5883             | 0.2484          | -1.5754        | -1.3270      | 0.3804          | 0.2876        | 0.7828           |
+| 1.971         | 1.9267 | 3600 | 2.0442          | -1.3219        | -1.5700          | 0.5861             | 0.2480          | -1.5700        | -1.3219      | 0.3035          | 0.2161        | 0.7832           |
+| 1.9276        | 2.1408 | 4000 | 2.0445          | -1.3312        | -1.6024          | 0.5905             | 0.2711          | -1.6024        | -1.3312      | 0.3771          | 0.2823        | 0.7784           |
+| 1.9438        | 2.3549 | 4400 | 2.0449          | -1.3381        | -1.6152          | 0.5942             | 0.2771          | -1.6152        | -1.3381      | 0.2493          | 0.1633        | 0.7754           |
+| 1.9434        | 2.5690 | 4800 | 2.0459          | -1.3386        | -1.6198          | 0.5942             | 0.2812          | -1.6198        | -1.3386      | 0.2611          | 0.1743        | 0.7744           |
+| 1.9666        | 2.7831 | 5200 | 2.0454          | -1.3354        | -1.6132          | 0.5942             | 0.2777          | -1.6132        | -1.3354      | 0.2918          | 0.2027        | 0.7755           |
+| 1.9498        | 2.9972 | 5600 | 2.0457          | -1.3358        | -1.6120          | 0.5927             | 0.2762          | -1.6120        | -1.3358      | 0.2351          | 0.1504        | 0.7755           |
+
+
+### 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": 2.028473087245443,
+    "train_runtime": 28359.3461,
+    "train_samples": 59790,
+    "train_samples_per_second": 6.325,
+    "train_steps_per_second": 0.198
+}

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": 2.028473087245443,
+    "train_runtime": 28359.3461,
+    "train_samples": 59790,
+    "train_samples_per_second": 6.325,
+    "train_steps_per_second": 0.198
+}