Model save

README.md

@@ -0,0 +1,77 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- trl
+- dpo
+- llama-factory
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+model-index:
+- name: Mistral-7B-Instruct-v0.2-ORPO-SALT-HALF
+  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. -->
+
+# Mistral-7B-Instruct-v0.2-ORPO-SALT-HALF
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8831
+- Rewards/chosen: -0.0820
+- Rewards/rejected: -0.1062
+- Rewards/accuracies: 0.5810
+- Rewards/margins: 0.0242
+- Logps/rejected: -1.0619
+- Logps/chosen: -0.8200
+- Logits/rejected: -2.8746
+- Logits/chosen: -2.8587
+- Sft Loss: 0.8200
+- Odds Ratio Loss: 0.6316
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|:--------:|:---------------:|
+| 0.9115        | 0.8467 | 500  | 0.9161          | -0.0853        | -0.1100          | 0.5733             | 0.0247          | -1.0998        | -0.8530      | -2.8628         | -2.8480       | 0.8530   | 0.6317          |
+| 0.8308        | 1.6935 | 1000 | 0.8892          | -0.0826        | -0.1068          | 0.5724             | 0.0242          | -1.0678        | -0.8261      | -2.8569         | -2.8411       | 0.8261   | 0.6311          |
+| 0.8476        | 2.5402 | 1500 | 0.8831          | -0.0820        | -0.1062          | 0.5810             | 0.0242          | -1.0619        | -0.8200      | -2.8746         | -2.8587       | 0.8200   | 0.6316          |
+
+
+### 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 +151,31 @@
 {"current_steps": 1490, "total_steps": 1770, "loss": 0.8578, "accuracy": 0.581250011920929, "learning_rate": 3.024615823368371e-07, "epoch": 2.523285351397121, "percentage": 84.18, "elapsed_time": "4:05:51", "remaining_time": "0:46:12"}
 {"current_steps": 1500, "total_steps": 1770, "loss": 0.8476, "accuracy": 0.6000000238418579, "learning_rate": 2.8165102503600716e-07, "epoch": 2.5402201524132093, "percentage": 84.75, "elapsed_time": "4:07:27", "remaining_time": "0:44:32"}
 {"current_steps": 1500, "total_steps": 1770, "eval_loss": 0.883125364780426, "epoch": 2.5402201524132093, "percentage": 84.75, "elapsed_time": "4:10:41", "remaining_time": "0:45:07"}
+{"current_steps": 1510, "total_steps": 1770, "loss": 0.9619, "accuracy": 0.46875, "learning_rate": 2.615393769259039e-07, "epoch": 2.557154953429297, "percentage": 85.31, "elapsed_time": "4:12:22", "remaining_time": "0:43:27"}
+{"current_steps": 1520, "total_steps": 1770, "loss": 0.8375, "accuracy": 0.59375, "learning_rate": 2.421329743475917e-07, "epoch": 2.574089754445385, "percentage": 85.88, "elapsed_time": "4:13:55", "remaining_time": "0:41:45"}
+{"current_steps": 1530, "total_steps": 1770, "loss": 0.9109, "accuracy": 0.543749988079071, "learning_rate": 2.234379314486973e-07, "epoch": 2.5910245554614733, "percentage": 86.44, "elapsed_time": "4:15:34", "remaining_time": "0:40:05"}
+{"current_steps": 1540, "total_steps": 1770, "loss": 0.8572, "accuracy": 0.643750011920929, "learning_rate": 2.0546013825709783e-07, "epoch": 2.6079593564775614, "percentage": 87.01, "elapsed_time": "4:17:13", "remaining_time": "0:38:24"}
+{"current_steps": 1550, "total_steps": 1770, "loss": 0.7636, "accuracy": 0.637499988079071, "learning_rate": 1.88205258825217e-07, "epoch": 2.6248941574936495, "percentage": 87.57, "elapsed_time": "4:18:53", "remaining_time": "0:36:44"}
+{"current_steps": 1560, "total_steps": 1770, "loss": 0.7906, "accuracy": 0.6187499761581421, "learning_rate": 1.7167872944552245e-07, "epoch": 2.6418289585097376, "percentage": 88.14, "elapsed_time": "4:20:27", "remaining_time": "0:35:03"}
+{"current_steps": 1570, "total_steps": 1770, "loss": 0.8469, "accuracy": 0.543749988079071, "learning_rate": 1.5588575693777142e-07, "epoch": 2.6587637595258258, "percentage": 88.7, "elapsed_time": "4:22:05", "remaining_time": "0:33:23"}
+{"current_steps": 1580, "total_steps": 1770, "loss": 0.908, "accuracy": 0.4937500059604645, "learning_rate": 1.4083131700856428e-07, "epoch": 2.675698560541914, "percentage": 89.27, "elapsed_time": "4:23:44", "remaining_time": "0:31:42"}
+{"current_steps": 1590, "total_steps": 1770, "loss": 0.8288, "accuracy": 0.6499999761581421, "learning_rate": 1.2652015268370315e-07, "epoch": 2.6926333615580016, "percentage": 89.83, "elapsed_time": "4:25:19", "remaining_time": "0:30:02"}
+{"current_steps": 1600, "total_steps": 1770, "loss": 0.9065, "accuracy": 0.5625, "learning_rate": 1.1295677281386502e-07, "epoch": 2.7095681625740897, "percentage": 90.4, "elapsed_time": "4:26:58", "remaining_time": "0:28:21"}
+{"current_steps": 1610, "total_steps": 1770, "loss": 0.9, "accuracy": 0.5562499761581421, "learning_rate": 1.0014545065404973e-07, "epoch": 2.726502963590178, "percentage": 90.96, "elapsed_time": "4:28:35", "remaining_time": "0:26:41"}
+{"current_steps": 1620, "total_steps": 1770, "loss": 0.8696, "accuracy": 0.550000011920929, "learning_rate": 8.809022251725502e-08, "epoch": 2.743437764606266, "percentage": 91.53, "elapsed_time": "4:30:12", "remaining_time": "0:25:01"}
+{"current_steps": 1630, "total_steps": 1770, "loss": 0.8917, "accuracy": 0.5625, "learning_rate": 7.679488650280509e-08, "epoch": 2.7603725656223537, "percentage": 92.09, "elapsed_time": "4:31:50", "remaining_time": "0:23:20"}
+{"current_steps": 1640, "total_steps": 1770, "loss": 0.8306, "accuracy": 0.5249999761581421, "learning_rate": 6.626300129972563e-08, "epoch": 2.777307366638442, "percentage": 92.66, "elapsed_time": "4:33:22", "remaining_time": "0:21:40"}
+{"current_steps": 1650, "total_steps": 1770, "loss": 0.8388, "accuracy": 0.6187499761581421, "learning_rate": 5.649788506555065e-08, "epoch": 2.79424216765453, "percentage": 93.22, "elapsed_time": "4:34:57", "remaining_time": "0:19:59"}
+{"current_steps": 1660, "total_steps": 1770, "loss": 0.8673, "accuracy": 0.581250011920929, "learning_rate": 4.7502614380908474e-08, "epoch": 2.811176968670618, "percentage": 93.79, "elapsed_time": "4:36:35", "remaining_time": "0:18:19"}
+{"current_steps": 1670, "total_steps": 1770, "loss": 0.8598, "accuracy": 0.5687500238418579, "learning_rate": 3.9280023280222066e-08, "epoch": 2.828111769686706, "percentage": 94.35, "elapsed_time": "4:38:11", "remaining_time": "0:16:39"}
+{"current_steps": 1680, "total_steps": 1770, "loss": 0.9058, "accuracy": 0.5874999761581421, "learning_rate": 3.1832702358818855e-08, "epoch": 2.8450465707027943, "percentage": 94.92, "elapsed_time": "4:39:53", "remaining_time": "0:14:59"}
+{"current_steps": 1690, "total_steps": 1770, "loss": 0.847, "accuracy": 0.59375, "learning_rate": 2.5162997956746647e-08, "epoch": 2.8619813717188824, "percentage": 95.48, "elapsed_time": "4:41:36", "remaining_time": "0:13:19"}
+{"current_steps": 1700, "total_steps": 1770, "loss": 0.8617, "accuracy": 0.606249988079071, "learning_rate": 1.9273011419536914e-08, "epoch": 2.8789161727349706, "percentage": 96.05, "elapsed_time": "4:43:05", "remaining_time": "0:11:39"}
+{"current_steps": 1710, "total_steps": 1770, "loss": 0.8701, "accuracy": 0.5562499761581421, "learning_rate": 1.4164598436159083e-08, "epoch": 2.8958509737510583, "percentage": 96.61, "elapsed_time": "4:44:38", "remaining_time": "0:09:59"}
+{"current_steps": 1720, "total_steps": 1770, "loss": 0.8422, "accuracy": 0.625, "learning_rate": 9.839368454371556e-09, "epoch": 2.9127857747671464, "percentage": 97.18, "elapsed_time": "4:46:16", "remaining_time": "0:08:19"}
+{"current_steps": 1730, "total_steps": 1770, "loss": 0.8252, "accuracy": 0.59375, "learning_rate": 6.298684173650649e-09, "epoch": 2.9297205757832345, "percentage": 97.74, "elapsed_time": "4:47:51", "remaining_time": "0:06:39"}
+{"current_steps": 1740, "total_steps": 1770, "loss": 0.8901, "accuracy": 0.574999988079071, "learning_rate": 3.543661115860686e-09, "epoch": 2.9466553767993227, "percentage": 98.31, "elapsed_time": "4:49:20", "remaining_time": "0:04:59"}
+{"current_steps": 1750, "total_steps": 1770, "loss": 0.8176, "accuracy": 0.5625, "learning_rate": 1.575167273800693e-09, "epoch": 2.963590177815411, "percentage": 98.87, "elapsed_time": "4:50:50", "remaining_time": "0:03:19"}
+{"current_steps": 1760, "total_steps": 1770, "loss": 0.9065, "accuracy": 0.5687500238418579, "learning_rate": 3.9382283773564676e-10, "epoch": 2.9805249788314985, "percentage": 99.44, "elapsed_time": "4:52:29", "remaining_time": "0:01:39"}
+{"current_steps": 1770, "total_steps": 1770, "loss": 0.9802, "accuracy": 0.6000000238418579, "learning_rate": 0.0, "epoch": 2.9974597798475866, "percentage": 100.0, "elapsed_time": "4:54:03", "remaining_time": "0:00:00"}
+{"current_steps": 1770, "total_steps": 1770, "epoch": 2.9974597798475866, "percentage": 100.0, "elapsed_time": "4:54:03", "remaining_time": "0:00:00"}