mNLP-project
/

gpt2-dpo

@@ -6,26 +6,26 @@ tags:
 - dpo
 - generated_from_trainer
 model-index:
-- name: gpt2-dpo
   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. -->
-# gpt2-dpo
 This model is a fine-tuned version of [mNLP-project/gpt2-finetuned](https://huggingface.co/mNLP-project/gpt2-finetuned) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4723
-- Rewards/chosen: 6.0254
-- Rewards/rejected: 4.8392
-- Rewards/accuracies: 0.6131
-- Rewards/margins: 1.1862
-- Logps/rejected: -744.8858
-- Logps/chosen: -889.1946
-- Logits/rejected: -39.0461
-- Logits/chosen: -34.0211
 ## Model description
@@ -44,14 +44,14 @@ More information needed
 ### Training hyperparameters
 The following hyperparameters were used during training:
-- learning_rate: 3e-05
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 2
 - total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
 - num_epochs: 10
@@ -59,16 +59,16 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step  | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
 |:-------------:|:-----:|:-----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
-| 1.2678        | 1.0   | 1337  | 1.5076          | 4.1438         | 3.2671           | 0.5687             | 0.8767          | -760.6065      | -908.0106    | -41.6142        | -35.6298      |
-| 0.804         | 2.0   | 2674  | 1.4723          | 6.0254         | 4.8392           | 0.6131             | 1.1862          | -744.8858      | -889.1946    | -39.0461        | -34.0211      |
-| 0.3498        | 3.0   | 4011  | 1.6023          | 7.3240         | 5.7922           | 0.6108             | 1.5318          | -735.3561      | -876.2083    | -39.8915        | -34.1137      |
-| 0.2381        | 4.0   | 5348  | 1.8159          | 10.2449        | 8.1301           | 0.6082             | 2.1148          | -711.9767      | -846.9996    | -30.1616        | -23.8379      |
-| 0.034         | 5.0   | 6685  | 1.8657          | 7.7458         | 5.8712           | 0.6067             | 1.8746          | -734.5658      | -871.9908    | -42.3683        | -36.2290      |
-| 0.1025        | 6.0   | 8022  | 1.9185          | 6.2157         | 4.4010           | 0.5869             | 1.8146          | -749.2675      | -887.2919    | -39.4627        | -32.6924      |
-| 0.0094        | 7.0   | 9359  | 2.0228          | 5.9773         | 4.0485           | 0.5907             | 1.9288          | -752.7930      | -889.6758    | -40.0105        | -32.9146      |
-| 0.0176        | 8.0   | 10696 | 2.1184          | 7.0049         | 4.8408           | 0.5914             | 2.1641          | -744.8698      | -879.3992    | -42.7145        | -35.6132      |
-| 0.0089        | 9.0   | 12033 | 2.1585          | 6.4084         | 4.2552           | 0.5899             | 2.1531          | -750.7258      | -885.3651    | -42.3970        | -35.1863      |
-| 0.0044        | 10.0  | 13370 | 2.1897          | 6.2187         | 4.0595           | 0.5877             | 2.1592          | -752.6830      | -887.2613    | -42.5334        | -35.2975      |
 ### Framework versions

 - dpo
 - generated_from_trainer
 model-index:
+- name: gpt2-dpo-with-cosine-lr-scheduler
   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. -->
+# gpt2-dpo-with-cosine-lr-scheduler
 This model is a fine-tuned version of [mNLP-project/gpt2-finetuned](https://huggingface.co/mNLP-project/gpt2-finetuned) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 1.1168
+- Rewards/chosen: 3.8849
+- Rewards/rejected: 3.2031
+- Rewards/accuracies: 0.5892
+- Rewards/margins: 0.6818
+- Logps/rejected: -761.2470
+- Logps/chosen: -910.5992
+- Logits/rejected: -36.5651
+- Logits/chosen: -30.3810
 ## Model description
 ### Training hyperparameters
 The following hyperparameters were used during training:
+- learning_rate: 1e-05
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 2
 - total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.1
 - num_epochs: 10
 | Training Loss | Epoch | Step  | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
 |:-------------:|:-----:|:-----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.9846        | 1.0   | 1337  | 1.1168          | 3.8849         | 3.2031           | 0.5892             | 0.6818          | -761.2470      | -910.5992    | -36.5651        | -30.3810      |
+| 0.6025        | 2.0   | 2674  | 1.1405          | 5.0060         | 4.0992           | 0.6175             | 0.9068          | -752.2864      | -899.3887    | -35.0528        | -28.9839      |
+| 0.2464        | 3.0   | 4011  | 1.1202          | 4.6754         | 3.6835           | 0.6160             | 0.9919          | -756.4427      | -902.6943    | -39.6513        | -33.3219      |
+| 0.1182        | 4.0   | 5348  | 1.3054          | 7.3114         | 5.8367           | 0.6131             | 1.4747          | -734.9108      | -876.3349    | -35.1974        | -28.6005      |
+| 0.0669        | 5.0   | 6685  | 1.3846          | 6.5378         | 5.0738           | 0.6093             | 1.4640          | -742.5399      | -884.0710    | -39.0355        | -31.8814      |
+| 0.0226        | 6.0   | 8022  | 1.4662          | 6.2901         | 4.6812           | 0.6052             | 1.6089          | -746.4659      | -886.5475    | -40.3811        | -32.9593      |
+| 0.0128        | 7.0   | 9359  | 1.5557          | 5.8081         | 4.1554           | 0.6108             | 1.6527          | -751.7241      | -891.3676    | -39.1744        | -31.2704      |
+| 0.019         | 8.0   | 10696 | 1.6676          | 5.5428         | 3.8458           | 0.6011             | 1.6970          | -754.8205      | -894.0207    | -40.5161        | -32.4700      |
+| 0.0101        | 9.0   | 12033 | 1.7100          | 5.5531         | 3.8215           | 0.6022             | 1.7315          | -755.0627      | -893.9178    | -40.7171        | -32.5929      |
+| 0.0053        | 10.0  | 13370 | 1.7177          | 5.4221         | 3.7030           | 0.6000             | 1.7191          | -756.2481      | -895.2274    | -40.8064        | -32.6689      |
 ### Framework versions

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:999885e52ec8040b3c1a078e8e7aa71469f9a66111a5053a04be273e74492e2d
 size 497774208

 version https://git-lfs.github.com/spec/v1
+oid sha256:4ef27d8cae5a67ccd7d8d3e0727dab7ae405ec179914db0c9054695a90af4a78
 size 497774208

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e9fe933f136ec8b8d9bd5296ef093520541ada90df3f9fead74fec43b3c51e9
 size 4984

 version https://git-lfs.github.com/spec/v1
+oid sha256:bac11c22c2d9c7ffea69e45b04ef286d1c79bca8bf6e705dbce85d7a2c13ca2e
 size 4984