Model save

README.md

@@ -0,0 +1,77 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: alignment-handbook/zephyr-7b-sft-full
+tags:
+- trl
+- dpo
+- generated_from_trainer
+model-index:
+- name: zephyr-7b-group-dpo-full-4
+  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. -->
+
+# zephyr-7b-group-dpo-full-4
+
+This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3329
+- Rewards/chosen: -3.5971
+- Rewards/rejected: -6.6557
+- Rewards/accuracies: 0.8281
+- Rewards/margins: 3.0586
+- Logps/rejected: -955.4623
+- Logps/chosen: -642.2396
+- Logits/rejected: -0.6052
+- Logits/chosen: -1.1035
+
+## 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-07
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 256
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
+|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.2094        | 0.2303 | 100  | 0.4273          | -1.2973        | -2.4710          | 0.7768             | 1.1737          | -536.9892      | -412.2621    | -2.8747         | -2.8886       |
+| 0.1232        | 0.4606 | 200  | 0.3541          | -2.8531        | -5.1625          | 0.8069             | 2.3094          | -806.1392      | -567.8411    | -1.2949         | -1.6181       |
+| 0.1           | 0.6908 | 300  | 0.3383          | -3.9067        | -6.9476          | 0.8158             | 3.0409          | -984.6500      | -673.2026    | -0.4879         | -0.9150       |
+| 0.0956        | 0.9211 | 400  | 0.3329          | -3.5971        | -6.6557          | 0.8281             | 3.0586          | -955.4623      | -642.2396    | -0.6052         | -1.1035       |
+
+
+### Framework versions
+
+- Transformers 4.44.1
+- Pytorch 2.1.2+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9994242947610823,
+    "total_flos": 0.0,
+    "train_loss": 0.17276417467451316,
+    "train_runtime": 14185.6914,
+    "train_samples": 111134,
+    "train_samples_per_second": 7.834,
+    "train_steps_per_second": 0.031
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.44.1"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9994242947610823,
+    "total_flos": 0.0,
+    "train_loss": 0.17276417467451316,
+    "train_runtime": 14185.6914,
+    "train_samples": 111134,
+    "train_samples_per_second": 7.834,
+    "train_steps_per_second": 0.031
+}