Model save

README.md

@@ -0,0 +1,77 @@
+---
+license: llama2
+library_name: peft
+tags:
+- trl
+- dpo
+- llama-factory
+- generated_from_trainer
+base_model: lmsys/vicuna-7b-v1.5
+model-index:
+- name: Vicuna-7B-v1.5-ORPO
+  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. -->
+
+# Vicuna-7B-v1.5-ORPO
+
+This model is a fine-tuned version of [lmsys/vicuna-7b-v1.5](https://huggingface.co/lmsys/vicuna-7b-v1.5) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0073
+- Rewards/chosen: -0.0940
+- Rewards/rejected: -0.1081
+- Rewards/accuracies: 0.5160
+- Rewards/margins: 0.0141
+- Logps/rejected: -1.0807
+- Logps/chosen: -0.9399
+- Logits/rejected: -0.2988
+- Logits/chosen: -0.3321
+- Sft Loss: 0.9399
+- Odds Ratio Loss: 0.6739
+
+## 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-06
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 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 | Sft Loss | Odds Ratio Loss |
+|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|:--------:|:---------------:|
+| 1.0913        | 0.8891 | 500  | 1.0354          | -0.0968        | -0.1107          | 0.5180             | 0.0140          | -1.1075        | -0.9676      | -0.3176         | -0.3490       | 0.9676   | 0.6776          |
+| 1.0328        | 1.7782 | 1000 | 1.0126          | -0.0945        | -0.1086          | 0.5160             | 0.0141          | -1.0856        | -0.9451      | -0.2979         | -0.3308       | 0.9451   | 0.6748          |
+| 0.9998        | 2.6673 | 1500 | 1.0073          | -0.0940        | -0.1081          | 0.5160             | 0.0141          | -1.0807        | -0.9399      | -0.2988         | -0.3321       | 0.9399   | 0.6739          |
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.40.1
+- Pytorch 2.3.0
+- Datasets 2.19.0
+- Tokenizers 0.19.1

trainer_log.jsonl

@@ -151,3 +151,22 @@
 {"current_steps": 1490, "total_steps": 1686, "loss": 1.0255, "accuracy": 0.48750001192092896, "learning_rate": 1.6490167940538343e-07, "epoch": 2.6494776617026004, "percentage": 88.37, "elapsed_time": "4:07:41", "remaining_time": "0:32:34"}
 {"current_steps": 1500, "total_steps": 1686, "loss": 0.9998, "accuracy": 0.5249999761581421, "learning_rate": 1.4866882516191339e-07, "epoch": 2.6672593909757722, "percentage": 88.97, "elapsed_time": "4:09:20", "remaining_time": "0:30:55"}
 {"current_steps": 1500, "total_steps": 1686, "eval_loss": 1.0073015689849854, "epoch": 2.6672593909757722, "percentage": 88.97, "elapsed_time": "4:12:26", "remaining_time": "0:31:18"}
+{"current_steps": 1510, "total_steps": 1686, "loss": 0.9915, "accuracy": 0.5625, "learning_rate": 1.3325243551706057e-07, "epoch": 2.685041120248944, "percentage": 89.56, "elapsed_time": "4:14:03", "remaining_time": "0:29:36"}
+{"current_steps": 1520, "total_steps": 1686, "loss": 0.9727, "accuracy": 0.550000011920929, "learning_rate": 1.1865786358165737e-07, "epoch": 2.702822849522116, "percentage": 90.15, "elapsed_time": "4:15:39", "remaining_time": "0:27:55"}
+{"current_steps": 1530, "total_steps": 1686, "loss": 1.1147, "accuracy": 0.512499988079071, "learning_rate": 1.0489017710262311e-07, "epoch": 2.720604578795288, "percentage": 90.75, "elapsed_time": "4:17:16", "remaining_time": "0:26:13"}
+{"current_steps": 1540, "total_steps": 1686, "loss": 1.0195, "accuracy": 0.46875, "learning_rate": 9.195415670326446e-08, "epoch": 2.73838630806846, "percentage": 91.34, "elapsed_time": "4:18:55", "remaining_time": "0:24:32"}
+{"current_steps": 1550, "total_steps": 1686, "loss": 1.0188, "accuracy": 0.4124999940395355, "learning_rate": 7.985429422327384e-08, "epoch": 2.7561680373416317, "percentage": 91.93, "elapsed_time": "4:20:28", "remaining_time": "0:22:51"}
+{"current_steps": 1560, "total_steps": 1686, "loss": 0.9834, "accuracy": 0.4749999940395355, "learning_rate": 6.859479115900818e-08, "epoch": 2.773949766614803, "percentage": 92.53, "elapsed_time": "4:22:05", "remaining_time": "0:21:10"}
+{"current_steps": 1570, "total_steps": 1686, "loss": 1.0133, "accuracy": 0.5, "learning_rate": 5.817955720457902e-08, "epoch": 2.791731495887975, "percentage": 93.12, "elapsed_time": "4:23:41", "remaining_time": "0:19:28"}
+{"current_steps": 1580, "total_steps": 1686, "loss": 1.012, "accuracy": 0.512499988079071, "learning_rate": 4.861220889427199e-08, "epoch": 2.809513225161147, "percentage": 93.71, "elapsed_time": "4:25:14", "remaining_time": "0:17:47"}
+{"current_steps": 1590, "total_steps": 1686, "loss": 1.0172, "accuracy": 0.5375000238418579, "learning_rate": 3.9896068346758074e-08, "epoch": 2.827294954434319, "percentage": 94.31, "elapsed_time": "4:26:49", "remaining_time": "0:16:06"}
+{"current_steps": 1600, "total_steps": 1686, "loss": 1.0071, "accuracy": 0.4312500059604645, "learning_rate": 3.203416211153832e-08, "epoch": 2.8450766837074903, "percentage": 94.9, "elapsed_time": "4:28:28", "remaining_time": "0:14:25"}
+{"current_steps": 1610, "total_steps": 1686, "loss": 1.0176, "accuracy": 0.4124999940395355, "learning_rate": 2.5029220118019393e-08, "epoch": 2.8628584129806622, "percentage": 95.49, "elapsed_time": "4:30:06", "remaining_time": "0:12:45"}
+{"current_steps": 1620, "total_steps": 1686, "loss": 0.9328, "accuracy": 0.625, "learning_rate": 1.8883674727586122e-08, "epoch": 2.880640142253834, "percentage": 96.09, "elapsed_time": "4:31:41", "remaining_time": "0:11:04"}
+{"current_steps": 1630, "total_steps": 1686, "loss": 0.9816, "accuracy": 0.4124999940395355, "learning_rate": 1.3599659889000639e-08, "epoch": 2.898421871527006, "percentage": 96.68, "elapsed_time": "4:33:20", "remaining_time": "0:09:23"}
+{"current_steps": 1640, "total_steps": 1686, "loss": 1.1156, "accuracy": 0.44999998807907104, "learning_rate": 9.179010397421528e-09, "epoch": 2.916203600800178, "percentage": 97.27, "elapsed_time": "4:35:02", "remaining_time": "0:07:42"}
+{"current_steps": 1650, "total_steps": 1686, "loss": 0.9291, "accuracy": 0.4937500059604645, "learning_rate": 5.623261257296509e-09, "epoch": 2.93398533007335, "percentage": 97.86, "elapsed_time": "4:36:38", "remaining_time": "0:06:02"}
+{"current_steps": 1660, "total_steps": 1686, "loss": 0.9945, "accuracy": 0.5249999761581421, "learning_rate": 2.933647149357122e-09, "epoch": 2.9517670593465217, "percentage": 98.46, "elapsed_time": "4:38:15", "remaining_time": "0:04:21"}
+{"current_steps": 1670, "total_steps": 1686, "loss": 1.0009, "accuracy": 0.4625000059604645, "learning_rate": 1.1111020018930717e-09, "epoch": 2.969548788619693, "percentage": 99.05, "elapsed_time": "4:39:52", "remaining_time": "0:02:40"}
+{"current_steps": 1680, "total_steps": 1686, "loss": 0.9695, "accuracy": 0.5874999761581421, "learning_rate": 1.5625866646051813e-10, "epoch": 2.987330517892865, "percentage": 99.64, "elapsed_time": "4:41:29", "remaining_time": "0:01:00"}
+{"current_steps": 1686, "total_steps": 1686, "epoch": 2.997999555456768, "percentage": 100.0, "elapsed_time": "4:42:30", "remaining_time": "0:00:00"}