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: tiiuae/falcon-7b-instruct
+model-index:
+- name: Falcon-7B-Instruct-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. -->
+
+# Falcon-7B-Instruct-ORPO-SALT-HALF
+
+This model is a fine-tuned version of [tiiuae/falcon-7b-instruct](https://huggingface.co/tiiuae/falcon-7b-instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.4967
+- Rewards/chosen: -0.1424
+- Rewards/rejected: -0.1512
+- Rewards/accuracies: 0.5038
+- Rewards/margins: 0.0088
+- Logps/rejected: -1.5123
+- Logps/chosen: -1.4238
+- Logits/rejected: -14.4005
+- Logits/chosen: -14.4333
+- Sft Loss: 1.4238
+- Odds Ratio Loss: 0.7294
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|:--------:|:---------------:|
+| 1.5988        | 0.8467 | 500  | 1.5655          | -0.1492        | -0.1572          | 0.4962             | 0.0080          | -1.5724        | -1.4919      | -14.3530        | -14.3859      | 1.4919   | 0.7361          |
+| 1.4213        | 1.6935 | 1000 | 1.5097          | -0.1437        | -0.1524          | 0.5038             | 0.0087          | -1.5240        | -1.4366      | -14.3997        | -14.4324      | 1.4366   | 0.7303          |
+| 1.4234        | 2.5402 | 1500 | 1.4967          | -0.1424        | -0.1512          | 0.5038             | 0.0088          | -1.5123        | -1.4238      | -14.4005        | -14.4333      | 1.4238   | 0.7294          |
+
+
+### 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": 1.4407, "accuracy": 0.5, "learning_rate": 3.024615823368371e-07, "epoch": 2.523285351397121, "percentage": 84.18, "elapsed_time": "6:02:32", "remaining_time": "1:08:07"}
 {"current_steps": 1500, "total_steps": 1770, "loss": 1.4234, "accuracy": 0.512499988079071, "learning_rate": 2.8165102503600716e-07, "epoch": 2.5402201524132093, "percentage": 84.75, "elapsed_time": "6:05:53", "remaining_time": "1:05:51"}
 {"current_steps": 1500, "total_steps": 1770, "eval_loss": 1.4967381954193115, "epoch": 2.5402201524132093, "percentage": 84.75, "elapsed_time": "6:13:19", "remaining_time": "1:07:11"}
+{"current_steps": 1510, "total_steps": 1770, "loss": 1.6479, "accuracy": 0.4124999940395355, "learning_rate": 2.615393769259039e-07, "epoch": 2.557154953429297, "percentage": 85.31, "elapsed_time": "6:16:44", "remaining_time": "1:04:52"}
+{"current_steps": 1520, "total_steps": 1770, "loss": 1.4165, "accuracy": 0.53125, "learning_rate": 2.421329743475917e-07, "epoch": 2.574089754445385, "percentage": 85.88, "elapsed_time": "6:19:57", "remaining_time": "1:02:29"}
+{"current_steps": 1530, "total_steps": 1770, "loss": 1.4659, "accuracy": 0.45625001192092896, "learning_rate": 2.234379314486973e-07, "epoch": 2.5910245554614733, "percentage": 86.44, "elapsed_time": "6:23:20", "remaining_time": "1:00:07"}
+{"current_steps": 1540, "total_steps": 1770, "loss": 1.4537, "accuracy": 0.5375000238418579, "learning_rate": 2.0546013825709783e-07, "epoch": 2.6079593564775614, "percentage": 87.01, "elapsed_time": "6:26:46", "remaining_time": "0:57:45"}
+{"current_steps": 1550, "total_steps": 1770, "loss": 1.35, "accuracy": 0.512499988079071, "learning_rate": 1.88205258825217e-07, "epoch": 2.6248941574936495, "percentage": 87.57, "elapsed_time": "6:30:14", "remaining_time": "0:55:23"}
+{"current_steps": 1560, "total_steps": 1770, "loss": 1.4545, "accuracy": 0.4749999940395355, "learning_rate": 1.7167872944552245e-07, "epoch": 2.6418289585097376, "percentage": 88.14, "elapsed_time": "6:33:29", "remaining_time": "0:52:58"}
+{"current_steps": 1570, "total_steps": 1770, "loss": 1.42, "accuracy": 0.4625000059604645, "learning_rate": 1.5588575693777142e-07, "epoch": 2.6587637595258258, "percentage": 88.7, "elapsed_time": "6:36:55", "remaining_time": "0:50:33"}
+{"current_steps": 1580, "total_steps": 1770, "loss": 1.553, "accuracy": 0.44999998807907104, "learning_rate": 1.4083131700856428e-07, "epoch": 2.675698560541914, "percentage": 89.27, "elapsed_time": "6:40:22", "remaining_time": "0:48:08"}
+{"current_steps": 1590, "total_steps": 1770, "loss": 1.4335, "accuracy": 0.543749988079071, "learning_rate": 1.2652015268370315e-07, "epoch": 2.6926333615580016, "percentage": 89.83, "elapsed_time": "6:43:38", "remaining_time": "0:45:41"}
+{"current_steps": 1600, "total_steps": 1770, "loss": 1.5327, "accuracy": 0.5375000238418579, "learning_rate": 1.1295677281386502e-07, "epoch": 2.7095681625740897, "percentage": 90.4, "elapsed_time": "6:47:03", "remaining_time": "0:43:14"}
+{"current_steps": 1610, "total_steps": 1770, "loss": 1.4981, "accuracy": 0.48124998807907104, "learning_rate": 1.0014545065404973e-07, "epoch": 2.726502963590178, "percentage": 90.96, "elapsed_time": "6:50:25", "remaining_time": "0:40:47"}
+{"current_steps": 1620, "total_steps": 1770, "loss": 1.4143, "accuracy": 0.5562499761581421, "learning_rate": 8.809022251725502e-08, "epoch": 2.743437764606266, "percentage": 91.53, "elapsed_time": "6:53:45", "remaining_time": "0:38:18"}
+{"current_steps": 1630, "total_steps": 1770, "loss": 1.4265, "accuracy": 0.5625, "learning_rate": 7.679488650280509e-08, "epoch": 2.7603725656223537, "percentage": 92.09, "elapsed_time": "6:57:10", "remaining_time": "0:35:49"}
+{"current_steps": 1640, "total_steps": 1770, "loss": 1.4103, "accuracy": 0.4312500059604645, "learning_rate": 6.626300129972563e-08, "epoch": 2.777307366638442, "percentage": 92.66, "elapsed_time": "7:00:17", "remaining_time": "0:33:18"}
+{"current_steps": 1650, "total_steps": 1770, "loss": 1.4274, "accuracy": 0.5625, "learning_rate": 5.649788506555065e-08, "epoch": 2.79424216765453, "percentage": 93.22, "elapsed_time": "7:03:31", "remaining_time": "0:30:48"}
+{"current_steps": 1660, "total_steps": 1770, "loss": 1.4234, "accuracy": 0.48750001192092896, "learning_rate": 4.7502614380908474e-08, "epoch": 2.811176968670618, "percentage": 93.79, "elapsed_time": "7:06:53", "remaining_time": "0:28:17"}
+{"current_steps": 1670, "total_steps": 1770, "loss": 1.4267, "accuracy": 0.48124998807907104, "learning_rate": 3.9280023280222066e-08, "epoch": 2.828111769686706, "percentage": 94.35, "elapsed_time": "7:10:10", "remaining_time": "0:25:45"}
+{"current_steps": 1680, "total_steps": 1770, "loss": 1.5849, "accuracy": 0.44999998807907104, "learning_rate": 3.1832702358818855e-08, "epoch": 2.8450465707027943, "percentage": 94.92, "elapsed_time": "7:13:44", "remaining_time": "0:23:14"}
+{"current_steps": 1690, "total_steps": 1770, "loss": 1.4407, "accuracy": 0.48750001192092896, "learning_rate": 2.5162997956746647e-08, "epoch": 2.8619813717188824, "percentage": 95.48, "elapsed_time": "7:17:17", "remaining_time": "0:20:42"}
+{"current_steps": 1700, "total_steps": 1770, "loss": 1.4203, "accuracy": 0.5249999761581421, "learning_rate": 1.9273011419536914e-08, "epoch": 2.8789161727349706, "percentage": 96.05, "elapsed_time": "7:20:16", "remaining_time": "0:18:07"}
+{"current_steps": 1710, "total_steps": 1770, "loss": 1.4457, "accuracy": 0.45625001192092896, "learning_rate": 1.4164598436159083e-08, "epoch": 2.8958509737510583, "percentage": 96.61, "elapsed_time": "7:23:27", "remaining_time": "0:15:33"}
+{"current_steps": 1720, "total_steps": 1770, "loss": 1.4405, "accuracy": 0.53125, "learning_rate": 9.839368454371556e-09, "epoch": 2.9127857747671464, "percentage": 97.18, "elapsed_time": "7:26:48", "remaining_time": "0:12:59"}
+{"current_steps": 1730, "total_steps": 1770, "loss": 1.4164, "accuracy": 0.512499988079071, "learning_rate": 6.298684173650649e-09, "epoch": 2.9297205757832345, "percentage": 97.74, "elapsed_time": "7:30:02", "remaining_time": "0:10:24"}
+{"current_steps": 1740, "total_steps": 1770, "loss": 1.4519, "accuracy": 0.550000011920929, "learning_rate": 3.543661115860686e-09, "epoch": 2.9466553767993227, "percentage": 98.31, "elapsed_time": "7:33:04", "remaining_time": "0:07:48"}
+{"current_steps": 1750, "total_steps": 1770, "loss": 1.4132, "accuracy": 0.512499988079071, "learning_rate": 1.575167273800693e-09, "epoch": 2.963590177815411, "percentage": 98.87, "elapsed_time": "7:36:09", "remaining_time": "0:05:12"}
+{"current_steps": 1760, "total_steps": 1770, "loss": 1.5085, "accuracy": 0.543749988079071, "learning_rate": 3.9382283773564676e-10, "epoch": 2.9805249788314985, "percentage": 99.44, "elapsed_time": "7:39:31", "remaining_time": "0:02:36"}
+{"current_steps": 1770, "total_steps": 1770, "loss": 1.5332, "accuracy": 0.550000011920929, "learning_rate": 0.0, "epoch": 2.9974597798475866, "percentage": 100.0, "elapsed_time": "7:42:46", "remaining_time": "0:00:00"}
+{"current_steps": 1770, "total_steps": 1770, "epoch": 2.9974597798475866, "percentage": 100.0, "elapsed_time": "7:42:46", "remaining_time": "0:00:00"}